GLM 5.3 FlashConfidentialnear/z-ai/glm-5.3-flashGLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear…
- Context
- —
- Input /1M
- $0.21
- Output /1M
- $0.70
Every model, one place
One account, every major provider. Switch models mid-conversation in the
app, or call any of them by ID through the OpenAI-compatible API — point
your client at https://api.privateer.pro/v1 and set
model. Chat, image, video, music, sound effects, voices and
3D meshes — every one of them with its ID and what it costs.
Chat billed per token
Media billed per unit of output
Prices at the developer-API rate
No models match . Try a provider, model name or ID.
Type
Input
Features
Privacy
Provider
Offers
545 models
49+ chat providers
423 chat · 57 image · 30 video · 25 audio · 10 3D
21 confidential
54 on sale · up to 90% off
On sale now 54 models up to 90% off · in / out, USD per 1M tokens · provider promotions, billed through at the discounted rate
DeepSeek V4 Flash 0731−90%deepseek/deepseek-v4-flash-0731
In$0.02
Outfrom $0.18list $1.79
DeepSeek V4 Pro 0423−88%deepseek/deepseek-v4-pro
In$0.29
Out$0.58
Mercury 2.5−80%
inception/mercury-2.5
In$0.06
Out$0.21
Qwen3 235B A22B Instruct 2507−75%qwen/qwen3-235b-a22b-2507
In$0.12
Out$0.49
Ling 3.0 Flash VL−72%
inclusionai/ling-3.0-flash-vl
In$0.03
Out$0.09
GLM 5.3−70%z-ai/glm-5.3
Infrom $0.04list $1.96
Outfrom $1.85list $6.16
Solar Pro 4−70%
upstage/solar-pro4
In$0.13
Out$0.50
DeepSeek V4 Flash 0423−70%deepseek/deepseek-v4-flash
In$0.04
Outfrom $0.12list $1.79
Ling 3.0 Flash−65%
inclusionai/ling-3.0-flash
In$0.03
Out$0.09
LongCat 2.0−60%
meituan/longcat-2.0
In$0.42
Out$1.68
Qwen3 30B A3B Instruct 2507−55%qwen/qwen3-30b-a3b-instruct-2507
In$0.07
Out$0.27
GLM 5.2−54%z-ai/glm-5.2
In$0.03
Outfrom $2.52list $22.40
DeepSeek V4.1 Flash−53%deepseek/deepseek-v4.1-flash
In<$0.01
Outfrom $0.25list $3.36
DeepSeek V4 Flash Vision Exp−51%deepseek/deepseek-v4-flash-vision-exp
In$0.30
Out$0.91
Solar Mini 4−50%
upstage/solar-mini4
In$0.07
Out$0.28
Gemini 3.8 Flash−50%google/gemini-3.8-flash
Infrom $0.52list $1.05
Outfrom $2.63list $5.25
Gemini 3.8 Flash (batch)−50%google/gemini-3.8-flash:batch
In$0.52
Out$2.63
GLM 5.3 Flash−50%z-ai/glm-5.3-flash
Infrom $0.05list $0.21
Outfrom $0.35list $0.70
GLM 5.3 Flash (batch)−50%z-ai/glm-5.3-flash:batch
In$0.08
Out$0.28
Gemini 3.7 Flash−50%google/gemini-3.7-flash
Infrom $0.52list $1.05
Outfrom $2.63list $5.25
Gemini 3.7 Flash (batch)−50%google/gemini-3.7-flash:batch
In$0.52
Out$2.63
DeepSeek V4 Pro 0813−50%deepseek/deepseek-v4-pro-0813
Infrom $0.27list $0.77
Outfrom $2.77list $7.00
GPT-5.6 Sol Pro−50%openai/gpt-5.6-sol-pro
Infrom $1.40list $2.80
Outfrom $7.00list $14.00
GPT-5.6 Sol Pro (batch)−50%openai/gpt-5.6-sol-pro:batch
In$1.40
Out$7.00
GPT-5.6 Sol−50%openai/gpt-5.6-sol
Infrom $1.40list $2.80
Outfrom $7.00list $14.00
GPT-5.6 Sol (batch)−50%openai/gpt-5.6-sol:batch
In$1.40
Out$7.00
MiniMax M3−50%minimax/minimax-m3
Infrom $0.32list $0.42
Outfrom $1.34list $1.68
Ling 3.0 Flash Fin−44%
inclusionai/ling-3.0-flash-fin
In$0.06
Out$0.17
Laguna XS 2.1−40%
poolside/laguna-xs-2.1
In$0.08
Out$0.17
GLM 5−40%z-ai/glm-5
In$0.84
Out$2.69
Qwen3 Coder Next−40%qwen/qwen3-coder-next
In$0.17
Out$1.12
DeepSeek V3.1 Terminus−40%deepseek/deepseek-v3.1-terminus
In$0.38
Out$1.40
GLM 5.3 (batch)−38%z-ai/glm-5.3:batch
In$0.63
Out$2.80
Kimi K2.6−37%moonshotai/kimi-k2.6
Infrom $0.65list $1.33
Outfrom $3.36list $5.60
Kimi K3−35%moonshotai/kimi-k3
Infrom $0.82list $0.94
Outfrom $13.65list $19.60
GLM 5.1−31%z-ai/glm-5.1
Infrom $1.35list $1.96
Outfrom $4.25list $6.16
DeepSeek V4.1 Flash (batch)−30%deepseek/deepseek-v4.1-flash:batch
In$0.16
Out$0.47
MiMo-V2.5-Pro−30%
xiaomi/mimo-v2.5-pro
Infrom $0.43list $0.61
Outfrom $0.85list $1.22
MiniMax M2.7−30%minimax/minimax-m2.7
In$0.29
Out$1.18
DeepSeek V3.2−28%deepseek/deepseek-v3.2
Infrom $0.29list $0.39
Outfrom $0.43list $0.59
GLM 4.7−27%z-ai/glm-4.7
Infrom $0.56list $0.84
Outfrom $2.45list $3.08
Mistral Nemo−27%mistralai/mistral-nemo
In$0.03
Out$0.04
Qwen3.8 27B−25%qwen/qwen3.8-27b
Infrom $0.03list $0.59
Outfrom $2.09list $3.57
Kimi K2.7 Code−25%moonshotai/kimi-k2.7-code
In$0.94
Outfrom $4.20list $4.69
Gemma 4 26B A4B −25%google/gemma-4-26b-a4b-it
Infrom $0.06list $0.09
Out$0.31
Llama 3.3 70B Instruct−25%meta-llama/llama-3.3-70b-instruct
Infrom $0.14list $0.31
Outfrom $0.45list $0.70
Qwen3.8 2.4T A95B−20%qwen/qwen3.8-2.4t-a95b
In$2.80
Out$8.40
Nemotron 3.5 Lightning−15%
nvidia/nemotron-3.5-lightning
Infrom $0.05list $0.08
Out$0.22
MiMo-V2.5−15%
xiaomi/mimo-v2.5
Infrom $0.17list $0.20
Outfrom $0.33list $0.39
MiniMax M2−15%minimax/minimax-m2
Infrom $0.36list $0.42
Outfrom $1.43list $1.68
Laguna S 2.1−10%
poolside/laguna-s-2.1
In$0.13
Out$0.25
MiniMax M2.5−10%minimax/minimax-m2.5
In$0.38
Outfrom $1.33list $1.51
DeepSeek V3−10%deepseek/deepseek-chat
In$0.36
Outfrom $1.25list $1.44
Kimi K2.5−5%moonshotai/kimi-k2.5
In$0.63
Out$3.15
Chat & reasoning 423 models 49 providers · search, filter or sort the whole list
Confidential 21 of these models run inside an attested hardware enclave — Intel TDX, NVIDIA Confidential Computing or AMD SEV-SNP, served by Tinfoil, Phala and NEAR AI. The prompt is decrypted only in there, and the app verifies the hardware attestation on every response; “verified” is claimed only where your own device does the attesting. Context and feature tags are not published per host, so those cells read “—”. What confidential compute means →
GLM 5.3 FlashConfidentialQwen3-VL-30B-A3B-InstructConfidentialnear/Qwen/Qwen3-VL-30B-A3B-InstructQwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct…
- Context
- —
- Input /1M
- $0.21
- Output /1M
- $0.77
Qwen 3.6 35B A3B FP8Confidentialnear/Qwen/Qwen3.6-35B-A3B-FP8
- Context
- —
- Input /1M
- $0.24
- Output /1M
- $1.54
Qwen 3.8 27BConfidentialnear/Qwen/Qwen3.8-27BQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal…
- Context
- —
- Input /1M
- $0.62
- Output /1M
- $4.62
Kimi K2.6Confidentialnear/moonshotai/kimi-k2.6Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent…
- Context
- —
- Input /1M
- $1.13
- Output /1M
- $5.39
Kimi K3Confidentialnear/moonshotai/kimi-k3Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and…
- Context
- —
- Input /1M
- $4.62
- Output /1M
- $23.10
Nemotron 3.5 LightningConfidential
phala/nvidia/nemotron-3.5-lightningNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for…
- Context
- —
- Input /1M
- $0.10
- Output /1M
- $0.28
Qwen2.5 7B InstructConfidential
phala/qwen/qwen-2.5-7b-instructQwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge…
- Context
- —
- Input /1M
- $0.14
- Output /1M
- $0.28
Gemma-4 26B-A4B Uncensored (Heretic)Confidential
phala/phala/gemma-4-26b-a4b-uncensored
- Context
- —
- Input /1M
- $0.21
- Output /1M
- $0.98
Qwen3.8 27BConfidential
phala/qwen/qwen3.8-27bQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal…
- Context
- —
- Input /1M
- $0.28
- Output /1M
- $3.50
Muse Glimmer 30BConfidential
phala/meta/muse-glimmer-30bMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous…
- Context
- —
- Input /1M
- $0.42
- Output /1M
- $1.54
Qwen3.8 27B Uncensored (Aggressive)Confidential
phala/phala/qwen3.8-27b-uncensored
- Context
- —
- Input /1M
- $0.42
- Output /1M
- $2.10
Qwen3.6 27BConfidential
phala/qwen/qwen3.6-27bQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal…
- Context
- —
- Input /1M
- $0.45
- Output /1M
- $3.78
GLM 5.3Confidential
phala/z-ai/glm-5.3GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and…
- Context
- —
- Input /1M
- $1.96
- Output /1M
- $6.16
GPT-OSS 120BConfidentialtinfoil/gpt-oss-120bgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and…
- Context
- —
- Input /1M
- $0.21
- Output /1M
- $0.84
Gemma 4 31BConfidentialtinfoil/gemma4-31b
- Context
- —
- Input /1M
- $0.56
- Output /1M
- $1.40
GLM 5.3 FlashConfidentialtinfoil/glm-5-3-flash
- Context
- —
- Input /1M
- $0.56
- Output /1M
- $1.75
DeepSeek V4.1 FlashConfidentialtinfoil/deepseek-v4-1-flash
- Context
- —
- Input /1M
- $0.91
- Output /1M
- $2.03
Llama 3.3 70BConfidentialtinfoil/llama3-3-70b
- Context
- —
- Input /1M
- $2.45
- Output /1M
- $3.85
GLM 5.3Confidentialtinfoil/glm-5-3
- Context
- —
- Input /1M
- $2.52
- Output /1M
- $8.05
Kimi K3Confidentialtinfoil/kimi-k3Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and…
- Context
- —
- Input /1M
- $5.60
- Output /1M
- $28.00
gpt-oss-20bopenai/gpt-oss-20bgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture…
- Context
- 131K
- Input /1M
- $0.03
- Output /1M
- $0.13
gpt-oss-20b (batch)openai/gpt-oss-20b:batchgpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture…
- Context
- 131K
- Input /1M
- $0.03
- Output /1M
- $0.16
GPT-5 Nano (batch)openai/gpt-5-nano:batchGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency…
- Context
- 400K
- Input /1M
- $0.03
- Output /1M
- $0.28
gpt-oss-120b (batch)openai/gpt-oss-120b:batchgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and…
- Context
- 131K
- Input /1M
- $0.04
- Output /1M
- $0.19
gpt-oss-120bopenai/gpt-oss-120bgpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and…
- Context
- 131K
- Input /1M
- $0.05
- Output /1M
- $0.24
GPT-6 Luna Pro (batch)openai/gpt-6-luna-pro:batchGPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $0.07
- Output /1M
- $0.35
GPT-6 Luna (batch)openai/gpt-6-luna:batchGPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and…
- Context
- 1.1M
- Input /1M
- $0.07
- Output /1M
- $0.35
GPT-5 Nanoopenai/gpt-5-nanoGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency…
- Context
- 400K
- Input /1M
- $0.07
- Output /1M
- $0.56
GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batchFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a…
- Context
- 1.0M
- Input /1M
- $0.07
- Output /1M
- $0.28
gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20bgpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE)…
- Context
- 131K
- Input /1M
- $0.10
- Output /1M
- $0.42
GPT-4o-mini (batch)openai/gpt-4o-mini:batchGPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model…
- Context
- 128K
- Input /1M
- $0.10
- Output /1M
- $0.42
GPT-6 Luna Proopenai/gpt-6-luna-proGPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $0.14
- Output /1M
- $0.70
GPT-6 Lunaopenai/gpt-6-lunaGPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and…
- Context
- 1.1M
- Input /1M
- $0.14
- Output /1M
- $0.70
GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batchGPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $0.14
- Output /1M
- $0.84
GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batchGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat…
- Context
- 1.1M
- Input /1M
- $0.14
- Output /1M
- $0.84
GPT-5.4 Nano (batch)openai/gpt-5.4-nano:batchGPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It…
- Context
- 400K
- Input /1M
- $0.14
- Output /1M
- $0.88
GPT-4.1 Nanoopenai/gpt-4.1-nanoFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a…
- Context
- 1.0M
- Input /1M
- $0.14
- Output /1M
- $0.56
GPT-5 Mini (batch)openai/gpt-5-mini:batchGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and…
- Context
- 400K
- Input /1M
- $0.17
- Output /1M
- $1.40
GPT-4o-miniopenai/gpt-4o-miniGPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model…
- Context
- 128K
- Input /1M
- $0.21
- Output /1M
- $0.84
GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model…
- Context
- 128K
- Input /1M
- $0.21
- Output /1M
- $0.84
GPT-5.6 Luna Proopenai/gpt-5.6-luna-proGPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $0.28
- Output /1M
- $1.68
GPT-5.6 Lunaopenai/gpt-5.6-lunaGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat…
- Context
- 1.1M
- Input /1M
- $0.28
- Output /1M
- $1.68
GPT-5.4 Nanoopenai/gpt-5.4-nanoGPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It…
- Context
- 400K
- Input /1M
- $0.28
- Output /1M
- $1.75
GPT-4.1 Mini (batch)openai/gpt-4.1-mini:batchGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million…
- Context
- 1.0M
- Input /1M
- $0.28
- Output /1M
- $1.12
GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-miniGPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex
- Context
- 400K
- Input /1M
- $0.35
- Output /1M
- $2.80
GPT-5 Miniopenai/gpt-5-miniGPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and…
- Context
- 400K
- Input /1M
- $0.35
- Output /1M
- $2.80
GPT-3.5 Turbo (batch)openai/gpt-3.5-turbo:batchGPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional…
- Context
- 16K
- Input /1M
- $0.35
- Output /1M
- $1.05
GPT-5.4 Mini (batch)openai/gpt-5.4-mini:batchGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text…
- Context
- 400K
- Input /1M
- $0.52
- Output /1M
- $3.15
GPT-4.1 Miniopenai/gpt-4.1-miniGPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million…
- Context
- 1.0M
- Input /1M
- $0.56
- Output /1M
- $2.24
GPT-3.5 Turboopenai/gpt-3.5-turboGPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional…
- Context
- 16K
- Input /1M
- $0.70
- Output /1M
- $2.10
o4 Mini (batch)openai/o4-mini:batchOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and…
- Context
- 200K
- Input /1M
- $0.77
- Output /1M
- $3.08
o3 Mini (batch)openai/o3-mini:batchOpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding…
- Context
- 200K
- Input /1M
- $0.77
- Output /1M
- $3.08
GPT-5.1 (batch)openai/gpt-5.1:batchGPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a…
- Context
- 400K
- Input /1M
- $0.88
- Output /1M
- $7.00
GPT-5 (batch)openai/gpt-5:batchGPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex…
- Context
- 400K
- Input /1M
- $0.88
- Output /1M
- $7.00
GPT-5.4 Miniopenai/gpt-5.4-miniGPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text…
- Context
- 400K
- Input /1M
- $1.05
- Output /1M
- $6.30
GPT-5.2 (batch)openai/gpt-5.2:batchGPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses…
- Context
- 400K
- Input /1M
- $1.22
- Output /1M
- $9.80
GPT-6 Sol Pro (batch)openai/gpt-6-sol-pro:batchGPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost…
- Context
- 1.1M
- Input /1M
- $1.40
- Output /1M
- $7.00
GPT-6 Sol (batch)openai/gpt-6-sol:batchGPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna…
- Context
- 1.1M
- Input /1M
- $1.40
- Output /1M
- $7.00
GPT-5.6 Terra Pro (batch)openai/gpt-5.6-terra-pro:batchGPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex…
- Context
- 1.1M
- Input /1M
- $1.40
- Output /1M
- $8.40
GPT-5.6 Terra (batch)openai/gpt-5.6-terra:batchGPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is…
- Context
- 1.1M
- Input /1M
- $1.40
- Output /1M
- $8.40
GPT-5.6 Sol Pro (batch)−50%openai/gpt-5.6-sol-pro:batchGPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $1.40
- Output /1M
- $7.00
GPT-5.6 Sol (batch)−50%openai/gpt-5.6-sol:batchGPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is…
- Context
- 1.1M
- Input /1M
- $1.40
- Output /1M
- $7.00
o3 (batch)openai/o3:batcho3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also…
- Context
- 200K
- Input /1M
- $1.40
- Output /1M
- $5.60
GPT-4.1 (batch)openai/gpt-4.1:batchGPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context…
- Context
- 1.0M
- Input /1M
- $1.40
- Output /1M
- $5.60
GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional…
- Context
- 4K
- Input /1M
- $1.40
- Output /1M
- $2.80
o4 Mini Highopenai/o4-mini-highOpenAI o4-mini-high is the same model as o4-mini with reasoningeffort set to high. OpenAI o4-mini is a compact reasoning model in the o-series…
- Context
- 200K
- Input /1M
- $1.54
- Output /1M
- $6.16
o4 Miniopenai/o4-miniOpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and…
- Context
- 200K
- Input /1M
- $1.54
- Output /1M
- $6.16
o3 Mini Highopenai/o3-mini-highOpenAI o3-mini-high is the same model as o3-mini with reasoningeffort set to high. o3-mini is a cost-efficient language model optimized for STEM…
- Context
- 200K
- Input /1M
- $1.54
- Output /1M
- $6.16
o3 Miniopenai/o3-miniOpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding…
- Context
- 200K
- Input /1M
- $1.54
- Output /1M
- $6.16
GPT-5.4 (batch)openai/gpt-5.4:batchGPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K…
- Context
- 1.1M
- Input /1M
- $1.75
- Output /1M
- $10.50
GPT-5.1-Codex-Maxopenai/gpt-5.1-codex-maxGPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an…
- Context
- 400K
- Input /1M
- $1.75
- Output /1M
- $14.00
GPT-5.1openai/gpt-5.1GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a…
- Context
- 400K
- Input /1M
- $1.75
- Output /1M
- $14.00
GPT-5.1-Codexopenai/gpt-5.1-codexGPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive…
- Context
- 400K
- Input /1M
- $1.75
- Output /1M
- $14.00
GPT-5openai/gpt-5GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex…
- Context
- 400K
- Input /1M
- $1.75
- Output /1M
- $14.00
GPT-4o (batch)openai/gpt-4o:batchGPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level…
- Context
- 128K
- Input /1M
- $1.75
- Output /1M
- $7.00
GPT-3.5 Turbo Instructopenai/gpt-3.5-turbo-instructThis model is a variant of GPT-3.5 Turbo tuned for instructional prompts and omitting chat-related optimizations. Training data: up to Sep 2021.
- Context
- 4K
- Input /1M
- $2.10
- Output /1M
- $2.80
GPT-5.3-Codexopenai/gpt-5.3-codexGPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the…
- Context
- 400K
- Input /1M
- $2.45
- Output /1M
- $19.60
GPT-5.2-Codexopenai/gpt-5.2-codexGPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive…
- Context
- 400K
- Input /1M
- $2.45
- Output /1M
- $19.60
GPT-5.2 Chatopenai/gpt-5.2-chatGPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general…
- Context
- 128K
- Input /1M
- $2.45
- Output /1M
- $19.60
GPT-5.2openai/gpt-5.2GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses…
- Context
- 400K
- Input /1M
- $2.45
- Output /1M
- $19.60
GPT-6.1 Sol Proopenai/gpt-6.1-sol-proGPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $2.80
- Output /1M
- $14.00
GPT-6.1 Solopenai/gpt-6.1-solGPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding…
- Context
- 1.1M
- Input /1M
- $2.80
- Output /1M
- $14.00
GPT-6 Sol Proopenai/gpt-6-sol-proGPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks. Cost…
- Context
- 1.1M
- Input /1M
- $2.80
- Output /1M
- $14.00
GPT-6 Solopenai/gpt-6-solGPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna…
- Context
- 1.1M
- Input /1M
- $2.80
- Output /1M
- $14.00
GPT-5.6 Terra Proopenai/gpt-5.6-terra-proGPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex…
- Context
- 1.1M
- Input /1M
- $2.80
- Output /1M
- $16.80
GPT-5.6 Terraopenai/gpt-5.6-terraGPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is…
- Context
- 1.1M
- Input /1M
- $2.80
- Output /1M
- $16.80
GPT-5.6 Sol Pro−50%openai/gpt-5.6-sol-proGPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $2.80from $1.40
- Output /1M
- $14.00from $7.00
GPT-5.6 Sol−50%openai/gpt-5.6-solGPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is…
- Context
- 1.1M
- Input /1M
- $2.80from $1.40
- Output /1M
- $14.00from $7.00
o3openai/o3o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also…
- Context
- 200K
- Input /1M
- $2.80
- Output /1M
- $11.20
GPT-4.1openai/gpt-4.1GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context…
- Context
- 1.0M
- Input /1M
- $2.80
- Output /1M
- $11.20
GPT-5.5 (batch)openai/gpt-5.5:batchGPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability…
- Context
- 1.1M
- Input /1M
- $3.50
- Output /1M
- $21.00
GPT-5.4openai/gpt-5.4GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K…
- Context
- 1.1M
- Input /1M
- $3.50
- Output /1M
- $21.00
GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve…
- Context
- 128K
- Input /1M
- $3.50
- Output /1M
- $14.00
GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the responeformat…
- Context
- 128K
- Input /1M
- $3.50
- Output /1M
- $14.00
GPT-4oopenai/gpt-4oGPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level…
- Context
- 128K
- Input /1M
- $3.50
- Output /1M
- $14.00
GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16kThis model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a…
- Context
- 16K
- Input /1M
- $4.20
- Output /1M
- $5.60
GPT-6 Astra (batch)openai/gpt-6-astra:batchGPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research…
- Context
- 1.1M
- Input /1M
- $7.00
- Output /1M
- $35.00
GPT-6 Astra Pro (batch)openai/gpt-6-astra-pro:batchGPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $7.00
- Output /1M
- $35.00
GPT Chat Latestopenai/gpt-chat-latestGPT Chat Latest points to OpenAI's stable API alias chat-latest that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI…
- Context
- 400K
- Input /1M
- $7.00
- Output /1M
- $42.00
GPT-5.5openai/gpt-5.5GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability…
- Context
- 1.1M
- Input /1M
- $7.00
- Output /1M
- $42.00
GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level…
- Context
- 128K
- Input /1M
- $7.00
- Output /1M
- $21.00
GPT-4 Turbo (batch)openai/gpt-4-turbo:batchThe latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December…
- Context
- 128K
- Input /1M
- $7.00
- Output /1M
- $21.00
GPT-5 Pro (batch)openai/gpt-5-pro:batchGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex…
- Context
- 400K
- Input /1M
- $10.50
- Output /1M
- $84.00
GPT-6 Astraopenai/gpt-6-astraGPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research…
- Context
- 1.1M
- Input /1M
- $14.00
- Output /1M
- $70.00
GPT-6 Astra Proopenai/gpt-6-astra-proGPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with reasoning.mode set to pro for higher-quality responses on complex tasks…
- Context
- 1.1M
- Input /1M
- $14.00
- Output /1M
- $70.00
GPT-4 Turboopenai/gpt-4-turboThe latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December…
- Context
- 128K
- Input /1M
- $14.00
- Output /1M
- $42.00
GPT-5.2 Pro (batch)openai/gpt-5.2-pro:batchGPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is…
- Context
- 400K
- Input /1M
- $14.70
- Output /1M
- $117.60
GPT-5.5 Pro (batch)openai/gpt-5.5-pro:batchGPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token…
- Context
- 1.1M
- Input /1M
- $21.00
- Output /1M
- $126.00
GPT-5.4 Pro (batch)openai/gpt-5.4-pro:batchGPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex…
- Context
- 1.1M
- Input /1M
- $21.00
- Output /1M
- $126.00
GPT-5 Proopenai/gpt-5-proGPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex…
- Context
- 400K
- Input /1M
- $21.00
- Output /1M
- $168.00
o1openai/o1The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained…
- Context
- 200K
- Input /1M
- $21.00
- Output /1M
- $84.00
o3 Proopenai/o3-proThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses…
- Context
- 200K
- Input /1M
- $28.00
- Output /1M
- $112.00
GPT-5.2 Proopenai/gpt-5.2-proGPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is…
- Context
- 400K
- Input /1M
- $29.40
- Output /1M
- $235.20
GPT-5.5 Proopenai/gpt-5.5-proGPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token…
- Context
- 1.1M
- Input /1M
- $42.00
- Output /1M
- $252.00
GPT-5.4 Proopenai/gpt-5.4-proGPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex…
- Context
- 1.1M
- Input /1M
- $42.00
- Output /1M
- $252.00
GPT-4openai/gpt-4OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous…
- Context
- 8K
- Input /1M
- $42.00
- Output /1M
- $84.00
o1-proopenai/o1-proThe o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses…
- Context
- 200K
- Input /1M
- $210.00
- Output /1M
- $840.00
Claude Haiku 4.5 (batch)anthropic/claude-haiku-4.5:batchClaude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of…
- Context
- 200K
- Input /1M
- $0.70
- Output /1M
- $3.50
Claude Sonnet 5.5 (batch)anthropic/claude-sonnet-5.5:batchClaude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially…
- Context
- 1M
- Input /1M
- $1.40
- Output /1M
- $7.00
Claude Sonnet 5 (batch)anthropic/claude-sonnet-5:batchSonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports…
- Context
- 1M
- Input /1M
- $1.40
- Output /1M
- $7.00
Claude Haiku 4.5anthropic/claude-haiku-4.5Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of…
- Context
- 200K
- Input /1M
- $1.40
- Output /1M
- $7.00
Claude Sonnet 4.6 (batch)anthropic/claude-sonnet-4.6:batchSonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at…
- Context
- 1M
- Input /1M
- $2.10
- Output /1M
- $10.50
Claude Sonnet 4.5 (batch)anthropic/claude-sonnet-4.5:batchClaude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers…
- Context
- 1M
- Input /1M
- $2.10
- Output /1M
- $10.50
Claude Sonnet 5.5anthropic/claude-sonnet-5.5Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially…
- Context
- 1M
- Input /1M
- $2.80
- Output /1M
- $14.00
Claude Opus 5.5 (batch)anthropic/claude-opus-5.5:batchClaude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is…
- Context
- 1M
- Input /1M
- $2.80
- Output /1M
- $14.00
Claude Sonnet 5anthropic/claude-sonnet-5Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports…
- Context
- 1M
- Input /1M
- $2.80
- Output /1M
- $14.00
Claude Opus 5 (batch)anthropic/claude-opus-5:batchClaude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end…
- Context
- 1M
- Input /1M
- $3.50
- Output /1M
- $17.50
Claude Opus 4.8 (batch)anthropic/claude-opus-4.8:batchClaude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text…
- Context
- 1M
- Input /1M
- $3.50
- Output /1M
- $17.50
Claude Opus 4.7 (batch)anthropic/claude-opus-4.7:batchOpus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic…
- Context
- 1M
- Input /1M
- $3.50
- Output /1M
- $17.50
Claude Opus 4.6 (batch)anthropic/claude-opus-4.6:batchOpus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows…
- Context
- 1M
- Input /1M
- $3.50
- Output /1M
- $17.50
Claude Opus 4.5 (batch)anthropic/claude-opus-4.5:batchClaude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer…
- Context
- 200K
- Input /1M
- $3.50
- Output /1M
- $17.50
Claude Sonnet 4.6anthropic/claude-sonnet-4.6Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at…
- Context
- 1M
- Input /1M
- $4.20
- Output /1M
- $21.00
Claude Sonnet 4.5anthropic/claude-sonnet-4.5Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers…
- Context
- 1M
- Input /1M
- $4.20
- Output /1M
- $21.00
Claude Sonnet 4anthropic/claude-sonnet-4Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved…
- Context
- 200K
- Input /1M
- $4.20
- Output /1M
- $21.00
Claude Opus 5.5anthropic/claude-opus-5.5Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is…
- Context
- 1M
- Input /1M
- $5.60
- Output /1M
- $28.00
Claude Fable 5.1 (batch)anthropic/claude-fable-5.1:batchClaude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and…
- Context
- 1M
- Input /1M
- $7.00
- Output /1M
- $35.00
Claude Opus 5anthropic/claude-opus-5Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end…
- Context
- 1M
- Input /1M
- $7.00
- Output /1M
- $35.00
Claude Fable 5 (batch)anthropic/claude-fable-5:batchClaude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs…
- Context
- 1M
- Input /1M
- $7.00
- Output /1M
- $35.00
Claude Opus 4.8anthropic/claude-opus-4.8Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text…
- Context
- 1M
- Input /1M
- $7.00
- Output /1M
- $35.00
Claude Opus 4.7anthropic/claude-opus-4.7Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic…
- Context
- 1M
- Input /1M
- $7.00
- Output /1M
- $35.00
Claude Opus 4.6anthropic/claude-opus-4.6Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows…
- Context
- 1M
- Input /1M
- $7.00
- Output /1M
- $35.00
Claude Opus 4.5anthropic/claude-opus-4.5Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer…
- Context
- 200K
- Input /1M
- $7.00
- Output /1M
- $35.00
Claude Opus 4.1 (batch)anthropic/claude-opus-4.1:batchClaude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It…
- Context
- 200K
- Input /1M
- $10.50
- Output /1M
- $52.50
Claude Fable 5.1anthropic/claude-fable-5.1Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and…
- Context
- 1M
- Input /1M
- $14.00
- Output /1M
- $70.00
Claude Fable 5anthropic/claude-fable-5Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs…
- Context
- 1M
- Input /1M
- $14.00
- Output /1M
- $70.00
Claude Opus 4.1anthropic/claude-opus-4.1Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It…
- Context
- 200K
- Input /1M
- $21.00
- Output /1M
- $105.00
Gemini 2.5 Flash Lite (batch)google/gemini-2.5-flash-lite:batchGemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers…
- Context
- 1.0M
- Input /1M
- $0.07
- Output /1M
- $0.28
Gemma 3 4Bgoogle/gemma-3-4b-itGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over…
- Context
- 131K
- Input /1M
- $0.07
- Output /1M
- $0.14
Gemma 3 12Bgoogle/gemma-3-12b-itGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over…
- Context
- 131K
- Input /1M
- $0.07
- Output /1M
- $0.21
Gemma 4 26B A4B −25%google/gemma-4-26b-a4b-itGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate…
- Context
- 262K
- Input /1M
- $0.09from $0.06
- Output /1M
- $0.31
Gemma 3 27Bgoogle/gemma-3-27b-itGemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over…
- Context
- 131K
- Input /1M
- $0.11
- Output /1M
- $0.63
Gemma 4 31Bgoogle/gemma-4-31b-itGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token…
- Context
- 262K
- Input /1M
- $0.13
- Output /1M
- $0.48
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-liteGemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers…
- Context
- 1.0M
- Input /1M
- $0.14
- Output /1M
- $0.56
Gemini 3.1 Flash Lite (batch)google/gemini-3.1-flash-lite:batchGemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image…
- Context
- 1.0M
- Input /1M
- $0.17
- Output /1M
- $1.05
Gemini 3.5 Flash Lite (batch)google/gemini-3.5-flash-lite:batchGemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused…
- Context
- 1.0M
- Input /1M
- $0.21
- Output /1M
- $1.75
Gemini 2.5 Flash (batch)google/gemini-2.5-flash:batchGemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific…
- Context
- 1.0M
- Input /1M
- $0.21
- Output /1M
- $1.75
Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-liteGemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image…
- Context
- 1.0M
- Input /1M
- $0.35
- Output /1M
- $2.10
Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-previewGemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on…
- Context
- 1.0M
- Input /1M
- $0.35
- Output /1M
- $2.10
Gemini 3 Flash Preview (batch)google/gemini-3-flash-preview:batchGemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It…
- Context
- 1.0M
- Input /1M
- $0.35
- Output /1M
- $2.10
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-liteGemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused…
- Context
- 1.0M
- Input /1M
- $0.42
- Output /1M
- $3.50
Gemini 2.5 Flashgoogle/gemini-2.5-flashGemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific…
- Context
- 1.0M
- Input /1M
- $0.42
- Output /1M
- $3.50
Gemini 3.8 Flash (batch)−50%google/gemini-3.8-flash:batchGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and…
- Context
- 1.0M
- Input /1M
- $0.52
- Output /1M
- $2.63
Gemini 3.7 Flash (batch)−50%google/gemini-3.7-flash:batchGemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks…
- Context
- 1.0M
- Input /1M
- $0.52
- Output /1M
- $2.63
Gemini 3.6 Flash (batch)google/gemini-3.6-flash:batchGemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce…
- Context
- 1.0M
- Input /1M
- $0.52
- Output /1M
- $2.63
Gemini 3 Flash Previewgoogle/gemini-3-flash-previewGemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It…
- Context
- 1.0M
- Input /1M
- $0.70
- Output /1M
- $4.20
Gemini 2.5 Pro (batch)google/gemini-2.5-pro:batchGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs…
- Context
- 1.0M
- Input /1M
- $0.88
- Output /1M
- $7.00
Gemma 2 27Bgoogle/gemma-2-27b-itGemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited…
- Context
- 8K
- Input /1M
- $0.91
- Output /1M
- $0.91
Gemini 3.8 Flash−50%google/gemini-3.8-flashGemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and…
- Context
- 1.0M
- Input /1M
- $1.05from $0.52
- Output /1M
- $5.25from $2.63
Gemini 3.7 Flash−50%google/gemini-3.7-flashGemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks…
- Context
- 1.0M
- Input /1M
- $1.05from $0.52
- Output /1M
- $5.25from $2.63
Gemini 3.6 Flashgoogle/gemini-3.6-flashGemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce…
- Context
- 1.0M
- Input /1M
- $1.05
- Output /1M
- $5.25
Gemini 3.5 Flash (batch)google/gemini-3.5-flash:batchGemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is…
- Context
- 1.0M
- Input /1M
- $1.05
- Output /1M
- $6.30
Gemini 3.1 Pro Preview (batch)google/gemini-3.1-pro-preview:batchGemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability…
- Context
- 1.0M
- Input /1M
- $1.40
- Output /1M
- $8.40
Gemini 2.5 Progoogle/gemini-2.5-proGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs…
- Context
- 1.0M
- Input /1M
- $1.75
- Output /1M
- $14.00
Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-previewGemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs…
- Context
- 1.0M
- Input /1M
- $1.75
- Output /1M
- $14.00
Gemini 3.5 Flashgoogle/gemini-3.5-flashGemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is…
- Context
- 1.0M
- Input /1M
- $2.10
- Output /1M
- $12.60
Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtoolsGemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash…
- Context
- 1.0M
- Input /1M
- $2.80
- Output /1M
- $16.80
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-previewGemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability…
- Context
- 1.0M
- Input /1M
- $2.80
- Output /1M
- $16.80
Grok Build 0.1x-ai/grok-build-0.1Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs…
- Context
- 256K
- Input /1M
- $1.40
- Output /1M
- $2.80
Grok 4.3 (batch)x-ai/grok-4.3:batchGrok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows…
- Context
- 1M
- Input /1M
- $1.40
- Output /1M
- $2.80
Grok 4.3x-ai/grok-4.3Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows…
- Context
- 1M
- Input /1M
- $1.75
- Output /1M
- $3.50
Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agentGrok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel…
- Context
- 2M
- Input /1M
- $1.75
- Output /1M
- $3.50
Grok 4.20x-ai/grok-4.20Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest…
- Context
- 2M
- Input /1M
- $1.75
- Output /1M
- $3.50
Grok 4.7x-ai/grok-4.7Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running…
- Context
- 500K
- Input /1M
- $2.80
- Output /1M
- $8.40
Grok 4.6x-ai/grok-4.6Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.
- Context
- 500K
- Input /1M
- $2.80
- Output /1M
- $8.40
Grok 4.5x-ai/grok-4.5Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
- Context
- 500K
- Input /1M
- $2.80
- Output /1M
- $8.40
Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instructLlama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and…
- Context
- 60K
- Input /1M
- $0.04
- Output /1M
- $0.28
Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instructLlama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue…
- Context
- 131K
- Input /1M
- $0.07
- Output /1M
- $0.46
Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instructMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has…
- Context
- 131K
- Input /1M
- $0.07
- Output /1M
- $0.11
Llama 4 Scoutmeta-llama/llama-4-scoutLlama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of…
- Context
- 1.3M
- Input /1M
- $0.14
- Output /1M
- $0.42
Llama Guard 4 12Bmeta-llama/llama-guard-4-12bLlama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions…
- Context
- 164K
- Input /1M
- $0.25
- Output /1M
- $0.25
Llama 4 Maverickmeta-llama/llama-4-maverickLlama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with…
- Context
- 1.0M
- Input /1M
- $0.26
- Output /1M
- $0.91
Llama 3.3 70B Instruct−25%meta-llama/llama-3.3-70b-instructThe Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The…
- Context
- 131K
- Input /1M
- $0.31from $0.14
- Output /1M
- $0.70from $0.45
Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instructMeta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality…
- Context
- 131K
- Input /1M
- $0.56
- Output /1M
- $0.56
Mistral Nemo−27%mistralai/mistral-nemoA 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting…
- Context
- 131K
- Input /1M
- $0.03
- Output /1M
- $0.04
Mistral Small 3mistralai/mistral-small-24b-instruct-2501Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0…
- Context
- 33K
- Input /1M
- $0.07
- Output /1M
- $0.11
Mistral Small 4 (batch)mistralai/mistral-small-2603:batchMistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single…
- Context
- 262K
- Input /1M
- $0.10
- Output /1M
- $0.42
Ministral 3 8B 2512 (batch)mistralai/ministral-8b-2512:batchA balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
- Context
- 262K
- Input /1M
- $0.10
- Output /1M
- $0.10
Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instructMistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and…
- Context
- 256K
- Input /1M
- $0.13
- Output /1M
- $0.35
Ministral 3 3B 2512mistralai/ministral-3b-2512The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
- Context
- 131K
- Input /1M
- $0.14
- Output /1M
- $0.14
Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text…
- Context
- 33K
- Input /1M
- $0.14
- Output /1M
- $0.42
Mistral Small 4mistralai/mistral-small-2603Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single…
- Context
- 262K
- Input /1M
- $0.21
- Output /1M
- $0.84
Ministral 3 8B 2512mistralai/ministral-8b-2512A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
- Context
- 262K
- Input /1M
- $0.21
- Output /1M
- $0.21
Codestral 2508 (batch)mistralai/codestral-2508:batchMistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as…
- Context
- 256K
- Input /1M
- $0.21
- Output /1M
- $0.63
Ministral 3 14B 2512mistralai/ministral-14b-2512The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small…
- Context
- 262K
- Input /1M
- $0.28
- Output /1M
- $0.28
Mistral Medium 3.1 (batch)mistralai/mistral-medium-3.1:batchMistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver…
- Context
- 131K
- Input /1M
- $0.28
- Output /1M
- $1.40
Sabamistralai/mistral-sabaMistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually…
- Context
- 33K
- Input /1M
- $0.28
- Output /1M
- $0.84
Mistral Large 3 2512 (batch)mistralai/mistral-large-2512:batchMistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B…
- Context
- 262K
- Input /1M
- $0.35
- Output /1M
- $1.05
Codestral 2508mistralai/codestral-2508Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as…
- Context
- 256K
- Input /1M
- $0.42
- Output /1M
- $1.26
Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instructMistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal…
- Context
- 128K
- Input /1M
- $0.49
- Output /1M
- $0.78
Devstral 2 2512mistralai/devstral-2512Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model…
- Context
- 262K
- Input /1M
- $0.56
- Output /1M
- $2.80
Mistral Medium 3.1mistralai/mistral-medium-3.1Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver…
- Context
- 131K
- Input /1M
- $0.56
- Output /1M
- $2.80
Mistral Medium 3mistralai/mistral-medium-3Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced…
- Context
- 131K
- Input /1M
- $0.56
- Output /1M
- $2.80
Mistral Large 3 2512mistralai/mistral-large-2512Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B…
- Context
- 262K
- Input /1M
- $0.70
- Output /1M
- $2.10
Mistral Medium 3.5 (batch)mistralai/mistral-medium-3-5:batchMistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed…
- Context
- 262K
- Input /1M
- $1.05
- Output /1M
- $5.25
Mistral Medium 3.5mistralai/mistral-medium-3-5Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed…
- Context
- 262K
- Input /1M
- $2.10
- Output /1M
- $10.50
Mistral Large 2407mistralai/mistral-large-2407This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at…
- Context
- 131K
- Input /1M
- $2.80
- Output /1M
- $8.40
Mixtral 8x22B Instructmistralai/mixtral-8x22b-instructMistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency…
- Context
- 66K
- Input /1M
- $2.80
- Output /1M
- $8.40
Mistral Largemistralai/mistral-largeThis is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at…
- Context
- 128K
- Input /1M
- $2.80
- Output /1M
- $8.40
DeepSeek V4.1 Flash−53%deepseek/deepseek-v4.1-flashDeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED)…
- Context
- 1.0M
- Input /1M
- <$0.01
- Output /1M
- $3.36from $0.25
DeepSeek V4 Flash 0731−90%deepseek/deepseek-v4-flash-0731DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained…
- Context
- 1.0M
- Input /1M
- $0.02
- Output /1M
- $1.79from $0.18
DeepSeek V4 Flash 0423−70%deepseek/deepseek-v4-flashDeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters…
- Context
- 1.0M
- Input /1M
- $0.04
- Output /1M
- $1.79from $0.12
DeepSeek V4.1 Flash (batch)−30%deepseek/deepseek-v4.1-flash:batchDeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED)…
- Context
- 1.0M
- Input /1M
- $0.16
- Output /1M
- $0.47
DeepSeek V4 Pro 0423−88%deepseek/deepseek-v4-proDeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a…
- Context
- 1.0M
- Input /1M
- $0.29
- Output /1M
- $0.58
DeepSeek V4 Flash Vision Exp−51%deepseek/deepseek-v4-flash-vision-expDeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while…
- Context
- 1.0M
- Input /1M
- $0.30
- Output /1M
- $0.91
DeepSeek V3.1deepseek/deepseek-chat-v3.1DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt…
- Context
- 164K
- Input /1M
- $0.35
- Output /1M
- $1.33
DeepSeek V3−10%deepseek/deepseek-chatDeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions…
- Context
- 164K
- Input /1M
- $0.36
- Output /1M
- $1.44from $1.25
DeepSeek V3.2 Expdeepseek/deepseek-v3.2-expDeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It…
- Context
- 164K
- Input /1M
- $0.38
- Output /1M
- $0.57
DeepSeek V3.1 Terminus−40%deepseek/deepseek-v3.1-terminusDeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users…
- Context
- 164K
- Input /1M
- $0.38
- Output /1M
- $1.40
DeepSeek V3.2−28%deepseek/deepseek-v3.2DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance…
- Context
- 164K
- Input /1M
- $0.39from $0.29
- Output /1M
- $0.59from $0.43
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It…
- Context
- 164K
- Input /1M
- $0.41
- Output /1M
- $1.60
R1 0528deepseek/deepseek-r1-0528May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B…
- Context
- 164K
- Input /1M
- $0.70
- Output /1M
- $3.01
DeepSeek V4 Pro 0813−50%deepseek/deepseek-v4-pro-0813DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
- Context
- 1.0M
- Input /1M
- $0.77from $0.27
- Output /1M
- $7.00from $2.77
R1deepseek/deepseek-r1DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with…
- Context
- 64K
- Input /1M
- $0.98
- Output /1M
- $3.50
Qwen3.7 Flashqwen/qwen3.7-flashQwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer…
- Context
- 1M
- Input /1M
- $0.04
- Output /1M
- $0.18
Qwen3 30B A3B Instruct 2507−55%qwen/qwen3-30b-a3b-instruct-2507Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It…
- Context
- 262K
- Input /1M
- $0.07
- Output /1M
- $0.27
Qwen3.5-Flashqwen/qwen3.5-flash-02-23The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse…
- Context
- 1M
- Input /1M
- $0.09
- Output /1M
- $0.36
Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instructQwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for…
- Context
- 262K
- Input /1M
- $0.10
- Output /1M
- $0.39
Qwen3 32Bqwen/qwen3-32bQwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It…
- Context
- 131K
- Input /1M
- $0.11
- Output /1M
- $0.39
Qwen3 235B A22B Instruct 2507−75%qwen/qwen3-235b-a22b-2507Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B…
- Context
- 262K
- Input /1M
- $0.12
- Output /1M
- $0.49
Qwen3.5-9Bqwen/qwen3.5-9bQwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an…
- Context
- 262K
- Input /1M
- $0.14
- Output /1M
- $0.21
Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instructQwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking”…
- Context
- 262K
- Input /1M
- $0.14
- Output /1M
- $1.54
Qwen2.5 7B Instructqwen/qwen-2.5-7b-instructQwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge…
- Context
- 33K
- Input /1M
- $0.14
- Output /1M
- $0.28
Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instructQwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text…
- Context
- 131K
- Input /1M
- $0.15
- Output /1M
- $0.58
Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instructQwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across…
- Context
- 262K
- Input /1M
- $0.16
- Output /1M
- $0.64
Qwen3 8Bqwen/qwen3-8bQwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It…
- Context
- 131K
- Input /1M
- $0.16
- Output /1M
- $0.64
Qwen3 Coder Next−40%qwen/qwen3-coder-nextQwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design…
- Context
- 262K
- Input /1M
- $0.17
- Output /1M
- $1.12
Qwen3 30B A3Bqwen/qwen3-30b-a3bQwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in…
- Context
- 131K
- Input /1M
- $0.17
- Output /1M
- $0.70
Qwen3 14Bqwen/qwen3-14bQwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It…
- Context
- 131K
- Input /1M
- $0.17
- Output /1M
- $0.34
Qwen3.8 Omni Flashqwen/qwen3.8-omni-flashQwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video…
- Context
- 1M
- Input /1M
- $0.21
- Output /1M
- $0.66
Qwen3.8 Flashqwen/qwen3.8-flashQwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document…
- Context
- 1M
- Input /1M
- $0.21
- Output /1M
- $0.66
Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token…
- Context
- 262K
- Input /1M
- $0.21
- Output /1M
- $1.40
Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3bThe Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a…
- Context
- 262K
- Input /1M
- $0.21
- Output /1M
- $1.40
Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instructQwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct…
- Context
- 262K
- Input /1M
- $0.21
- Output /1M
- $0.84
Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinkingQwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s…
- Context
- 262K
- Input /1M
- $0.21
- Output /1M
- $1.68
Qwen3 VL 8B Thinkingqwen/qwen3-vl-8b-thinkingQwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning…
- Context
- 131K
- Input /1M
- $0.25
- Output /1M
- $2.94
Qwen3.6 Flashqwen/qwen3.6-flashQwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context…
- Context
- 1M
- Input /1M
- $0.26
- Output /1M
- $1.57
Qwen3.5-27Bqwen/qwen3.5-27bThe Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing…
- Context
- 262K
- Input /1M
- $0.27
- Output /1M
- $2.18
Qwen3 Coder Flashqwen/qwen3-coder-flashQwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model…
- Context
- 1M
- Input /1M
- $0.27
- Output /1M
- $1.36
Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinkingQwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking…
- Context
- 262K
- Input /1M
- $0.28
- Output /1M
- $3.36
Qwen3 30B A3B Thinking 2507qwen/qwen3-30b-a3b-thinking-2507Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step…
- Context
- 82K
- Input /1M
- $0.28
- Output /1M
- $3.36
Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instructQwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and…
- Context
- 262K
- Input /1M
- $0.29
- Output /1M
- $2.66
Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It…
- Context
- 131K
- Input /1M
- $0.32
- Output /1M
- $3.22
Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10bThe Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse…
- Context
- 262K
- Input /1M
- $0.36
- Output /1M
- $2.91
Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse…
- Context
- 1M
- Input /1M
- $0.36
- Output /1M
- $2.18
Qwen Plus 0728qwen/qwen-plus-2025-07-28Qwen Plus 0728, based on the Qwen3 foundation model, is a 1 million context hybrid reasoning model with a balanced performance, speed, and cost…
- Context
- 1M
- Input /1M
- $0.36
- Output /1M
- $1.09
Qwen-Plusqwen/qwen-plusQwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.
- Context
- 1M
- Input /1M
- $0.36
- Output /1M
- $1.09
Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text…
- Context
- 1M
- Input /1M
- $0.42
- Output /1M
- $2.52
Qwen3 Coder 480B A35Bqwen/qwen3-coderQwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding…
- Context
- 262K
- Input /1M
- $0.42
- Output /1M
- $1.40
Qwen3.7 Plusqwen/qwen3.7-plusQwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text…
- Context
- 1M
- Input /1M
- $0.45
- Output /1M
- $1.79
Qwen3.6 27Bqwen/qwen3.6-27bQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal…
- Context
- 262K
- Input /1M
- $0.45
- Output /1M
- $3.78
Qwen3.6 Plusqwen/qwen3.6-plusQwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong…
- Context
- 1M
- Input /1M
- $0.45
- Output /1M
- $2.73
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instructQwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more…
- Context
- 33K
- Input /1M
- $0.50
- Output /1M
- $0.56
Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinkingQwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The…
- Context
- 131K
- Input /1M
- $0.56
- Output /1M
- $5.60
Qwen3.8 27B−25%qwen/qwen3.8-27bQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal…
- Context
- 1M
- Input /1M
- $0.59from $0.03
- Output /1M
- $3.57from $2.09
Qwen3 235B A22Bqwen/qwen3-235b-a22bQwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports…
- Context
- 131K
- Input /1M
- $0.64
- Output /1M
- $2.55
Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17bThe Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a…
- Context
- 262K
- Input /1M
- $0.77
- Output /1M
- $4.90
Qwen3 Coder Plusqwen/qwen3-coder-plusQwen3 Coder Plus is Alibaba's proprietary version of the Open Source Qwen3 Coder 480B A35B. It is a powerful coding agent model specializing in…
- Context
- 1M
- Input /1M
- $0.91
- Output /1M
- $4.55
Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instructQwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following…
- Context
- 33K
- Input /1M
- $0.92
- Output /1M
- $1.40
Qwen3 Max Thinkingqwen/qwen3-max-thinkingQwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step…
- Context
- 262K
- Input /1M
- $1.09
- Output /1M
- $5.46
Qwen3 Maxqwen/qwen3-maxQwen3-Max is an updated release built on the Qwen3 series, offering major improvements in reasoning, instruction following, multilingual support…
- Context
- 262K
- Input /1M
- $1.09
- Output /1M
- $5.46
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instructQwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts…
- Context
- 128K
- Input /1M
- $1.12
- Output /1M
- $1.40
Qwen3.6 Max Previewqwen/qwen3.6-max-previewQwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1…
- Context
- 262K
- Input /1M
- $1.44
- Output /1M
- $8.63
Qwen3.7 Maxqwen/qwen3.7-maxQwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with…
- Context
- 1M
- Input /1M
- $2.06
- Output /1M
- $6.20
Qwen3.8 Max (0902)qwen/qwen3.8-max-0902Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that…
- Context
- 1M
- Input /1M
- $2.80
- Output /1M
- $8.40
Qwen3.8 2.4T A95B−20%qwen/qwen3.8-2.4t-a95bQwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active…
- Context
- 1.0M
- Input /1M
- $2.80
- Output /1M
- $8.40
Qwen3.8 Max Primeqwen/qwen3.8-max-primeQwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It…
- Context
- 1M
- Input /1M
- $5.60
- Output /1M
- $16.80
Kimi K2.5−5%moonshotai/kimi-k2.5Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm…
- Context
- 262K
- Input /1M
- $0.63
- Output /1M
- $3.15
Kimi K2 0711moonshotai/kimi-k2Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32…
- Context
- 131K
- Input /1M
- $0.80
- Output /1M
- $3.22
Kimi K2 Thinkingmoonshotai/kimi-k2-thinkingKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built…
- Context
- 262K
- Input /1M
- $0.84
- Output /1M
- $3.50
Kimi K2 0905moonshotai/kimi-k2-0905Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI…
- Context
- 262K
- Input /1M
- $0.84
- Output /1M
- $3.50
Kimi K3−35%moonshotai/kimi-k3Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and…
- Context
- 1.0M
- Input /1M
- $0.94from $0.82
- Output /1M
- $19.60from $13.65
Kimi K2.7 Code−25%moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over…
- Context
- 262K
- Input /1M
- $0.94
- Output /1M
- $4.69from $4.20
Kimi K2.6−37%moonshotai/kimi-k2.6Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent…
- Context
- 262K
- Input /1M
- $1.33from $0.65
- Output /1M
- $5.60from $3.36
Kimi K3 (batch)moonshotai/kimi-k3:batchKimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and…
- Context
- 1.0M
- Input /1M
- $3.19
- Output /1M
- $15.96
GLM 5.2−54%z-ai/glm-5.2GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for…
- Context
- 1.0M
- Input /1M
- $0.03
- Output /1M
- $22.40from $2.52
GLM 5.3 Flash (batch)−50%z-ai/glm-5.3-flash:batchGLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear…
- Context
- 1.0M
- Input /1M
- $0.08
- Output /1M
- $0.28
GLM 4.7 Flashz-ai/glm-4.7-flashAs a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding…
- Context
- 200K
- Input /1M
- $0.08
- Output /1M
- $0.56
GLM 4.5 Airz-ai/glm-4.5-airGLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it…
- Context
- 131K
- Input /1M
- $0.18
- Output /1M
- $1.19
GLM 5.3 Flash−50%z-ai/glm-5.3-flashGLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear…
- Context
- 1.0M
- Input /1M
- $0.21from $0.05
- Output /1M
- $0.70from $0.35
GLM 4.6Vz-ai/glm-4.6vGLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed…
- Context
- 131K
- Input /1M
- $0.42
- Output /1M
- $1.26
GLM 5.3 FlashXz-ai/glm-5.3-flashxGLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s…
- Context
- 1.0M
- Input /1M
- $0.52
- Output /1M
- $1.75
GLM 4.6z-ai/glm-4.6Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to…
- Context
- 205K
- Input /1M
- $0.60
- Output /1M
- $2.45
GLM 5.3 (batch)−38%z-ai/glm-5.3:batchGLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and…
- Context
- 1.0M
- Input /1M
- $0.63
- Output /1M
- $2.80
GLM 5−40%z-ai/glm-5GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert…
- Context
- 205K
- Input /1M
- $0.84
- Output /1M
- $2.69
GLM 4.7−27%z-ai/glm-4.7GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step…
- Context
- 205K
- Input /1M
- $0.84from $0.56
- Output /1M
- $3.08from $2.45
GLM 4.5Vz-ai/glm-4.5vGLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B…
- Context
- 66K
- Input /1M
- $0.84
- Output /1M
- $2.52
GLM 4.5z-ai/glm-4.5GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture…
- Context
- 131K
- Input /1M
- $0.84
- Output /1M
- $3.08
GLM 5V Turboz-ai/glm-5v-turboGLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles…
- Context
- 203K
- Input /1M
- $1.68
- Output /1M
- $5.60
GLM 5 Turboz-ai/glm-5-turboGLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It…
- Context
- 203K
- Input /1M
- $1.68
- Output /1M
- $5.60
GLM 5.3−70%z-ai/glm-5.3GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and…
- Context
- 1.0M
- Input /1M
- $1.96from $0.04
- Output /1M
- $6.16from $1.85
GLM 5.1−31%z-ai/glm-5.1GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models…
- Context
- 205K
- Input /1M
- $1.96from $1.35
- Output /1M
- $6.16from $4.25
GLM 5.3 Primez-ai/glm-5.3-primeGLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through…
- Context
- 1M
- Input /1M
- $3.92
- Output /1M
- $12.32
Switchyard
nvidia/switchyardSwitchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter…
- Context
- 1M
- Input /1M
- <$0.01
- Output /1M
- <$0.01
Nemotron 3 Nano 30B A3B
nvidia/nemotron-3-nano-30b-a3bNVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized…
- Context
- 262K
- Input /1M
- $0.07
- Output /1M
- $0.28
Nemotron 3.5 Lightning−15%
nvidia/nemotron-3.5-lightningNVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for…
- Context
- 262K
- Input /1M
- $0.08from $0.05
- Output /1M
- $0.22
Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12bNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in…
- Context
- 262K
- Input /1M
- $0.11
- Output /1M
- $0.63
Nemotron 3.5 Content Safety
nvidia/nemotron-3.5-content-safetyNVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It…
- Context
- 131K
- Input /1M
- $0.28
- Output /1M
- $0.28
Nemotron 3 Ultra
nvidia/nemotron-3-ultra-550b-a55bNVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE)…
- Context
- 262K
- Input /1M
- $0.70
- Output /1M
- $3.08
Command R7B (12-2024)
cohere/command-r7b-12-2024Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar…
- Context
- 128K
- Input /1M
- $0.05
- Output /1M
- $0.21
Command R (08-2024)
cohere/command-r-08-2024command-r-08-2024 is an update of the Command R with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More…
- Context
- 128K
- Input /1M
- $0.21
- Output /1M
- $0.84
Command A+
cohere/command-a-plusCommand A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports…
- Context
- 192K
- Input /1M
- $0.42
- Output /1M
- $2.10
Command A
cohere/command-aCommand A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual…
- Context
- 256K
- Input /1M
- $3.50
- Output /1M
- $14.00
Command R+ (08-2024)
cohere/command-r-plus-08-2024command-r-plus-08-2024 is an update of the Command R+ with roughly 50% higher throughput and 25% lower latencies as compared to the previous…
- Context
- 128K
- Input /1M
- $3.50
- Output /1M
- $14.00
Sonar
perplexity/sonarSonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for…
- Context
- 127K
- Input /1M
- $1.40
- Output /1M
- $1.40
Sonar Reasoning Pro
perplexity/sonar-reasoning-proNote: Sonar Pro pricing includes Perplexity search pricing. See details here Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek…
- Context
- 128K
- Input /1M
- $2.80
- Output /1M
- $11.20
Sonar Deep Research
perplexity/sonar-deep-researchSonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously…
- Context
- 128K
- Input /1M
- $2.80
- Output /1M
- $11.20
Sonar Pro Search
perplexity/sonar-pro-searchExclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed…
- Context
- 200K
- Input /1M
- $4.20
- Output /1M
- $21.00
Sonar Pro
perplexity/sonar-proNote: Sonar Pro pricing includes Perplexity search pricing. See details here For enterprises seeking more advanced capabilities, the Sonar Pro API…
- Context
- 200K
- Input /1M
- $4.20
- Output /1M
- $21.00
Phi 4
microsoft/phi-4Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or…
- Context
- 16K
- Input /1M
- $0.10
- Output /1M
- $0.20
WizardLM-2 8x22B
microsoft/wizardlm-2-8x22bWizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary…
- Context
- 66K
- Input /1M
- $0.87
- Output /1M
- $0.87
Nova Micro 1.0
amazon/nova-micro-v1Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With…
- Context
- 128K
- Input /1M
- $0.05
- Output /1M
- $0.20
Nova Lite 1.0
amazon/nova-lite-v1Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate…
- Context
- 300K
- Input /1M
- $0.08
- Output /1M
- $0.34
Nova 2 Lite
amazon/nova-2-lite-v1Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2…
- Context
- 1M
- Input /1M
- $0.42
- Output /1M
- $3.50
Nova Pro 1.0
amazon/nova-pro-v1Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of…
- Context
- 300K
- Input /1M
- $1.12
- Output /1M
- $4.48
Nova Premier 1.0
amazon/nova-premier-v1Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling…
- Context
- 1M
- Input /1M
- $3.50
- Output /1M
- $17.50
MiniMax-01minimax/minimax-01MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9…
- Context
- 1.0M
- Input /1M
- $0.28
- Output /1M
- $1.54
MiniMax M2.7−30%minimax/minimax-m2.7MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to…
- Context
- 205K
- Input /1M
- $0.29
- Output /1M
- $1.18
MiniMax M2.5−10%minimax/minimax-m2.5MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working…
- Context
- 205K
- Input /1M
- $0.38
- Output /1M
- $1.51from $1.33
MiniMax M3−50%minimax/minimax-m3MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window…
- Context
- 1.0M
- Input /1M
- $0.42from $0.32
- Output /1M
- $1.68from $1.34
MiniMax M2-herminimax/minimax-m2-herMiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn…
- Context
- 66K
- Input /1M
- $0.42
- Output /1M
- $1.68
MiniMax M2.1minimax/minimax-m2.1MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development…
- Context
- 205K
- Input /1M
- $0.42
- Output /1M
- $1.68
MiniMax M2−15%minimax/minimax-m2MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated…
- Context
- 205K
- Input /1M
- $0.42from $0.36
- Output /1M
- $1.68from $1.43
MiniMax M1minimax/minimax-m1MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid…
- Context
- 1M
- Input /1M
- $0.77
- Output /1M
- $3.08
Seed 1.6 Flashbytedance-seed/seed-1.6-flashSeed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k…
- Context
- 262K
- Input /1M
- $0.10
- Output /1M
- $0.42
Seed-2.0-Minibytedance-seed/seed-2.0-miniSeed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference…
- Context
- 262K
- Input /1M
- $0.14
- Output /1M
- $0.56
UI-TARS 7B bytedance/ui-tars-1.5-7bUI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems…
- Context
- 128K
- Input /1M
- $0.14
- Output /1M
- $0.28
Seed-2.0-Litebytedance-seed/seed-2.0-liteSeed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably…
- Context
- 262K
- Input /1M
- $0.35
- Output /1M
- $2.80
Seed 1.6bytedance-seed/seed-1.6Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a…
- Context
- 262K
- Input /1M
- $0.35
- Output /1M
- $2.80
Seed 2.1 Turbobytedance-seed/seed-2-1-turboSeed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software…
- Context
- 262K
- Input /1M
- $0.70
- Output /1M
- $3.50
Seed-2.0-Codebytedance-seed/seed-2.0-codeSeed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks…
- Context
- 262K
- Input /1M
- $0.70
- Output /1M
- $4.20
Hy-MT2-1.8B
tencent/hy-mt2-1.8bHy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and…
- Context
- 8K
- Input /1M
- $0.06
- Output /1M
- $0.25
Hy-MT2-30B-A3B
tencent/hy-mt2-30b-a3bHy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and…
- Context
- 8K
- Input /1M
- $0.10
- Output /1M
- $0.41
Hy-MT2-7B
tencent/hy-mt2-7bHy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs…
- Context
- 8K
- Input /1M
- $0.10
- Output /1M
- $0.41
Hy3
tencent/hy3Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows…
- Context
- 262K
- Input /1M
- $0.18
- Output /1M
- $0.74
Hunyuan A13B Instruct
tencent/hunyuan-a13b-instructHunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and…
- Context
- 131K
- Input /1M
- $0.20
- Output /1M
- $0.80
Hy3 preview
tencent/hy3-previewHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable…
- Context
- 262K
- Input /1M
- $0.25
- Output /1M
- $0.84
Hy4 preview
tencent/hy4-previewTencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents…
- Context
- 1.0M
- Input /1M
- $1.17
- Output /1M
- $3.50
Aion 3.5 Mini
aion-labs/aion-3.5-miniAion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost…
- Context
- 262K
- Input /1M
- $0.98
- Output /1M
- $1.96
Aion-3.0-Mini
aion-labs/aion-3.0-miniAion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative…
- Context
- 131K
- Input /1M
- $0.98
- Output /1M
- $1.96
Aion-2.0
aion-labs/aion-2.0Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension…
- Context
- 131K
- Input /1M
- $1.12
- Output /1M
- $2.24
Aion-RP 1.0 (8B)
aion-labs/aion-rp-llama-3.1-8bAion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of…
- Context
- 33K
- Input /1M
- $1.12
- Output /1M
- $2.24
Aion 3.5
aion-labs/aion-3.5Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation…
- Context
- 262K
- Input /1M
- $4.20
- Output /1M
- $8.40
Aion-3.0
aion-labs/aion-3.0Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation…
- Context
- 131K
- Input /1M
- $4.20
- Output /1M
- $8.40
Muse Spark 1.3 Contributor
meta/muse-spark-1.3-contributorMuse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and…
- Context
- 1.0M
- Input /1M
- $0.14
- Output /1M
- $0.28
Muse Spark 1.2 Contributor
meta/muse-spark-1.2-contributorMuse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s…
- Context
- 1.0M
- Input /1M
- $0.14
- Output /1M
- $0.28
Muse Glimmer 30B
meta/muse-glimmer-30bMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous…
- Context
- 131K
- Input /1M
- $0.49
- Output /1M
- $2.10
Muse Spark 1.3
meta/muse-spark-1.3Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track…
- Context
- 1.0M
- Input /1M
- $1.75
- Output /1M
- $5.95
Muse Spark 1.2
meta/muse-spark-1.2Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text…
- Context
- 1.0M
- Input /1M
- $1.75
- Output /1M
- $5.95
Muse Spark 1.1
meta/muse-spark-1.1Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns…
- Context
- 1.0M
- Input /1M
- $1.75
- Output /1M
- $5.95
MiMo-V2.6-Flash
xiaomi/mimo-v2.6-flashMiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and…
- Context
- 1.1M
- Input /1M
- $0.20
- Output /1M
- $0.39
MiMo-V2.5−15%
xiaomi/mimo-v2.5MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing…
- Context
- 1.1M
- Input /1M
- $0.20from $0.17
- Output /1M
- $0.39from $0.33
MiMo-V2.6-Pro
xiaomi/mimo-v2.6-proMiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of…
- Context
- 1.1M
- Input /1M
- $0.61
- Output /1M
- $1.22
MiMo-V2.5-Pro−30%
xiaomi/mimo-v2.5-proMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and…
- Context
- 1.1M
- Input /1M
- $0.61from $0.43
- Output /1M
- $1.22from $0.85
MiMo-V2.6-Pro-UltraSpeed
xiaomi/mimo-v2.6-pro-ultraspeedMiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro…
- Context
- 1.0M
- Input /1M
- $6.09
- Output /1M
- $12.18
Sakana Namazu
sakana/sakana-namazuSakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and…
- Context
- 262K
- Input /1M
- $1.33
- Output /1M
- $5.60
Fugu Max
sakana/fugu-maxFugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent…
- Context
- 1M
- Input /1M
- $2.80
- Output /1M
- $8.40
Fugu Ultra v2
sakana/fugu-ultra-v2Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent…
- Context
- 1M
- Input /1M
- $7.00
- Output /1M
- $42.00
Fugu Ultra
sakana/fugu-ultraFugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent…
- Context
- 1M
- Input /1M
- $7.00
- Output /1M
- $42.00
Ling 3.0 Flash VL−72%
inclusionai/ling-3.0-flash-vlLing 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while…
- Context
- 262K
- Input /1M
- $0.03
- Output /1M
- $0.09
Ling 3.0 Flash−65%
inclusionai/ling-3.0-flashLing-3.0-flash is a 124B-parameter Mixture-of-Experts (MoE) model, with approximately 5.1B parameters activated per token. The model is designed…
- Context
- 262K
- Input /1M
- $0.03
- Output /1M
- $0.09
Ling 3.0 Flash Fin−44%
inclusionai/ling-3.0-flash-finLing 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B…
- Context
- 262K
- Input /1M
- $0.06
- Output /1M
- $0.17
Hermes 3 70B Instruct
nousresearch/hermes-3-llama-3.1-70bHermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying…
- Context
- 131K
- Input /1M
- $0.98
- Output /1M
- $0.98
Hermes 4 405B
nousresearch/hermes-4-405bHermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where…
- Context
- 131K
- Input /1M
- $1.40
- Output /1M
- $4.20
Hermes 3 405B Instruct
nousresearch/hermes-3-llama-3.1-405bHermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying…
- Context
- 131K
- Input /1M
- $1.40
- Output /1M
- $1.40
Fusionopenrouter/fusionFusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web…
- Context
- 1M
- Input /1M
- <$0.01
- Output /1M
- <$0.01
Pareto Code Routeropenrouter/pareto-codeThe Pareto Router maintains a tiered shortlist of strong coding models, ranked by Artificial Analysis coding percentiles. Set mincodingscore…
- Context
- 2M
- Input /1M
- <$0.01
- Output /1M
- <$0.01
Body Builder (beta)openrouter/bodybuilderTransform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and…
- Context
- 128K
- Input /1M
- <$0.01
- Output /1M
- <$0.01
Solar Mini 4−50%
upstage/solar-mini4Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context…
- Context
- 524K
- Input /1M
- $0.07
- Output /1M
- $0.28
Solar Pro 4−70%
upstage/solar-pro4Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic…
- Context
- 524K
- Input /1M
- $0.13
- Output /1M
- $0.50
Solar Pro 3
upstage/solar-pro-3Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass…
- Context
- 131K
- Input /1M
- $0.21
- Output /1M
- $0.84
Granite 4.0 Micro
ibm-granite/granite-4.0-h-microGranite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They…
- Context
- 131K
- Input /1M
- $0.02
- Output /1M
- $0.16
Granite 4.2 8B
ibm-granite/granite-4.2-8bGranite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows…
- Context
- 131K
- Input /1M
- $0.08
- Output /1M
- $0.35
Mercury 2.5−80%
inception/mercury-2.5Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury…
- Context
- 260K
- Input /1M
- $0.06
- Output /1M
- $0.21
Mercury 2
inception/mercury-2Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2…
- Context
- 128K
- Input /1M
- $0.35
- Output /1M
- $1.05
Schematron V2 Turbo
inference-net/schematron-v2-turboSchematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction…
- Context
- 128K
- Input /1M
- $0.04
- Output /1M
- $0.21
Schematron V2 Small
inference-net/schematron-v2-smallSchematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and…
- Context
- 128K
- Input /1M
- $0.07
- Output /1M
- $0.32
Morph V3 Fast
morph/morph-v3-fastMorph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to…
- Context
- 82K
- Input /1M
- $1.12
- Output /1M
- $1.68
Morph V3 Large
morph/morph-v3-largeMorph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires…
- Context
- 262K
- Input /1M
- $1.26
- Output /1M
- $2.66
Nex-N2.5-Mini
nex-agi/nex-n2.5-miniNex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback…
- Context
- 262K
- Input /1M
- $0.03
- Output /1M
- $0.14
Nex-N2.5-Pro
nex-agi/nex-n2.5-proNex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback…
- Context
- 262K
- Input /1M
- $0.10
- Output /1M
- $0.35
Perceptron Mk1.5
perceptron/perceptron-mk1.5Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with…
- Context
- 37K
- Input /1M
- $0.21
- Output /1M
- $2.10
Perceptron Mk1
perceptron/perceptron-mk1Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning. It accepts image and video inputs…
- Context
- 33K
- Input /1M
- $0.21
- Output /1M
- $2.10
Laguna XS 2.1−40%
poolside/laguna-xs-2.1Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their Laguna XS.2 model (released in…
- Context
- 262K
- Input /1M
- $0.08
- Output /1M
- $0.17
Laguna S 2.1−10%
poolside/laguna-s-2.1Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2%…
- Context
- 1.0M
- Input /1M
- $0.13
- Output /1M
- $0.25
Reka Edge
rekaai/reka-edgeReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model…
- Context
- 16K
- Input /1M
- $0.14
- Output /1M
- $0.14
Reka Flash 3
rekaai/reka-flash-3Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat…
- Context
- 66K
- Input /1M
- $0.14
- Output /1M
- $0.28
Relace Apply 3
relace/relace-apply-3Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o…
- Context
- 256K
- Input /1M
- $1.19
- Output /1M
- $1.75
Relace Search
relace/relace-searchThe relace-search model uses 4-12 viewfile and grep tools in parallel to explore a codebase and return relevant files to the user request. In…
- Context
- 256K
- Input /1M
- $1.40
- Output /1M
- $4.20
Step 3.5 Flash
stepfun/step-3.5-flashStep 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively…
- Context
- 262K
- Input /1M
- $0.14
- Output /1M
- $0.42
Step 3.7 Flash
stepfun/step-3.7-flashStep 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision…
- Context
- 262K
- Input /1M
- $0.28
- Output /1M
- $1.61
Inkling Small
thinkingmachines/inkling-smallInkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is…
- Context
- 524K
- Input /1M
- $0.63
- Output /1M
- $1.68
Inkling
thinkingmachines/inklingInkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is…
- Context
- 524K
- Input /1M
- $1.33
- Output /1M
- $5.67
Pareto 26.10 Preview
unbiased/pareto-26.10-previewPareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a…
- Context
- 1.0M
- Input /1M
- $1.12
- Output /1M
- $4.48
Pareto
unbiased/paretoPareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a…
- Context
- 262K
- Input /1M
- $3.50
- Output /1M
- $10.50
Trinity Large Thinking
arcee-ai/trinity-large-thinkingTrinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic…
- Context
- 262K
- Input /1M
- $0.35
- Output /1M
- $1.12
ERNIE 4.5 VL 424B A47B
baidu/ernie-4.5-vl-424b-a47bERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B…
- Context
- 123K
- Input /1M
- $0.59
- Output /1M
- $1.75
Ember-1
fireworks/ember-1Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces…
- Context
- 1.0M
- Input /1M
- $4.20
- Output /1M
- $21.00
KAT-Coder-Pro V2.5
kwaipilot/kat-coder-pro-v2.5KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it…
- Context
- 262K
- Input /1M
- $1.04
- Output /1M
- $4.14
LongCat 2.0−60%
meituan/longcat-2.0LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding…
- Context
- 1.0M
- Input /1M
- $0.42
- Output /1M
- $1.68
Ternary Bonsai 2 27B
prism-ml/ternary-bonsai-2-27bBonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image…
- Context
- 262K
- Input /1M
- $0.10
- Output /1M
- $0.70
Jev Router
typesafe/jev-routerJev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on Jev, TypeSafe's first System…
- Context
- 1M
- Input /1M
- <$0.01
- Output /1M
- <$0.01
Palmyra X5
writer/palmyra-x5Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading…
- Context
- 1.0M
- Input /1M
- $0.84
- Output /1M
- $8.40
Image generation 57 models billed per generated image, per megapixel or per output token — whichever the provider meters
Recraft-
Recraft V4.1 Flash
recraft/recraft-v4.1-flash$0.0098/ image -
Recraft V4 Styles
recraft/recraft-v4-styles$0.049/ image -
Recraft V4.1
recraft/recraft-v4.1$0.049/ image -
Recraft V4.1 Utility
recraft/recraft-v4.1-utility$0.049/ image -
Recraft V3
recraft/recraft-v3$0.056/ image -
Recraft V4
recraft/recraft-v4$0.056/ image -
Recraft V4 Styles Vector
recraft/recraft-v4-styles-vector$0.07/ image -
Recraft V4 Vector
recraft/recraft-v4-vector$0.112/ image -
Recraft V4.1 Vector
recraft/recraft-v4.1-vector$0.112/ image -
Recraft V4 Styles Pro
recraft/recraft-v4-styles-pro$0.14/ image -
Recraft V4 Styles Pro Vector
recraft/recraft-v4-styles-pro-vector$0.168/ image -
Recraft V4.1 Pro
recraft/recraft-v4.1-pro$0.294/ image -
Recraft V4.1 Utility Pro
recraft/recraft-v4.1-utility-pro$0.294/ image -
Recraft V4 Pro
recraft/recraft-v4-pro$0.35/ image -
Recraft V4 Pro Vector
recraft/recraft-v4-pro-vector$0.42/ image -
Recraft V4.1 Pro Vector
recraft/recraft-v4.1-pro-vector$0.42/ image
OpenAI-
GPT Image 1 Mini
openai/gpt-image-1-mini$11.20/ 1M tokens -
GPT-5 Image Mini
openai/gpt-5-image-mini$11.20/ 1M tokens -
GPT Image 2
openai/gpt-image-2$42.00/ 1M tokens -
GPT Image 2.5 Flare
openai/gpt-image-2.5-flare$42.00/ 1M tokens -
GPT Image 2.5 Sunburst
openai/gpt-image-2.5-sunburst$42.00/ 1M tokens -
GPT-5.4 Image 2
openai/gpt-5.4-image-2$42.00/ 1M tokens -
GPT Image 1
openai/gpt-image-1$56.00/ 1M tokens -
GPT-5 Image
openai/gpt-5-image$56.00/ 1M tokens
Google-
Nano Banana (Gemini 2.5 Flash Image)
google/gemini-2.5-flash-image$42.00/ 1M tokens -
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
google/gemini-3.1-flash-lite-image$42.00/ 1M tokens -
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
google/gemini-3.1-flash-image-preview$84.00/ 1M tokens -
Nano Banana 2 (Gemini 3.1 Flash Image)
google/gemini-3.1-flash-image$84.00/ 1M tokens -
Nano Banana Pro (Gemini 3 Pro Image Preview)
google/gemini-3-pro-image-preview$84.00/ 1M tokens -
Nano Banana Pro (Gemini 3 Pro Image)
google/gemini-3-pro-image$168.00/ 1M tokens
Black Forest Labs-
FLUX.2 Klein 4B
black-forest-labs/flux.2-klein-4b$0.0196/ megapixel -
FLUX.2 Pro
black-forest-labs/flux.2-pro$0.042/ megapixel -
FLUX.3 Image
black-forest-labs/flux-3-image$0.0574/ image -
FLUX.2 Flex
black-forest-labs/flux.2-flex$0.084/ megapixel -
FLUX.2 Max
black-forest-labs/flux.2-max$0.098/ megapixel
ByteDance-
Seedream 5.0 Flash
bytedance-seed/seedream-5-0-flash$0.0252/ image -
Seedream 5.0 Lite
bytedance-seed/seedream-5-0-lite$0.049/ image -
Seedream 4.5
bytedance-seed/seedream-4.5$0.056/ image -
Seedream 5.0 Pro
bytedance-seed/seedream-5-0-pro$0.063/ image
Microsoft
-
MAI-Image-2.6 Flash
microsoft/mai-image-2.6-flash$26.60/ 1M tokens -
MAI-Image-2.6
microsoft/mai-image-2.6$53.20/ 1M tokens -
MAI-Image-2.5
microsoft/mai-image-2.5$65.80/ 1M tokens -
MAI-Image-2.5 Pro
microsoft/mai-image-2.5-pro$151.20/ 1M tokens
Sourceful
-
Riverflow V2.5 Fast
sourceful/riverflow-v2.5-fast$0.0266/ image -
Riverflow V2 Fast
sourceful/riverflow-v2-fast$0.028/ image -
Riverflow V2.5 Pro
sourceful/riverflow-v2.5-pro$0.182/ image -
Riverflow V2 Pro
sourceful/riverflow-v2-pro$0.21/ image
Krea
-
Krea 2 Large
krea/krea-2-largemetered -
Krea 2 Medium
krea/krea-2-mediummetered -
Krea 2 Medium Turbo
krea/krea-2-medium-turbometered
Inclusionai
-
Ming Image 0.1 Design
inclusionai/ming-image-0.1-designFree/ 1M tokens -
Ming Image 0.1 Design Layer
inclusionai/ming-image-0.1-design-layerFree/ 1M tokens
Qwen-
Qwen Image 3
qwen/qwen-image-3$0.042/ image -
Qwen Image 3 Pro
qwen/qwen-image-3-pro$0.056/ image
xAI-
Grok Imagine Image 2.0
x-ai/grok-imagine-image-2.0$0.056/ image -
Grok Imagine Image Quality
x-ai/grok-imagine-image-quality$0.07/ image
Meta-
Muse Image
meta/muse-imagemetered
Video generation 30 models billed per second of output — or per token where the provider meters that way; a range spans the model’s resolutions
Alibaba-
Wan 3.0audio
alibaba/wan-3.0$0.07–$0.28/ second -
Wan 3.0 Primeaudio
alibaba/wan-3.0-prime$0.0952–$0.392/ second -
HappyHorse 1.0
alibaba/happyhorse-1.0$0.138–$0.237/ second -
HappyHorse 1.1
alibaba/happyhorse-1.1$0.138–$0.179/ second -
Wan 2.7audio
alibaba/wan-2.7$0.14/ second -
Wan 2.6audio
alibaba/wan-2.6metered
ByteDance-
Seedance 1.5 Proaudio
bytedance/seedance-1-5-pro$1.68–$3.36/ 1M tokens -
Seedance 2.0 Miniaudio
bytedance/seedance-2.0-mini$2.94–$4.90/ 1M tokens -
Seedance 2.0audio
bytedance/seedance-2.0$3.36–$10.78/ 1M tokens -
Seedance 2.0 Fastaudio
bytedance/seedance-2.0-fast$3.46–$5.88/ 1M tokens -
Seedance 2.5audio
bytedance/seedance-2.5$8.96–$14.98/ 1M tokens
Black Forest Labs-
FLUX Video Upscale
black-forest-labs/flux-video-upscale$0.105–$0.147/ MP-second -
FLUX Video Edit
black-forest-labs/flux-video-editmetered -
FLUX.3 Videoaudio
black-forest-labs/flux-3-videometered
Google-
Veo 3.1 Liteaudio
google/veo-3.1-lite$0.042–$0.112/ second -
Veo 3.1 Fastaudio
google/veo-3.1-fast$0.112–$0.42/ second -
Veo 3.1audio
google/veo-3.1$0.28–$0.84/ second
Kuaishou-
Video v3.0 Standardaudio
kwaivgi/kling-v3.0-std$0.118–$0.176/ second -
Video O1audio
kwaivgi/kling-video-o1$0.157/ second -
Video v3.0 Proaudio
kwaivgi/kling-v3.0-pro$0.157–$0.235/ second
MiniMax-
H3 Max
minimax/hailuo-3-max$0.07–$0.112/ second -
Hailuo 2.3
minimax/hailuo-2.3$0.114/ second -
H3audio
minimax/hailuo-3$0.182/ second
HeyGen
-
HeyGen Video
heygen/heygen-video-1$0.028–$0.042/ second -
Avatar IV
heygen/avatar-iv$0.07/ second
Runway-
Aleph 2.0
runway/aleph-2metered -
Gen-4.5
runway/gen-4.5metered
xAI-
Grok Imagine Video
x-ai/grok-imagine-videometered -
Grok Imagine Video 1.5
x-ai/grok-imagine-video-1.5metered
OpenAI-
Sora 2 Proaudio
openai/sora-2-pro$0.42–$0.7/ second
Music generation 17 models full tracks from a text brief — flat per track, or by the second
MiniMax-
MiniMax Music 3
minimax/music-3$0.0028/ second -
MiniMax Music 1.5
fal-ai/minimax-music/v1.5$0.042/ generation -
MiniMax Music 2.0
fal-ai/minimax-music/v2$0.042/ generation -
MiniMax Music 2.5
fal-ai/minimax-music/v2.5$0.21/ generation -
MiniMax Music 2.6
fal-ai/minimax-music/v2.6$0.21/ generation
Stability AI-
Stable Audio 3 Small Music
fal-ai/stable-audio-3/small/music/text-to-audio$0.0304/ generation -
Stable Audio 3 Medium
fal-ai/stable-audio-3/medium/text-to-audio$0.0526/ generation -
Stable Audio 3 Medium Base
fal-ai/stable-audio-3/medium/base/text-to-audio$0.0671/ generation -
Stable Audio 2.5
fal-ai/stable-audio-25/text-to-audio$0.28/ generation
Google DeepMind-
Lyria 3
fal-ai/lyria3$0.056/ generation -
Lyria 3 Pro
fal-ai/lyria3/pro$0.112/ generation -
Lyria 2
fal-ai/lyria2$0.14/ generation
ACE-Step
-
ACE-Step
fal-ai/ace-step$0.00028/ second
CassetteAI
-
CassetteAI Music
cassetteai/music-generator$0.028/ minute
DiffRhythm
-
DiffRhythm
fal-ai/diffrhythm$0.0014/ second
ElevenLabs
-
ElevenLabs Music
fal-ai/elevenlabs/music$0.84/ minute
Sonilo
-
Sonilo v1.1
sonilo/v1.1/text-to-music$0.0035/ second
Sound effects 3 models one short sound from a description — impacts, ambiences, foley
CassetteAI
-
CassetteAI Sound Effects
cassetteai/sound-effects-generator$0.014/ generation
ElevenLabs
-
ElevenLabs Sound Effects v2
fal-ai/elevenlabs/sound-effects/v2$0.0028/ second
Stability AI-
Stable Audio 3 Small SFX
fal-ai/stable-audio-3/small/sfx/text-to-audio$0.0288/ generation
Voices (text to speech) 5 models billed per 1,000 characters submitted
ElevenLabs
-
ElevenLabs Turbo v2.5
fal-ai/elevenlabs/tts/turbo-v2.5$0.07/ 1K chars -
ElevenLabs Multilingual v2
fal-ai/elevenlabs/tts/multilingual-v2$0.14/ 1K chars -
ElevenLabs v3
fal-ai/elevenlabs/tts/eleven-v3$0.14/ 1K chars
Kokoro
-
Kokoro American English
fal-ai/kokoro/american-english$0.028/ 1K chars -
Kokoro British English
fal-ai/kokoro/british-english$0.028/ 1K chars
3D model generation 10 models image to mesh; priced by the options you pick, so each model shows its range
Tencent
-
Hunyuan 3D v3.1 Rapid
fal-ai/hunyuan-3d/v3.1/rapid/image-to-3d$0.322–$0.532/ mesh -
Hunyuan3D v3
fal-ai/hunyuan3d-v3/image-to-3d$0.322–$1.26/ mesh -
Hunyuan 3D v3.1 Pro
fal-ai/hunyuan-3d/v3.1/pro/image-to-3d$0.532–$1.16/ mesh
Tripo3D
-
Tripo H3.1
tripo3d/h3.1/image-to-3d$0.28–$0.91/ mesh -
Tripo v2.5
tripo3d/tripo/v2.5/image-to-3d$0.28–$0.7/ mesh -
Tripo P1
tripo3d/p1/image-to-3d$0.56–$0.7/ mesh
Hyper3D
-
Rodin v2.5 Fast
fal-ai/hyper3d/rodin/v2.5/fast$0.14/ mesh -
Rodin v2.5
fal-ai/hyper3d/rodin/v2.5$0.56–$1.68/ mesh
Meshy
-
Meshy v7
meshy/v7/image-to-3d$1.12–$2.41/ mesh
Trellis
-
Trellis 2
fal-ai/trellis-2$0.35–$0.49/ mesh
Availability & pricing refresh with each deploy from the live
provider catalogue; the app always shows current per-model pricing before
you spend. Free and NSFW/roleplay models are excluded. Every price on this
page is USD at the developer-API rate — see the
API pricing page for how billing works.
Reading the media prices. Chat is per token; everything else is per
unit of output, and the unit is the provider’s own. An image can be
metered per generated image, per megapixel or per output token; video per
second, with a range spanning the model’s resolutions — ask for
480p rather than 1080p and you pay the low end. Music is either flat per
track or by the second, sound effects likewise, voices per 1,000 characters
of text you submit, and a mesh by the options you pick, which is why 3D
models show a range rather than a rate. We quote each in its own unit
rather than converting: converting would mean inventing the resolution,
duration or token count that your actual request decides. A row marked
metered is billed at whatever the provider
charges for the call — it is not free, it simply publishes no rate we
can quote ahead of time.
About the discounts. A −40% chip means the
model’s provider had a promotional discount running when this page was
last built. The developer API bills what the provider actually charged for
your call, plus our flat markup — so a live promotion reaches your bill on
its own, with nothing to claim and no code to enter. The
from $0.00 figure is the cheapest endpoint
serving that model; which endpoint answers a given request is the
provider’s routing decision, so treat it as a floor, not a quote.
Input and output are quoted separately, and discounted separately —
on a reasoning model the output rate is usually what decides the bill.
The promotions are the providers’ own and can end at any time.