# gpt-5.6-luna — API, Pricing & Context Window

gpt-5.6-luna on Vivgrid: OpenAI's fast, low-cost gpt-5.6 model with a 1.05M-token context window for high-volume agent workloads.

`gpt-5.6-luna` is the fast, low-cost model in OpenAI's gpt-5.6 family. Unlike earlier small models, it keeps the family's **1.05M-token context window**, making it the cheapest way to run long-context agents at scale.

On Vivgrid, `gpt-5.6-luna` is served through a single OpenAI-compatible endpoint with **geo-distributed acceleration across AMER and EMEA**, reachable with the same unified key as the rest of the catalog.

## Specifications

|     |     |
| --- | --- |
| **Provider** | OpenAI |
| **Model ID** | `gpt-5.6-luna` |
| **Best for** | General-purpose |
| **Context window** | 1,050,000 tokens |
| **Max output** | 128,000 tokens |
| **Modalities** | Text, Image |
| **Tool / function calling** | Yes |
| **Knowledge cutoff** | 2026-03 |
| **Acceleration** | ⚡ Geo-Distributed — AMER, EMEA |

## Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

| Input | Cached input | Output |
| --- | --- | --- |
| $1.00 | $0.10 | $6.00 |

## Quick start

Call `gpt-5.6-luna` through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the [Vivgrid Console](https://console.vivgrid.com/).

```
curl https://api.vivgrid.com/v1/chat/completions \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-luna",
    "messages": [\
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }\
    ],
    "stream": true
  }'
```

Requests beyond **272K input tokens** are billed at the long-context rate: $2.00 input / $0.20 cached input / $9.00 output per 1M tokens.

## Ideal use cases

- High-volume agent and content pipelines where cost dominates
- Long-context retrieval, summarization, and classification
- Fast interactive assistants and chat products
- Fallback or draft model alongside gpt-5.6-sol / terra

## Related models

- [gpt-5.6-terra](/content/docs/models/gpt-5.6-terra/index.html) — the balanced gpt-5.6 model
- [gpt-5.6-sol](/content/docs/models/gpt-5.6-sol/index.html) — the flagship gpt-5.6 model
- [gpt-5.4-mini](/content/docs/models/gpt-5.4-mini/index.html) — the prior-generation light model