# GPT-5.6 Luna

Canonical page: https://agentsky.dev/models/openai/gpt-5.6-luna
JSON record: https://gateway.agentsky.dev/v1/models/openai/gpt-5.6-luna

GPT-5.6 Luna is a text and image-input model by OpenAI, available through the AgentSky API as openai/gpt-5.6-luna at $0.14 per million input tokens and $0.84 per million output tokens, with a 1.1M context window.

The cost-optimised GPT-5.6 tier, built for high-volume workloads.

## Facts

- **Model id:** `openai/gpt-5.6-luna`
- **Maker:** OpenAI
- **Input modalities:** Text, Image
- **Context:** 1.1M
- **Max output tokens:** 128,000
- **Released:** Jul 9, 2026
- **Aliases:** `openai/gpt-5.6-luna`, `gpt-5.6-luna`

## Pricing

USD per million tokens on the default plan. Signed-in pages show your own plan's price; every response carries the cost of that call in `usage.cost`.

| Meter | Per 1M tokens |
|---|---|
| Input | $0.14 |
| Output | $0.84 |
| Cache read | $0.014 |
| Cache write | $0.175 |

## Use it

Anthropic wire base URL: `https://gateway.agentsky.dev`. OpenAI wire base URL: `https://gateway.agentsky.dev/v1`. Authenticate with an AgentSky API key (`ast_…`) and pass the model id.

### OpenAI SDK

```js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "openai/gpt-5.6-luna",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response
```

### Codex

```bash
export OPENAI_BASE_URL="https://gateway.agentsky.dev/v1"
export OPENAI_API_KEY="$AGENTSKY_API_KEY"

codex --model openai/gpt-5.6-luna
```

### OpenCode

```js
// opencode.json — then switch models any time with /models
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "agentsky": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AgentSky",
      "options": {
        "baseURL": "https://gateway.agentsky.dev/v1",
        "apiKey": "{env:AGENTSKY_API_KEY}"
      },
      "models": { "openai/gpt-5.6-luna": {} }
    }
  }
}
```

## Run it with an agent

- [Hermes + GPT-5.6 Luna](https://agentsky.dev/agents/hermes/with/gpt-5.6-luna)
- [Claude Code + GPT-5.6 Luna](https://agentsky.dev/agents/claude-code/with/gpt-5.6-luna)
- [Codex + GPT-5.6 Luna](https://agentsky.dev/agents/codex/with/gpt-5.6-luna)
- [OpenClaw + GPT-5.6 Luna](https://agentsky.dev/agents/openclaw/with/gpt-5.6-luna)
- [pi + GPT-5.6 Luna](https://agentsky.dev/agents/pi/with/gpt-5.6-luna)
- [DeepSeek Harness + GPT-5.6 Luna](https://agentsky.dev/agents/dsh/with/gpt-5.6-luna)
- [Kimi Code + GPT-5.6 Luna](https://agentsky.dev/agents/kimi-code/with/gpt-5.6-luna)
- [OpenCode + GPT-5.6 Luna](https://agentsky.dev/agents/opencode/with/gpt-5.6-luna)
- [Cline + GPT-5.6 Luna](https://agentsky.dev/agents/cline/with/gpt-5.6-luna)
- [DeepAgents + GPT-5.6 Luna](https://agentsky.dev/agents/deepagents/with/gpt-5.6-luna)
- [goose + GPT-5.6 Luna](https://agentsky.dev/agents/goose/with/gpt-5.6-luna)
- [Grok Build + GPT-5.6 Luna](https://agentsky.dev/agents/grok-build/with/gpt-5.6-luna)
- [Kilo + GPT-5.6 Luna](https://agentsky.dev/agents/kilo/with/gpt-5.6-luna)
- [Qwen Code + GPT-5.6 Luna](https://agentsky.dev/agents/qwen-code/with/gpt-5.6-luna)

## Questions

### What is GPT-5.6 Luna?

GPT-5.6 Luna is a model from OpenAI. The cost-optimised GPT-5.6 tier, built for high-volume workloads.

### How much does GPT-5.6 Luna cost?

$0.14 / $0.84 per million tokens at the prices shown, for input and output respectively. The exact price of every call comes back in the response as usage.cost, so you never have to compute it.

### What is the context length of GPT-5.6 Luna?

1.1M tokens, and it writes up to 128K tokens in one reply. These are the limits listed for this model in the current AgentSky catalog.

### Which clients can call GPT-5.6 Luna?

Anything that speaks the OpenAI-compatible request format. Point the client's base URL at the gateway, use an AgentSky key, and pass openai/gpt-5.6-luna as the model.

### How do I name GPT-5.6 Luna in a request?

The gateway accepts openai/gpt-5.6-luna, gpt-5.6-luna. Any of them resolves to the same model, so an existing integration usually needs no change to its model string.

### Can GPT-5.6 Luna read images?

Yes. Its listed input types are text, image. Include the image with your request; image input does not imply image generation.

### What output can GPT-5.6 Luna produce?

The listed output types are text. This model returns text. Producing image, video or audio files requires a suitable tool or another model; it is not included in text generation.

### How should I plan a long prompt for GPT-5.6 Luna?

Plan your instructions, conversation history and source material around the 1.1M-token context limit, leaving room for the response. The listed response ceiling is 128K tokens. A larger window lets you supply more relevant material; it does not make unrelated content useful.

### What would 10,000 input tokens and 2,000 output tokens cost with GPT-5.6 Luna?

At the displayed input and output rates, the model-token subtotal is $0.00308. This example assumes uncached input and excludes additional pricing categories, tool calls and agent runtime. Actual usage determines the final charge.

### How is cached input priced for GPT-5.6 Luna?

The catalog lists $0.014 per million cache-read tokens. Cache writes are listed at $0.175 per million tokens. Repeating a prompt does not by itself guarantee a cache hit; only usage reported as cached receives that rate.

### Does the GPT-5.6 Luna token price cover an entire agent task?

No. The model price covers the model usage described above. A task can also incur tool and runtime charges, and several model calls may be needed to complete it. Compare total task usage when evaluating cost.

### How do I use GPT-5.6 Luna on AgentSky?

The composer above preselects GPT-5.6 Luna for a compatible agent. Enter a concrete task, select any tools or connectors it needs, and send. Sign in if prompted; paid execution requires available credits.