Inkling 256K

Text Generation • thinkingmachines

thinkingmachines/inkling-256k

  • Third-party

The 256K-context variant of Inkling, Thinking Machines' open-weights hybrid reasoning MoE model. Same hybrid reasoning, tool-use, and streaming support as the base model, with an extended context window for longer conversations and documents. Currently intended for low-traffic testing and internal use rather than high-throughput production deployments.

Model Info
Context Window ↗ 262,144 tokens
More information link ↗
Request formats Anthropic Messages
Pricing <ul><li>Input (per 1M tokens)$3.74</li><li>Output (per 1M tokens)$9.36</li><li>Cached input (per 1M tokens)$0.748</li><li>Cache creation (per 1M tokens)$3.74</li></ul>

Usage

const response = await env.AI.run(
  'thinkingmachines/inkling-256k',
  { max_tokens: 512, messages: [{ content: 'The capital of France is', role: 'user' }] },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/messages \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "thinkingmachines/inkling-256k",
  "max_tokens": 512,
  "messages": [
    {
      "content": "The capital of France is",
      "role": "user"
    }
  ]
}'

The capital of France is **Paris**.

{
  "id": "msg_f3f0874570144f29add4272d4f07491d",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "thinking",
      "thinking": "The user is asking \"The capital of France is\". This is a straightforward factual question. The capital of France is Paris. I should provide the answer clearly and concisely.",
      "signature": ""
    },
    {
      "type": "text",
      "text": "The capital of France is **Paris**."
    }
  ],
  "model": "thinkingmachines/Inkling:peft:262144",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 52,
    "cache_creation_input_tokens": 19,
    "cache_read_input_tokens": 0
  }
}

Examples

<details>

<summary>Tool Use — Tool use round-trip: the model requests a tool call, then answers using the tool_result supplied in a follow-up user message</summary>

const response = await env.AI.run(
  'thinkingmachines/inkling-256k',
  {
    max_tokens: 1024,
    messages: [
      { content: "What's the weather in Paris?", role: 'user' },
      {
        content: [
          {
            id: 'toolu_01A1x1x1x1x1x1x1x1x1x1x1',
            input: { city: 'Paris' },
            name: 'get_weather',
            type: 'tool_use',
          },
        ],
        role: 'assistant',
      },
      {
        content: [
          {
            content: 'Sunny, 22°C',
            tool_use_id: 'toolu_01A1x1x1x1x1x1x1x1x1x1x1',
            type: 'tool_result',
          },
        ],
        role: 'user',
      },
    ],
    tools: [
      {
        description: 'Get the current weather for a city.',
        input_schema: {
          properties: { city: { type: 'string' } },
          required: ['city'],
          type: 'object',
        },
        name: 'get_weather',
      },
    ],
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/messages \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "thinkingmachines/inkling-256k",
  "max_tokens": 1024,
  "messages": [
    {
      "content": "What'\''s the weather in Paris?",
      "role": "user"
    },
    {
      "content": [
        {
          "id": "toolu_01A1x1x1x1x1x1x1x1x1x1x1",
          "input": {
            "city": "Paris"
          },
          "name": "get_weather",
          "type": "tool_use"
        }
      ],
      "role": "assistant"
    },
    {
      "content": [
        {
          "content": "Sunny, 22°C",
          "tool_use_id": "toolu_01A1x1x1x1x1x1x1x1x1x1x1",
          "type": "tool_result"
        }
      ],
      "role": "user"
    }
  ],
  "tools": [
    {
      "description": "Get the current weather for a city.",
      "input_schema": {
        "properties": {
          "city": {
            "type": "string"
          }
        },
        "required": [
          "city"
        ],
        "type": "object"
      },
      "name": "get_weather"
    }
  ]
}'

The weather in Paris is sunny with a temperature of 22°C.

{
  "id": "msg_5711f240c8da46eeb462f8900281d087",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "thinking",
      "thinking": "The user asked for the weather in Paris. The function returned \"Sunny, 22°C\". I should provide a clear, concise answer.",
      "signature": ""
    },
    {
      "type": "text",
      "text": "The weather in Paris is sunny with a temperature of 22°C."
    }
  ],
  "model": "thinkingmachines/Inkling:peft:262144",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 0,
    "output_tokens": 49,
    "cache_creation_input_tokens": 95,
    "cache_read_input_tokens": 0
  }
}

</details>

Parameters

▶messages[]

arrayrequired

max_tokens

numberrequiredexclusiveMinimum: 0

system

string

temperature

numberminimum: 0maximum: 1

top_p

numberminimum: 0maximum: 1

top_k

numberexclusiveMinimum: 0

stream

boolean

▶metadata{}

object

id

string

type

stringconst: message

role

stringconst: assistant

▶content[]

array

model

string

stop_reason

string

▶usage{}

object

API Schemas (Raw)

Input Open Download

Output Open Download

Was this helpful?

YesNo

On this page

Inkling 256K - 图1Docs

{"@context":"https://schema.org","@type":"TechArticle","@id":"https://developers.cloudflare.com/ai/models/thinkingmachines/inkling-256k/#page","headline":"Inkling 256K","description":"The 256K-context variant of Inkling, Thinking Machines' open-weights hybrid reasoning MoE model. Same hybrid reasoning, tool-use, and streaming support as the base model, with an extended context window for longer conversations and documents. Currently intended for low-traffic testing and internal use rather than high-throughput production deployments.","url":"https://developers.cloudflare.com/ai/models/thinkingmachines/inkling-256k/","inLanguage":"en","image":"https://developers.cloudflare.com/og-docs.png","publisher":{"@type":"Organization","name":"Cloudflare","description":"One platform for your apps, agents, and workforce. Build, secure, and scale without managing infrastructure","url":"https://www.cloudflare.com/","sameAs":["https://github.com/cloudflare","https://www.linkedin.com/company/cloudflare","https://x.com/cloudflare"],"logo":{"@type":"ImageObject","url":"https://developers.cloudflare.com/logo.svg"},"address":{"@type":"PostalAddress","streetAddress":"101 Townsend St","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94107","addressCountry":"US"},"contactPoint":[{"@type":"ContactPoint","contactType":"Customer Support","url":"https://support.cloudflare.com/","availableLanguage":["English"]},{"@type":"ContactPoint","contactType":"Sales","url":"https://www.cloudflare.com/contact/","availableLanguage":["English"]}]},"isPartOf":{"@type":"WebSite","@id":"https://developers.cloudflare.com/#website","name":"Cloudflare Docs","url":"https://developers.cloudflare.com/"}}

description: Topaz Labs Starlight Fast 2 (slf-2) enhances and upscales source video to 1080p or 4K with faster processing than Starlight Precise. It is designed for video restoration workflows where turnaround time is important. title: Starlight Fast 2 image: https://developers.cloudflare.com/og-docs.png

Skip to content

Documentation Index
Fetch the complete documentation index at: https://developers.cloudflare.com/llms.txt
Use this file to discover all available pages before exploring further.

t