Inkling

by thinkingmachines · family inkling

Facts

Release date	2026-07-15
Retired date	—
Knowledge cutoff	—
Context (max)	1,048,576
Max output	32,768
Modalities	text, image, audio → text
Aliases	`thinkingmachines/inkling`
Open weights	no
Description	Thinking Machines' reasoning model with vision and audio input, 1M context / 32K output; served on Baseten.

Unknown values are shown as —.

Intelligence Index v4.1.1: 42 · base · Source: Artificial Analysis (accessed 2026-08-20)

Offerings

Provider	Wire ID	Variant	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
Baseten	`thinkingmachines/inkling`		chat-completions	openai-chat	ga	1.00 / 4.05	effort · default on · returns reasoning_content · round-trips reasoning_content
OpenRouter	`thinkingmachines/inkling`		chat-completions	openai-chat	ga	0.95 / 4.05	effort · default on · returns reasoning_content · round-trips reasoning_content

Reasoning controls

Baseten· thinkingmachines/inkling· chat-completions effort

reasoning_effort nonelowhigh● Default high; none disables reasoning.

effort · default on · returns reasoning_content · round-trips reasoning_content

OpenRouter· thinkingmachines/inkling· chat-completions effort

reasoning.effort nonelowmedium●highxhighmax

effort · default on · returns reasoning_content · round-trips reasoning_content

Example requests

Baseten · openai-chat · thinkingmachines/inkling

curl 'https://inference.baseten.co/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "thinkingmachines/inkling",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://inference.baseten.co/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "thinkingmachines/inkling",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://inference.baseten.co/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "thinkingmachines/inkling",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).

OpenRouter · openai-chat · thinkingmachines/inkling

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "thinkingmachines/inkling",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "medium"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "thinkingmachines/inkling",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "medium"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "thinkingmachines/inkling",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "medium"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).