GPT-6.1 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-6.1 Sol is OpenAI's newest Sol model, delivering near-Astra performance at a lower cost for complex coding, computer use, and professional work.

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)$0.10 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)$0.20 Long-context cache write (per 1M)$5.00 Long-context output (per 1M)$15.00

Usage

const response = await env.AI.run(
  'openai/gpt-6.1-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-6.1-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.

The downtime budget is:
\[
43{,}200 \times (1 - 0.999) = 43.2 \text{ minutes}
\]

With **31 minutes** of total downtime, it has **12.2 minutes remaining** in the monthly error budget.

{
  "id": "resp_0742f162d8d88f47006abbfb65797087d1bf6067c71ad4f488",
  "object": "response",
  "created_at": 1790704485,
  "status": "completed",
  "access_programs": null,
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1790704489,
  "error": null,
  "frequency_penalty": 0,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": 512,
  "max_tool_calls": null,
  "model": "gpt-6.1-sol",
  "moderation": null,
  "output": [
    {
      "id": "rs_0742f162d8d88f47006abbfb66b91887d1b350a855c33b1a1d",
      "type": "reasoning",
      "content": [],
      "encrypted_content": "gAAAAABqu_tp8krmIOoigihwk28V3hw4d1Y_Eool5VFtPYh3G8ZpXSlRoDhZdTuB2XNHizSr-faVPlm3Z-K0RgfU74vlZp8aWqhlnrGs8_XYwk1Iqi-TSacN9S_3wYvHyHpVKFqGAqAaj63TVGuYen-flkgSasvprEnL6KUPPjcJlHFoPMppkXXPFrwuaw7F47QHGv0FAvok_wtBiSgghzbXH4_dgwxvT0hsAcX03xTWRGMQP18n1esxQr47TyrQG2APoynZLdietAvr-qUmghFeKTrTusGjeLgVIFCDDEwSvLBW3sZj5ezX9-mWwKWdAx98-7C2e9322jTGXWSC_8Z3axK8DjKWLf8VXe8bBvAFA3g15o0aBpy144hYrsymXIax1k5SSYqvHvNiuV_eA2pzCG_BcJkvRtZ-9zFQLZ3rtO6objv3UbZ21qXwNfvlp2FGxI4Qv0LbReLaHua5Zttkg7N-t0n0D8NB2Tv2UP6FUdbAgLOqJXMYcivRP2vtvnrkUJz5DN23FIhiqGL8HgGDedg--_AqReHxNWGmh3EUsUK0IBLwJSO0WXF3yfBFqveVW_OWIoXugQha_KDz0SSTS3F4I98UAXCTV51KskT-caWnKs8SrilQtuHdhf-axWo_MnQLlsjoSNvPJI-G3-Dz8f-hLQvlo6yE3WejMXJpTpXtboCFId7ezJgZYrbDZTZJGurWODEGmk9BRmwRvg-BqFRt6OVyTioGafw0efSrEGEne50Lv5ACUfBzOV0-tCQ_bGFp0YW7HwpxLsdWjk0l6IteeFHQ6r6sFDm1lvt0GvYTa0KMmYJJxj3heM-m245AUZIrFf-D0vrII0VwKtHTtBhavXIpS--6P_SQ2A_RP10zMoWj3EOWa4s1tZ9zaJX1W1IFdqwBuOS4ISBAgaOKJe-GwypcOWMzmhNDV9ZGWtHwdkgzdd3ksZ6m5VF1mm1ngooUdJT1KidlGLLpamsmEPlUAJskSHBcMOcaT5RXqp4nPx3CPcHFetUTbSsYH0ArFRdPuPM8L8tR_HJ11sEM2fFWwKdgntQ48sS1o3ZS_t72yKBWxVO3XHWY-2Ej2PHvP1gjEuIRy1gWvZVBchb3KVBbqwGAND9IJ5zWmjlHEo48khWpCZiJUHtS8W1roy4bNOvEF0kWY0pe01-N7HKBDGHLPJbR3ifB0GMtQHkuTR_LhlfluWvvgODrRvzSdaconMNl_9V0p_KRulPSBVYdhQ1Pef_F0mm5S_rVq2aJR1v9Iqb7bF52TBFbZ4iXJphjpft1AxzDEEamX4O1hAiHpu0HgdwAwsV8lTxdUdeQ5c1fksqQyXCVwmBVL-Kiw7NGoiFDW1Q_uVLC1iv6-IiRaHWrFmvo85MLlhF-pUocgZasQC4mM70zW5AUaaT6adJD15cmTGIv3C5_UvjHUbPJ40Fy8Wd65bdZiER0WL2qTD13FUomOIK3JqTGTccqakCzkFDAv_2HCZBbn0xgM_oEdN2WsrP-iiBquNPCUr5Y8jqVsPHsLfxTOgbDCdWRHcAl-oe5aN_RtciAF6aH_oHoAft4LLRzS9APxWemfhUV9vsrQN4jxg32WghgIK3ot5vkKW0bJFnRmhr86esnTXfJIUMOQgjRA4hWvoejNqWnMLiWK9_C8PdvSiNhxTxxGVTEChQmql6WpS-AFYuZdTR9tARXap_cpQ==",
      "summary": []
    },
    {
      "id": "msg_0742f162d8d88f47006abbfb68a39c87d1b289852fcb1469dc",
      "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.\n\nThe downtime budget is:\n\\[\n43{,}200 \\times (1 - 0.999) = 43.2 \\text{ minutes}\n\\]\n\nWith **31 minutes** of total downtime, it has **12.2 minutes remaining** in the monthly error budget."
        }
      ],
      "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": 222,
    "output_tokens_details": {
      "reasoning_tokens": 129
    },
    "total_tokens": 266
  },
  "user": null,
  "metadata": {}
}

Examples

Migration Safeguards — Generate a concise answer through Chat Completions

const response = await env.AI.run(
  'openai/gpt-6.1-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-6.1-sol",
  "messages": [
    {
      "role": "user",
      "content": "List three practical safeguards for a production API migration."
    }
  ],
  "max_completion_tokens": 256
}'

1. **Validate backward compatibility:** Run contract and integration tests against real client workflows. Version breaking changes and keep the old API available during the transition.

2. **Roll out gradually with monitoring:** Start with a small canary group, then increase traffic while tracking error rates, latency, and data correctness. Define thresholds that pause or reverse the rollout.

3. **Test the rollback plan:** Use feature flags or traffic routing to restore the old API quickly. Back up affected data and ensure schema changes remain compatible with the old version.

{
  "id": "chatcmpl-ETWKQsjDdzqugdVw1xUKVJuFad33U",
  "object": "chat.completion",
  "created": 1790704490,
  "model": "gpt-6.1-sol",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1. **Validate backward compatibility:** Run contract and integration tests against real client workflows. Version breaking changes and keep the old API available during the transition.\n\n2. **Roll out gradually with monitoring:** Start with a small canary group, then increase traffic while tracking error rates, latency, and data correctness. Define thresholds that pause or reverse the rollout.\n\n3. **Test the rollback plan:** Use feature flags or traffic routing to restore the old API quickly. Back up affected data and ensure schema changes remain compatible with the old version.",
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 16,
    "completion_tokens": 155,
    "total_tokens": 171,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 40,
      "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