GPT-5.6 Luna
By OpenAI. Unknown parameters, a context window of 1,050,000 tokens, licence Unknown.
Facts
- Released
- 2026-07-09 the release date models.dev records models.dev, read
- Licence
- Unknown
- Open weights
- No models.dev records whether the weights are open models.dev, read
- Parameters
- Unknown
- Active parameters
- Unknown
- Knowledge cutoff
- 2026-02-16 the knowledge cutoff OpenRouter lists OpenRouter, read
- Context window
- 1,050,000 tokens the context length OpenRouter lists OpenRouter, read
- 1,050,000 tokens the context limit models.dev records for the maker's own API models.dev, read
- Longest output
- 128,000 tokens the largest output OpenRouter's first provider allows OpenRouter, read
- 128,000 tokens the output limit models.dev records for the maker's own API models.dev, read
- Tool calling
- Yes OpenRouter lists tools among the supported parameters OpenRouter, read
- Yes models.dev records tool_call as true models.dev, read
- Structured output
- Yes OpenRouter lists structured outputs among the supported parameters OpenRouter, read
- Yes models.dev records structured_output as true models.dev, read
- Reasoning controls
- Yes OpenRouter lists reasoning controls, with the efforts max, xhigh, high, medium, low, none OpenRouter, read
- Yes models.dev records reasoning as true models.dev, read
- Inputs and outputs
- file, image, text in, text out OpenRouter, read
- Good for
- Reasoning: OpenRouter lists reasoning controls for it OpenRouter, read
- Vision: OpenRouter lists images among its inputs OpenRouter, read
Prices
| Provider | Input | Output | Context | As of | Source |
|---|---|---|---|---|---|
| OpenAI through OpenRouter | 0.100 USD | 0.600 USD | 1,050,000 | OpenRouter endpoints, read | |
| OpenAI through OpenRouter | 0.100 USD | 0.600 USD | 1,050,000 | OpenRouter endpoints, read | |
| Azure through OpenRouter | 0.200 USD | 1.20 USD | 1,050,000 | OpenRouter endpoints, read | |
| Azure through OpenRouter | 0.200 USD | 1.20 USD | 1,050,000 | OpenRouter endpoints, read | |
| OpenAI direct | 0.200 USD | 1.20 USD | 1,050,000 | older than 30 days; check the provider | models.dev, read |
| OpenAI through OpenRouter | 0.200 USD | 1.20 USD | 1,050,000 | OpenRouter endpoints, read | |
| OpenAI through OpenRouter | 0.200 USD | 1.20 USD | 1,050,000 | OpenRouter endpoints, read | |
| Amazon Bedrock through OpenRouter | 0.220 USD | 1.32 USD | 1,050,000 | OpenRouter endpoints, read | |
| Amazon Bedrock through OpenRouter | 0.220 USD | 1.32 USD | 1,050,000 | OpenRouter endpoints, read | |
| Azure through OpenRouter | 0.220 USD | 1.32 USD | 1,050,000 | OpenRouter endpoints, read | |
| Azure through OpenRouter | 0.220 USD | 1.32 USD | 1,050,000 | OpenRouter endpoints, read | |
| Azure through OpenRouter | 0.220 USD | 1.32 USD | 1,050,000 | OpenRouter endpoints, read | |
| Azure through OpenRouter | 0.220 USD | 1.32 USD | 1,050,000 | OpenRouter endpoints, read | |
| OpenAI through OpenRouter | 0.400 USD | 2.40 USD | 1,050,000 | OpenRouter endpoints, read | |
| OpenAI through OpenRouter | 0.400 USD | 2.40 USD | 1,050,000 | OpenRouter endpoints, read |
Run it on your own hardware
No source lists weight files or a parameter count for this model, so its memory needs are Unknown.
Use it from your harness
Set up for OpenAI with the model gpt-5.6-luna. Each endpoint page has the same setup for its own address.
OpenCode
Put this in opencode.json in your project folder:
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"openai": {
"npm": "@ai-sdk/openai-compatible",
"name": "OpenAI",
"options": {
"baseURL": "https://api.openai.com/v1",
"apiKey": "{env:OPENAI_API_KEY}"
},
"models": {
"gpt-5.6-luna": {
"name": "GPT-5.6 Luna",
"limit": {
"context": 1050000,
"output": 128000
}
}
}
}
}
}- OpenCode reads any OpenAI-compatible address through the @ai-sdk/openai-compatible package, and an address that speaks the Responses API through @ai-sdk/openai.
From OpenCode documentation, read .
Pi
Put this in ~/.pi/agent/models.json:
{
"providers": {
"openai": {
"baseUrl": "https://api.openai.com/v1",
"api": "openai-completions",
"apiKey": "$OPENAI_API_KEY",
"models": [
{
"id": "gpt-5.6-luna"
}
]
}
}
}- The apiKey field can name an environment variable as $NAME.
From Pi documentation, read .
Codex
Put this in ~/.codex/config.toml:
model = "gpt-5.6-luna"- Codex speaks the Responses API only: responses is the one supported wire API of a custom provider. Ollama and LM Studio are built in and start with --oss.
From Codex documentation, read .
Claude Code
Claude Code sends Anthropic Messages requests, and OpenAI documents no such address. A gateway that translates to that API can sit in between.
- Claude Code sends Anthropic Messages requests to ANTHROPIC_BASE_URL. Anthropic says it does not support routing Claude Code to models other than Claude through any gateway, so some features may not work with another model.
From Claude Code documentation, read .
Other ways to reach it
- OpenRouter, model
openai/gpt-5.6-luna
Published results
These are results other people published. Baltor did not run them and does not rank models by them.
- Artificial Analysis Intelligence Index: 37.3 published by Artificial Analysis OpenRouter, read
- Artificial Analysis Coding Index: 71.4 published by Artificial Analysis OpenRouter, read
- Artificial Analysis Agentic Index: 42.1 published by Artificial Analysis OpenRouter, read
Sources of this page
Paid links
No link in this directory is a paid link or an ad, and no listing is paid for. The order and the contents of every list come from the sources named on this page.