GPT-6 Sol

Model ID

Use with the Workers AI binding, the AI Gateway REST API, or the Unified API.

Calling the provider directly? Use the provider's model name instead, including with provider-native endpoints or the provider's own SDK. For example, Anthropic's name for anthropic/claude-opus-4.8 is claude-opus-4-8.

Third-party
Zero data retention

GPT-6 Sol is OpenAI's mid-tier GPT-6 model, built to power complex coding and agentic workflows.

Model Info
Context Window ↗	1,050,000 tokens
Terms and License	link ↗
More information	link ↗
Zero data retention	Yes
Request formats	Responses, Chat Completions
Pricing	Short-context input (per 1M)$2.00 Short-context cached input (per 1M)$0.20 Short-context cache write (per 1M)$2.50 Short-context output (per 1M)$10.00 Long-context input (per 1M)$4.00 Long-context cached input (per 1M)$0.40 Long-context cache write (per 1M)$5.00 Long-context output (per 1M)$15.00

Usage

const response = await env.AI.run(
  'openai/gpt-6-sol',
  {
    input:
      'A service has 99.9% monthly availability and just had 31 minutes of downtime. Has it exceeded the monthly error budget for a 30-day month? Show the calculation briefly.',
    max_output_tokens: 512,
    reasoning: { effort: 'high' },
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-6-sol",
  "input": "A service has 99.9% monthly availability and just had 31 minutes of downtime. Has it exceeded the monthly error budget for a 30-day month? Show the calculation briefly.",
  "max_output_tokens": 512,
  "reasoning": {
    "effort": "high"
  }
}'

No. A 30-day month has \(30 \times 24 \times 60 = 43{,}200\) minutes, so the 0.1% downtime budget is **43.2 minutes**. After 31 minutes of downtime, **12.2 minutes remain**.

{
  "id": "resp_004a362708bc0a44006ab2cc7bd4c487d1bffa1555dc6c5110",
  "object": "response",
  "created_at": 1790102651,
  "status": "completed",
  "access_programs": {
    "cyber": "daybreak_blue"
  },
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1790102653,
  "error": null,
  "frequency_penalty": 0,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": 512,
  "max_tool_calls": null,
  "model": "gpt-6-sol",
  "moderation": null,
  "output": [
    {
      "id": "rs_004a362708bc0a44006ab2cc7c78bc87d1b3ac1095e5bbaaae",
      "type": "reasoning",
      "content": [],
      "encrypted_content": "gAAAAABqssx9oBJ5yr_VdmObO4zvyzJEasvjs_4xsaXswQG7TjMqx-6kfx_szw29t29TiMj1CMtiWD8IdaVjgznOab6hu0poxB9ZuvgbmIrkgiYx_oqp8UHjtJd06fhkzNaTp01_BBaBQpcwhC9bd_Y6VR8HlvEB1Go4JL7-RLhwh2nJN5wjRjWOlqWaHZRaz1Wz2eQon9IYI8pJ9jpxvYMQpNBle___KLzlJiCjeDKw5yFf9NAjKDwqi75YR4f2uhsWYIfRNgi3Eyzx-h_5dnIahzx1-26Bj_UcRQvUhqf0-0jGmIS1PLg1uSVlHJ7iQsuLJwtcwJYG7X-FYEx61X9BtqtiUFODxRODCUpq3RMrZKUm6N9BtNwqB1PkLR6Y5gCyhWPAdf77zvcxGJKncLGIduS4Fei5u3lJTg8NlDpFC5sFNUu6wEmBV3Mz3e_uCo3B2bHVFNAFcK8h-nnvj3hM6EYbVTRnXlaFrb2Fb51_TvZBQ1ReAPmz9nQcdb9bIZRBeRIN7PAKChmwgS4gYD_r3IE3k4q8CWBHOPzzxHeQzOSPgameIHzXR13uc9dy-gBD8o2wWChw616xhktHemPEUZG4l2AIBVSJNuFKIoGS_jT_P7ScPZwynxwS3wSGuyCLa3qAPkZWeP7qqfZQmtDKWj0xnjyipbOGoDQh5pAPtkIMdKIsMBj12RY_Ms-sYB7ojN1vOhUWeN-2MXPDkBmxY_L58hUjNVyLbYo1TUQsZVQX5r0tT0o3_9GI7aAa-vgMz_hXFJ4QepBtzc2hlGDT6CKp5tt235fisry5k0xaMAsl9ae6o-yEn0KDeLmpeIICZX6vDgqIZjPny7D_jpmHNZPLYkC56kQL2xaLI695l3GuMkeV6S5kphxK1y-5yyEJ9lasAT2aEwTIFSQ1fjdMwb9QjCpDXL-w-fUMxAfy_u8LapQBH5aV6XH5L2No4VKP-0IDrstrfh38LEEm9sBt55zVBQ2-UpB_DYy-BsG4Qn77cpDVaKC3MHXBbMhYWaNc6vJ1zsLaUhO2AgH7QW8sCRHexDRb1QO9NRXbp9Y-HSOIV8UxFEXjxbUV_dPxYUABNioPutzYq54kqnJc8ekT45AN-CRgviXVG9824m20cjEz1ryvnVNIKmen_ysou2W98MQqIch2Hh4cqgCkBxOyh7iYTqSS8LhGoJqAtGRgK7XlV8sB-q3xEDLEsW5cD_irRuVzh5Bb1ofy4emT2HNeoYUNdA9SLvpZfK9c8jCHr01ia4NzGrjwSBn4fzujX-eCPoYaN2MLQ2N8mp1cfYGH35LDIhmCjA==",
      "summary": []
    },
    {
      "id": "msg_004a362708bc0a44006ab2cc7ca89487d1a80f11a6def484c5",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "logprobs": [],
          "text": "No. A 30-day month has \\(30 \\times 24 \\times 60 = 43{,}200\\) minutes, so the 0.1% downtime budget is **43.2 minutes**. After 31 minutes of downtime, **12.2 minutes remain**."
        }
      ],
      "phase": "final_answer",
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "24h",
  "reasoning": {
    "context": "all_turns",
    "effort": "high",
    "mode": "standard",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "store": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tool_usage": {
    "image_gen": {
      "input_tokens": 0,
      "input_tokens_details": {
        "image_tokens": 0,
        "text_tokens": 0
      },
      "output_tokens": 0,
      "output_tokens_details": {
        "image_tokens": 0,
        "text_tokens": 0
      },
      "total_tokens": 0
    },
    "web_search": {
      "num_requests": 0
    }
  },
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 44,
    "input_tokens_details": {
      "cache_write_tokens": 0,
      "cached_tokens": 0
    },
    "output_tokens": 103,
    "output_tokens_details": {
      "reasoning_tokens": 36
    },
    "total_tokens": 147
  },
  "user": null,
  "metadata": {}
}

Examples

Migration Safeguards — Generate a concise answer through Chat Completions

const response = await env.AI.run(
  'openai/gpt-6-sol',
  {
    messages: [
      { role: 'user', content: 'List three practical safeguards for a production API migration.' },
    ],
    max_completion_tokens: 256,
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-6-sol",
  "messages": [
    {
      "role": "user",
      "content": "List three practical safeguards for a production API migration."
    }
  ],
  "max_completion_tokens": 256
}'

1. **Preserve compatibility:** Version breaking changes and run contract tests against existing clients.
2. **Roll out gradually:** Start with a canary or small percentage of traffic, and monitor errors, latency, and key business metrics.
3. **Prepare a rollback:** Keep the previous API deployable, back up data, and rehearse how to reverse any schema changes.

{
  "id": "chatcmpl-EQzlOt1nlzMH6eShi7U8iGaHTJByy",
  "object": "chat.completion",
  "created": 1790102654,
  "model": "gpt-6-sol",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1. **Preserve compatibility:** Version breaking changes and run contract tests against existing clients.\n2. **Roll out gradually:** Start with a canary or small percentage of traffic, and monitor errors, latency, and key business metrics.\n3. **Prepare a rollback:** Keep the previous API deployable, back up data, and rehearse how to reverse any schema changes.",
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 16,
    "completion_tokens": 118,
    "total_tokens": 134,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 34,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  },
  "service_tier": "default",
  "system_fingerprint": null
}

Parameters

▶input

one ofrequired

instructions

string

temperature

numberminimum: 0maximum: 2

max_output_tokens

numberexclusiveMinimum: 0

top_p

numberminimum: 0maximum: 1

stream

boolean

▶tools[]

array

tool_choice

▶text{}

object

▶reasoning{}

object

string

object

stringconst: response

created_at

number

model

string

▶output[]

array

output_text

string

status

stringenum: in_progress, completed, failed, incomplete

▶usage{}

object

API Schemas (Raw)

Input

Output