About
Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total.
Pricing
| Input | $1.40 | per 1M prompt tokens |
|---|---|---|
| Output | $5.67 | per 1M generated tokens, reasoning included |
| Cached input | $0.24 | per 1M tokens read back from the prompt cache |
What a request costs
| Typical request | Each | Per 1,000 |
|---|---|---|
| Short chat reply1,500 in · 400 out | $0.0044 | $4.37 |
| Question over a long document40,000 in · 800 out | $0.061 | $60.54 |
| Agent tool step20,000 in · 1,200 out | $0.035 | $34.80 |
At the developer-API rate, before any provider promotion or prompt-cache saving. In the app, the model picker shows what a message costs on your plan before you send it.
Benchmarks
Head-to-head rankings
- #22Web appsAgent arenaElo 118949% wins
- #53WebsitesModel arenaElo 122645% wins
- #56CodeModel arenaElo 120842% wins
- #57SVGModel arenaElo 111135% wins
- #58UI componentsModel arenaElo 119740% wins
- #62ASCII artModel arenaElo 109434% wins
- #633DModel arenaElo 116140% wins
- #67Game devModel arenaElo 116938% wins
- #75Data vizModel arenaElo 116238% wins
Scores from Artificial Analysis; bars are scaled to the best model on our list. Rankings from Design Arena head-to-head votes. Published by OpenRouter alongside its catalogue.
Call it from code
OpenAI-compatible: point any OpenAI SDK at https://api.privateer.pro/v1 and set
model. Keys are created in the app under Settings.
cURL
curl https://api.privateer.pro/v1/chat/completions \
-H "Authorization: Bearer $PRIVATEER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "thinkingmachines/inkling",
"messages": [{ "role": "user", "content": "Hello" }],
"reasoning": { "effort": "medium" }
}'Python
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.privateer.pro/v1",
api_key=os.environ["PRIVATEER_API_KEY"],
)
reply = client.chat.completions.create(
model="thinkingmachines/inkling",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.privateer.pro/v1",
apiKey: process.env.PRIVATEER_API_KEY,
});
const reply = await client.chat.completions.create({
model: "thinkingmachines/inkling",
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);Parameters this model accepts
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p