What is GPT 5.6 Luna built for?

Cost-sensitive, high-volume workloads. OpenAI built GPT 5.6 Luna as the fast, affordable tier of the GPT-5.6 family, for pipelines where per-request price decides feasibility.

How does GPT 5.6 Luna compare with GPT-5.6 Terra and GPT-5.6 Sol?

GPT 5.6 Luna carries the lowest price in the family and the least capability headroom. GPT-5.6 Terra balances intelligence against cost for everyday work, and GPT-5.6 Sol is the flagship for the hardest tasks.

What context window and output limit does GPT 5.6 Luna support?

1.1M tokens, with up to 128K tokens of output per request, matching the rest of the GPT-5.6 family. A low-cost tier with that much context can read long documents in one pass.

What inputs does GPT 5.6 Luna accept?

Text and images, with text output. Audio and video input are not supported, so route voice work to the gpt-realtime family instead.

Does GPT 5.6 Luna support tool calling and structured outputs?

Yes. Function calling, structured outputs, and streaming all work, and the Responses API adds web search, file search, code interpreter, computer use, and MCP tools.

Does GPT 5.6 Luna support zero data retention through AI Gateway?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

What are typical latency characteristics?

This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.

OpenAI

GPT 5.6 Luna

GPT 5.6 Luna is the fast, low-cost model of the GPT-5.6 family, holding strong capability at the lowest price in the series while sharing the family's agentic gains in coding, biology, and cybersecurity and a context window of 1.1M tokens. Your use is subject to OpenAI's Terms & Privacy Policies.

View API reference

Input and output price: Prices from: Input $0.20, Output $1.20, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

const result = streamText({
  model: 'openai/gpt-5.6-luna',
  prompt: 'Why is the sky blue?'
})

Read docs

Overview Playground Providers Uptime Status Throughput Latency API Similar About FAQ

Copy link to headingPlayground

Try out GPT 5.6 Luna by OpenAI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.

GPT 5.6 Luna

Copy link to headingProviders

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Checking availability for your team

Provider

Context	Max Output	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	ZDR	No Training	Regional Inference	Free Tier	Release Date

OpenAI

Legal:Terms•Privacy

1.1M

128K

2.1 s

48 tps

$0.20/M+4 more

$1.20/M+4 more

Read$0.02/M

Write$0.25/M

$10/K

07/09/2026

Azure

Legal:Terms•Privacy

1.1M

128K

4.0 s

143 tps

$0.20/M+1 more

$1.20/M+1 more

Read$0.02/M

Write$0.25/M

$14/K

07/09/2026

Bedrock

Legal:Terms•Privacy

1.1M

128K

4.8 s

122 tps

$0.20/M+2 more

$1.20/M+2 more

Read$0.02/M

Write$0.25/M

$10/K

07/09/2026

Getting started

Call GPT 5.6 Luna through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-luna',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Top-level parameters

The same GPT 5.6 Luna request in each API format AI Gateway supports.

top-level-params.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-luna',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
  });

  console.log(result.text);
}

main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

Parameter	Type	Required	Description
`model`	`string`	Yes	Model ID in the form `creator/model`, e.g. `openai/gpt-5.6-luna`. AI Gateway routes the request to an available provider.
`maxOutputTokens`	`number`	No	Hard cap on generated tokens. GPT 5.6 Luna supports up to `128,000` output tokens. Reasoning tokens count toward this limit.
`reasoning`	`'provider-default' \| 'none' \| 'minimal' \| 'low' \| 'medium' \| 'high' \| 'xhigh'`	No	Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under `providerOptions` take precedence when both are set. See the Reasoning section below.
`providerOptions`	`Record<string, JSONValue>`	No	AI Gateway routing options under `gateway`, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

Input	Formats	Sources	Max count	Max size	Limits
Text	—	—	—	—	Prompt and response share the 1.1M-token context window
Image	—	URL, base64, Uint8Array	—	—	Sent as image parts in messages; counts as input tokens
PDF	—	URL, base64, Uint8Array	—	—	Sent as file parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK openai provider docs.

provider-options.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-luna',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['openai', 'azure'],
      },
    },
  });

  console.log(result.text);
}

main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

Parameter	Type	Required	Description
`providerOptions.gateway.only`	`string[]`	No	Restrict routing to these provider slugs. Requests fail over only within the listed providers.
`providerOptions.gateway.order`	`string[]`	No	Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
`providerOptions.gateway.sort`	`'cost' \| 'ttft' \| 'tps'`	No	Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
`providerOptions.gateway.zeroDataRetention`	`boolean`	No	Route only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Reasoning

AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.

Learn more in the AI Gateway reasoning guide.

reasoning.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-luna',
    prompt: 'Explain the Monty Hall problem step by step.',
    reasoning: 'high',
  });

  console.log(result.text);
}

main().catch(console.error);

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-luna',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

PDF input

Attach PDFs as file parts. Their contents count as input tokens.

pdf-input.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-luna',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Summarize this document.' },
          {
            type: 'file',
            mediaType: 'application/pdf',
            data: 'https://example.com/document.pdf',
          },
        ],
      },
    ],
  });

  console.log(result.text);
}

main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts

import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-luna',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });

  console.log(result.text);
}

main().catch(console.error);

Fast mode

GPT 5.6 Luna can run in fast mode for lower latency by appending -fast to the model ID.

fast-mode.ts

import { generateText } from 'ai';
import 'dotenv/config';

async function main() {
  const result = await generateText({
    model: 'openai/gpt-5.6-luna-fast',
    prompt: 'Why is the sky blue?',
  });

  console.log(result.text);
}

main().catch(console.error);

Copy link to headingMore models by OpenAI

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

openai/gpt-6-astra

1.1M

3.2 s

63 tps

$10/M+2 more

$50/M+2 more

Read$1/M

Write$12.50/M

$10/K

09/04/2026

openai/gpt-5.6-sol

1.1M

3.5 s

66 tps

$4/M+2 more

$20/M+2 more

Read$0.40/M

Write$5/M

$10/K

07/09/2026

openai/gpt-5.6-terra

1.1M

1.8 s

126 tps

$2/M+2 more

$12/M+2 more

Read$0.20/M

Write$2.50/M

$10/K

07/09/2026

openai/gpt-5.4

1.1M

1.7 s

92 tps

$2.50/M+2 more

$15/M+2 more

Read$0.25/M

$10/K

03/05/2026

openai/gpt-5-nano

400K

4.4 s

201 tps

$0.05/M

$0.40/M

Read$0.005/M

$14/K

08/07/2025

openai/gpt-5-mini

400K

3.1 s

198 tps

$0.25/M+1 more

$2/M+1 more

Read$0.03/M

$14/K

08/07/2025

Copy link to headingAbout GPT 5.6 Luna

GPT 5.6 Luna became available on AI Gateway on July 9, 2026 as the fast, low-cost model of the GPT-5.6 family, alongside GPT-5.6 Sol and GPT-5.6 Terra. All three GPT-5.6 models handle agentic work across coding, biology, and cybersecurity better than the previous generation, and all three use fewer tokens to reach an answer.

OpenAI built GPT 5.6 Luna for cost-sensitive, high-volume workloads, and it maps to the nano tier of earlier GPT-5 families. The point of the tier is unit economics: features that touch every request, every session, or every document stay viable when the per-request cost stays low.

GPT 5.6 Luna accepts text and image input and returns text, with a context window of 1.1M tokens and up to 128K tokens of output per request. Reasoning tokens, streaming, function calling, and structured outputs are supported, and the Responses API adds web search, file search, code interpreter, computer use, and MCP (Model Context Protocol) tools. The large context window means a low-cost model can still read a long document in one pass.

Set the model to openai/gpt-5.6-luna in the AI SDK, the Chat Completions API, the Responses API, or another supported API format, from TypeScript or Python. List pricing is $0.2 per million input tokens and $1.2 per million output tokens, with cached input at $0.02. Short-context and long-context requests are priced separately. AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference, including for Bring Your Own Key requests.

Copy link to headingWhat To Consider When Choosing a Provider

Configuration: GPT 5.6 Luna corresponds to the nano tier of earlier GPT-5 families and targets cost-sensitive, high-volume workloads. Upstream list prices came down after launch, and AI Gateway passes the provider rate through with no markup.
Configuration: The tradeoff is capability headroom. Classification, extraction, routing, and short generation suit GPT 5.6 Luna; multi-step agentic runs and hard research questions belong on GPT-5.6 Terra or GPT-5.6 Sol. Test that boundary with your own prompts, because a lower rate only pays off while output quality holds.
Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen to Use GPT 5.6 Luna

Best for

High-Volume Classification: Labeling, routing, and moderation pipelines that run on every request
Structured Extraction: Pulling fields from documents, tickets, and logs at scale
Fast Interactive Responses: Autocomplete, summaries, and suggestions in latency-sensitive surfaces
Agent Support Steps: Cheap intermediate turns in a pipeline that escalates when a step gets hard
Cost-Bound Product Features: Surfaces where per-request price decides whether the feature ships

Consider alternatives when

Balanced Everyday Work: GPT-5.6 Terra weighs intelligence against cost for general production traffic
Hardest Agentic Tasks: GPT-5.6 Sol is the flagship and the most capable model in the family
Autonomous Coding Agents: GPT-5.x codex variants target sandboxed software engineering directly
Live Voice Interfaces: The gpt-realtime family handles speech-to-speech conversation natively

Copy link to headingConclusion

GPT 5.6 Luna is where high-volume GPT-5.6 traffic belongs: the lowest price in the family, the same context window as its siblings, and the generation's agentic gains. Run the repetitive work here and escalate to GPT-5.6 Terra or GPT-5.6 Sol when a request needs more depth.

Copy link to headingFrequently Asked Questions

What is GPT 5.6 Luna built for?
Cost-sensitive, high-volume workloads. OpenAI built GPT 5.6 Luna as the fast, affordable tier of the GPT-5.6 family, for pipelines where per-request price decides feasibility.
How does GPT 5.6 Luna compare with GPT-5.6 Terra and GPT-5.6 Sol?
GPT 5.6 Luna carries the lowest price in the family and the least capability headroom. GPT-5.6 Terra balances intelligence against cost for everyday work, and GPT-5.6 Sol is the flagship for the hardest tasks.
What context window and output limit does GPT 5.6 Luna support?
1.1M tokens, with up to 128K tokens of output per request, matching the rest of the GPT-5.6 family. A low-cost tier with that much context can read long documents in one pass.
What inputs does GPT 5.6 Luna accept?
Text and images, with text output. Audio and video input are not supported, so route voice work to the gpt-realtime family instead.
Which APIs can I use to call GPT 5.6 Luna?
Set the model to openai/gpt-5.6-luna in the AI SDK, the Chat Completions API, the Responses API, or another supported API format. AI Gateway accepts each format and routes the request.
Does GPT 5.6 Luna support tool calling and structured outputs?
Yes. Function calling, structured outputs, and streaming all work, and the Responses API adds web search, file search, code interpreter, computer use, and MCP tools.
What does GPT 5.6 Luna cost?
List pricing is $0.2 per million input tokens and $1.2 per million output tokens, with cached input at $0.02. Short-context and long-context requests are priced separately, and AI Gateway mirrors provider pricing with no markup.
Does GPT 5.6 Luna support zero data retention through AI Gateway?
Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.
What are typical latency characteristics?
This page shows live throughput and time-to-first-token metrics measured across real AI Gateway traffic.

GPT 5.6 Luna

Copy link to headingPlayground

Copy link to headingProviders

Copy link to headingUptime24 hours

Copy link to headingThroughput24 hours

Copy link to headingLatency24 hours

Getting started

Top-level parameters

Input limits

Provider options

Routing across providers

Reasoning

Image input

PDF input

Tool calling

Fast mode

Copy link to headingMore models by OpenAI

Copy link to headingAbout GPT 5.6 Luna

Copy link to headingWhat To Consider When Choosing a Provider

Copy link to headingWhen to Use GPT 5.6 Luna

Best for

Consider alternatives when

Copy link to headingConclusion

Copy link to headingFrequently Asked Questions