GPT-6 Luna

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

GPT-6 Luna is OpenAI's most efficient GPT-6 model, built for focused, high-volume tasks.

Model Info
Context Window ↗	1,050,000 tokens
Terms and License	link ↗
More information	link ↗
Request formats	Responses, Chat Completions
Pricing	Short-context input (per 1M)$0.10 Short-context cached input (per 1M)$0.01 Short-context cache write (per 1M)$0.125 Short-context output (per 1M)$0.50 Long-context input (per 1M)$0.20 Long-context cached input (per 1M)$0.02 Long-context cache write (per 1M)$0.25 Long-context output (per 1M)$0.75

Usage

const response = await env.AI.run(
  'openai/gpt-6-luna',
  {
    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-luna",
  "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 43,200 minutes, so a 99.9% availability target allows **43.2 minutes** of downtime.

**31 minutes < 43.2 minutes** — the service is within its error budget, with **12.2 minutes** remaining.

{
  "id": "resp_0834f111f7f68c6e006ab2cf91391887d1b9ed77f9003d8001",
  "object": "response",
  "created_at": 1790103441,
  "status": "completed",
  "access_programs": {
    "cyber": "daybreak_blue"
  },
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1790103442,
  "error": null,
  "frequency_penalty": 0,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": 512,
  "max_tool_calls": null,
  "model": "gpt-6-luna",
  "moderation": null,
  "output": [
    {
      "id": "rs_0834f111f7f68c6e006ab2cf91a3dc87d194f310e59b05b545",
      "type": "reasoning",
      "content": [],
      "encrypted_content": "gAAAAABqss-TspJODH9IZcFL8SzWTp9z3qvEH482IoLj1OmrPlxluS5KGNZRrU1yGjrek9eQ7K6QzWND5RagCGsxWPN3ZK7lFfa8HWjztExHY-locYCrFDRWniTGdOmjF0dAUcm_5L5laGAhFa5qiRByPmSSapXvxyhbYx1Qs-_SjUxRF7rvxFIisGHm4XeHSuTMLUaVGk3okdDMWwxJDZrPjOk66JLwvZ_D8n345Iw6WG7L6iS30KsEhOuKVxkdkl0H_T_2fDaGxaJfOIr0WCSFjM62vvZNw6Gi9-zf8tzupmjORta_cLu9YDNSklYSNio-rUS-2RMlfJA1RvFQPKIx8347HtpYUYqHBNFRlNA-Az99fWBdGffyNtYL2vuItF4X0UJ1tDN_KtuFil7qLPJMGHTdXI7_-2YzNw9u-rmeeR9tnp3zbCertjlHMsTAcT0fbuLh_ob-GCDSg0pR8Ac5fsJv75nRqIMVixC_e7sL_5sGDAsJDi-24_nUAtU84zCPinglfdiYNvwBoEOgZQ-bYT8K3DZ-Z6dJaupCz_ncOtsFIvvEehM2JzcVdKkhUv6ilUst-J-RoMEzb3HzpKZE2Y6Ry3R-VDvLOda2HL-DrmbK4zW_o8X5-Yp5I-XXIomnt3yxMRYyH5WI66HkMQAFQtiP7ukmQEpI-_ItySu48cro2tpY3tBnRBJAvAU45yGDm9EhG6F_jThXyEav90yADc4GfJw82gZDzrnmQ0Oki8U0jEfPUipKztlsstiLw06Da5IF6cBxhOMiNq2TbB4j5o3bG48HSxAzwgu8xHHSR00_IWMEFO49l6lWpO9W0FWN9OdeaMKkRFQ8cGNIZCqDgYvkw3x0NlbOtjm_TqIQMRVM7vfsdujWSwb1iidy6BEYde7TVAmEg_D0jk7tq9JPIQIngvbxeWXpE2zmvEGrgDqD9y8d-dF2svsxMegzFpZjVowcWRPhJXcySYsMnPrIYqM8bCmXPhSXoBgmTqvWO8BCBJUPvRLPAkJSUU4JTI3GAsN4XAKVm-NaQghf4t5ofeZkIRx9sc1jkz1KfEZ_hH02_89s_A8u2GaiCREYGisKBd9ZuvtDu2WxzIsqud1YKqn9epw-ZC5zCkS0MfZW5rZGmBmu2K6Zia2swsBgs3mypZPh4ihYkkeuAxs_eX1nFtCW-tdYGFcCKVRBf3tvbA2XRgcfgNr9LH6kmbWSBM53kjxLI5L6hR-CDBJ9lWuWoal1R3GzWL9-uIbU4i4ailowQwcgQ2o8Lnnq_jZTs-yurDDyThIVKeo_ZkrmniqyReoVlwYZYRWKaKsSV6i95J-GosOjqM4BoVZGB0tvebNbEOz4tGzKPmoDFI6ckl4Jede1l3dYWAobbPgGab7pp4QgmerdWhiIyK2-kRrDsocrazxjIv0hEqOZha1jwN_cWqmfPTgfmv7jIHZ9Be0S8xrQdd11Qwwyik1OPyJlYte3Ru1IO6FDcCRNbAE3yFBE9pSU8kOKIg==",
      "summary": []
    },
    {
      "id": "msg_0834f111f7f68c6e006ab2cf925fd487d1b67ccd2ee1e2dfe5",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "logprobs": [],
          "text": "No. A 30-day month has 43,200 minutes, so a 99.9% availability target allows **43.2 minutes** of downtime.\n\n**31 minutes < 43.2 minutes** — the service is within its error budget, with **12.2 minutes** remaining."
        }
      ],
      "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": 151,
    "output_tokens_details": {
      "reasoning_tokens": 84
    },
    "total_tokens": 195
  },
  "user": null,
  "metadata": {}
}

Examples

Migration Safeguards — Generate a concise answer through Chat Completions

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

1. **Preserve compatibility:** Version the API or support old and new contracts during the transition; document breaking changes and give clients a migration window.
2. **Roll out gradually:** Test in staging, then use a canary or percentage-based rollout with monitoring for errors, latency, and client failures.
3. **Plan validation and rollback:** Verify key workflows and data before and after cutover, keep backups or a reversible migration path, and define clear rollback triggers.

{
  "id": "chatcmpl-EQzy7Or5tZ9ZdoXfjhVAYfwDEj28S",
  "object": "chat.completion",
  "created": 1790103443,
  "model": "gpt-6-luna",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1. **Preserve compatibility:** Version the API or support old and new contracts during the transition; document breaking changes and give clients a migration window.\n2. **Roll out gradually:** Test in staging, then use a canary or percentage-based rollout with monitoring for errors, latency, and client failures.\n3. **Plan validation and rollback:** Verify key workflows and data before and after cutover, keep backups or a reversible migration path, and define clear rollback triggers.",
        "refusal": null,
        "annotations": []
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 16,
    "completion_tokens": 128,
    "total_tokens": 144,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 25,
      "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