--- title: GPT-5.6 Luna description: GPT-5.6 Luna is an OpenAI GPT-5.6 model optimized for cost-sensitive workloads, using the Responses API for efficient text generation. image: https://edgetunnel-b2h.pages.dev/dev-products-preview.png --- > Documentation Index > Fetch the complete documentation index at: https://edgetunnel-b2h.pages.dev/ai/llms.txt > Use this file to discover all available pages before exploring further. [Skip to content](#%5Ftop) ![OpenAI logo](https://edgetunnel-b2h.pages.dev/_astro/openai.BI8PEEzI.svg) # GPT-5.6 Luna Text Generation • OpenAI `openai/gpt-5.6-luna` GPT-5.6 Luna is an OpenAI GPT-5.6 model optimized for cost-sensitive workloads, using the Responses API for efficient text generation. | Model Info | | | -------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------- | | Context Window[ ↗](https://edgetunnel-b2h.pages.dev/workers-ai/glossary/) | 1,050,000 tokens | | Terms and License | [link ↗](https://openai.com/policies/) | | More information | [link ↗](https://openai.com/) | | Request formats | Responses | | Pricing | [View pricing in the Cloudflare dashboard ↗](https://dash.cloudflare.com/?to=/:account/ai/models/openai/gpt-5.6-luna) | ## Usage * [ TypeScript ](#tab-panel-1484) * [ cURL ](#tab-panel-1485) **TypeScript** ```ts const response = await env.AI.run( 'openai/gpt-5.6-luna', { input: 'Summarize the benefits of API rate limiting in three bullets.', max_output_tokens: 256, }, ) console.log(response) ``` ```bash 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-5.6-luna", "input": "Summarize the benefits of API rate limiting in three bullets.", "max_output_tokens": 256 }' ``` * [ Output ](#tab-panel-1488) * [ Raw response ](#tab-panel-1489) - **Protects system stability:** Prevents overload, reduces outages, and ensures predictable performance during traffic spikes. - **Ensures fair access:** Stops individual users or applications from consuming disproportionate resources. - **Improves security and cost control:** Helps mitigate abuse, brute-force attacks, and unexpected infrastructure usage. ```json { "id": "resp_0e481f0cb46bf357016a4fe99bd5fc8194b6ce2049aa65ab08", "object": "response", "created_at": 1783622043, "status": "completed", "background": false, "billing": { "payer": "developer" }, "completed_at": 1783622044, "error": null, "frequency_penalty": 0, "incomplete_details": null, "instructions": null, "max_output_tokens": 256, "max_tool_calls": null, "model": "gpt-5.6-luna", "moderation": null, "output": [ { "id": "msg_0e481f0cb46bf357016a4fe99c2e288194a6fd0ce3f5f88786", "type": "message", "status": "completed", "content": [ { "type": "output_text", "annotations": [], "logprobs": [], "text": "- **Protects system stability:** Prevents overload, reduces outages, and ensures predictable performance during traffic spikes.\n- **Ensures fair access:** Stops individual users or applications from consuming disproportionate resources.\n- **Improves security and cost control:** Helps mitigate abuse, brute-force attacks, and unexpected infrastructure usage." } ], "phase": "final_answer", "role": "assistant" } ], "parallel_tool_calls": true, "presence_penalty": 0, "previous_response_id": null, "prompt_cache_key": null, "prompt_cache_retention": "in_memory", "reasoning": { "context": "all_turns", "effort": "medium", "mode": "standard", "summary": null }, "safety_identifier": null, "service_tier": "default", "store": false, "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": 19, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 66, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 85 }, "user": null, "metadata": {} } ``` ## Examples **Pull Request Description** — Using instructions for a cost-sensitive drafting task * [ TypeScript ](#tab-panel-1486) * [ cURL ](#tab-panel-1487) **TypeScript** ```ts const response = await env.AI.run( 'openai/gpt-5.6-luna', { input: 'Write a brief pull request description for a bug fix that prevents duplicate webhook deliveries.', instructions: 'Keep it under 100 words.', max_output_tokens: 256, }, ) console.log(response) ``` ```bash 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-5.6-luna", "input": "Write a brief pull request description for a bug fix that prevents duplicate webhook deliveries.", "instructions": "Keep it under 100 words.", "max_output_tokens": 256 }' ``` * [ Output ](#tab-panel-1490) * [ Raw response ](#tab-panel-1491) ## Summary Prevents duplicate webhook deliveries by ensuring each event is processed only once, even when retries or concurrent requests occur. ## Changes - Added idempotency checks for webhook events. - Prevented duplicate delivery attempts. - Added regression tests covering retries and concurrent processing. ## Testing All existing and new tests pass. ```json { "id": "resp_0bed05adeda548a1016a4fe99d1e408194bb0375bad96ab71a", "object": "response", "created_at": 1783622045, "status": "completed", "background": false, "billing": { "payer": "developer" }, "completed_at": 1783622046, "error": null, "frequency_penalty": 0, "incomplete_details": null, "instructions": "Keep it under 100 words.", "max_output_tokens": 256, "max_tool_calls": null, "model": "gpt-5.6-luna", "moderation": null, "output": [ { "id": "msg_0bed05adeda548a1016a4fe99daa748194992854423ba08e72", "type": "message", "status": "completed", "content": [ { "type": "output_text", "annotations": [], "logprobs": [], "text": "## Summary\nPrevents duplicate webhook deliveries by ensuring each event is processed only once, even when retries or concurrent requests occur.\n\n## Changes\n- Added idempotency checks for webhook events.\n- Prevented duplicate delivery attempts.\n- Added regression tests covering retries and concurrent processing.\n\n## Testing\nAll existing and new tests pass." } ], "phase": "final_answer", "role": "assistant" } ], "parallel_tool_calls": true, "presence_penalty": 0, "previous_response_id": null, "prompt_cache_key": null, "prompt_cache_retention": "in_memory", "reasoning": { "context": "all_turns", "effort": "medium", "mode": "standard", "summary": null }, "safety_identifier": null, "service_tier": "default", "store": false, "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": 33, "input_tokens_details": { "cache_write_tokens": 0, "cached_tokens": 0 }, "output_tokens": 69, "output_tokens_details": { "reasoning_tokens": 0 }, "total_tokens": 102 }, "user": null, "metadata": {} } ``` ## Parameters * [ Input ](#tab-panel-1492) * [ Output ](#tab-panel-1493) ▶input `one of`required instructions `string` temperature `number`minimum: 0maximum: 2 max\_output\_tokens `number`exclusiveMinimum: 0 top\_p `number`minimum: 0maximum: 1 stream `boolean` ▶tools\[\] `array` tool\_choice `` ▶text{} `object` ▶reasoning{} `object` id `string` object `string`const: response created\_at `number` model `string` ▶output\[\] `array` output\_text `string` status `string`enum: in\_progress, completed, failed, incomplete ▶usage{} `object` ## API Schemas (Raw) Input [ ](https://edgetunnel-b2h.pages.dev/ai/models/openai/gpt-5.6-luna/schema-input.json "Open") [ ](https://edgetunnel-b2h.pages.dev/ai/models/openai/gpt-5.6-luna/schema-input.json "Download") Output [ ](https://edgetunnel-b2h.pages.dev/ai/models/openai/gpt-5.6-luna/schema-output.json "Open") [ ](https://edgetunnel-b2h.pages.dev/ai/models/openai/gpt-5.6-luna/schema-output.json "Download") ```json {"@context":"https://schema.org","@type":"TechArticle","@id":"https://edgetunnel-b2h.pages.dev/ai/models/openai/gpt-5.6-luna/#page","headline":"GPT-5.6 Luna (OpenAI) · Cloudflare AI docs · Cloudflare AI docs","description":"GPT-5.6 Luna is an OpenAI GPT-5.6 model optimized for cost-sensitive workloads, using the Responses API for efficient text generation.","url":"https://edgetunnel-b2h.pages.dev/ai/models/openai/gpt-5.6-luna/","inLanguage":"en","image":"https://edgetunnel-b2h.pages.dev/dev-products-preview.png","publisher":{"@type":"Organization","name":"Cloudflare","url":"https://www.cloudflare.com/"},"isPartOf":{"@type":"WebSite","@id":"https://edgetunnel-b2h.pages.dev/#website","name":"Cloudflare Docs","url":"https://edgetunnel-b2h.pages.dev/"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"item":{"@id":"/directory/","name":"Directory"}},{"@type":"ListItem","position":2,"item":{"@id":"/ai/","name":"AI"}},{"@type":"ListItem","position":3,"item":{"@id":"/ai/models/","name":"Models"}}]} ```