# GPT-6 Luna API — pricing & specs

GPT-6 Luna is an OpenAI text and image model with selectable reasoning effort and Responses function calling. On KeepRouter, GPT-6 Luna costs $0.2500 per 1M input tokens and $0.7500 per 1M output tokens, billed pay-as-you-go with no monthly fee; actual request cost depends on measured token usage. Call it through a compatible KeepRouter endpoint supported by its active route, with the model id `gpt-6-luna`.

| Spec | Value |
|---|---|
| Maker | OpenAI |
| Modality | Text, vision |
| Context window | 1,050,000 tokens |
| Max output | 128,000 tokens |
| Knowledge cutoff | 2026-05-18 |
| Input price | $0.2500 per 1M tokens |
| Output price | $0.7500 per 1M tokens |
| Cached input | $0.0200 per 1M tokens |
| Capabilities | Vision (image input), Chat completions, Streaming where supported, Tool calling where supported |
| Endpoint | POST /v1/chat/completions or POST /v1/responses |
| Model id | `gpt-6-luna` |

## Call it via /v1/responses

Use POST /v1/chat/completions or, on compatible chat routes, POST /v1/messages; streaming and tool support depend on the model's active route.

### cURL

```bash
curl https://keeprouter.com/v1/responses \
  -H "Authorization: Bearer $KEEPROUTER_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-6-luna","input":"Reply with one short greeting.","reasoning":{"effort":"low"},"max_output_tokens":1024,"store":false}'
```

### Python

```python
import os
from openai import OpenAI
client = OpenAI(base_url="https://keeprouter.com/v1", api_key=os.environ["KEEPROUTER_KEY"], max_retries=0)
r = client.responses.create(model="gpt-6-luna", input="Reply with one short greeting.", reasoning={"effort": "low"}, max_output_tokens=1024, store=False)
```

### JavaScript

```js
const res = await fetch("https://keeprouter.com/v1/responses", {
  method: "POST",
  headers: { Authorization: "Bearer " + process.env.KEEPROUTER_KEY, "Content-Type": "application/json" },
  body: JSON.stringify({"model":"gpt-6-luna","input":"Reply with one short greeting.","reasoning":{"effort":"low"},"max_output_tokens":1024,"store":false}),
});
```

## Estimate API costs

At the current KeepRouter customer price, an example workload of 1,000 total input tokens, no cached input, and 500 output tokens per request costs approximately $0.000625 per request. At 100 requests per day, that is $1.88 over 30 days. This is a usage estimate, excluding processing fees, taxes, retries and application infrastructure. Actual usage, cache hits and supported generation durations need their own checks.

[Adjust quantities in the API cost calculator](/tools/api-cost-calculator?model=gpt-6-luna).

## Model identity and official sources

Sources checked 2026-10-03.

### Bounded generation checked

On October 3, 2026, this exact ID returned HTTP 200, visible text and final token usage through /v1/responses. These small checks do not establish task accuracy, full-context capacity, media compatibility or sustained throughput.

[KeepRouter · API reference](https://keeprouter.com/api/docs)

### Model and evaluation task

Evaluate coding changes against the same repository tests, including a multi-step tool conversation. Sol and Luna have different prices; compare cost per accepted change rather than cost per token alone.

[OpenAI · model documentation](https://developers.openai.com/api/docs/models/gpt-6-luna)

### API contract and migration

Use Responses for reasoning with tools. Chat Completions tools require reasoning_effort=none. The copyable example uses Responses and a bounded output budget.

[OpenAI · model documentation](https://developers.openai.com/api/docs/models/gpt-6-luna)

### Customer price and verification scope

The live prices above are KeepRouter customer rates. One fixed input rate covers ordinary input and the supported cache-write or long-context ceiling; no extra cache-write fee is added. Cache hits use the separate cached-input rate. These are not the maker's short-context base prices. Maker specifications and catalog checks do not certify every generation workflow.

[KeepRouter · pricing and usage](https://keeprouter.com/models) · [KeepRouter · workload calculator](https://keeprouter.com/tools/api-cost-calculator)

## How to evaluate GPT-6 Luna

GPT-6 Luna is listed on KeepRouter as text, vision under the exact id `gpt-6-luna`. Use /v1/responses for the listed route; a maker's upstream features do not automatically apply to this gateway endpoint. The published context window is 1,050,000 tokens and the published output limit is 128,000 tokens. These are limits, not a recommended request size.

**First workload:** Start with a text question plus one representative image, then repeat the same question with text only. Compare answer quality, latency and billed input/output tokens.

**Before production:** For agent use, test tool calls and structured output on this exact model route before production; an OpenAI-compatible chat endpoint alone does not prove either feature.

### Agent setup paths

### OpenAI SDK (Responses)

Use the SDK's responses.create operation with the exact model `gpt-6-luna`. In an agent product, select an adapter that emits /v1/responses; a Chat Completions configuration is not an equivalent tool integration. Preserve complete returned conversation items between tool turns. [Official setup](https://developers.openai.com/api/docs/models/gpt-6-luna).

```python
import os
from openai import OpenAI
client = OpenAI(base_url="https://keeprouter.com/v1", api_key=os.environ["KEEPROUTER_KEY"], max_retries=0)
r = client.responses.create(model="gpt-6-luna", input="Reply with one short greeting.", reasoning={"effort": "low"}, max_output_tokens=1024, store=False)
```


These are documented configuration paths; model-specific tool, streaming and multimodal behavior still needs a real request test.

## Public model usage evidence

No public, exact-variant usage figure has been verified for this KeepRouter model id. Missing data is not zero usage; family-level or maker-wide traffic is not presented as this model's traffic.

## Published examples and cases

No exact-model customer case has been verified for this entry. The workload above is an evaluation recipe, not a claim of a public deployment.

## Source and verification boundary

[Official GPT-6 Luna documentation](https://developers.openai.com/api/docs/models/gpt-6-luna). KeepRouter's live catalog is authoritative for the customer price and enabled endpoint shown here; the maker remains authoritative for upstream model capabilities and limits.

## Pricing and implementation guides

- [GPT-6.1 Sol: Responses, tools and pricing](https://keeprouter.com/blog/gpt-6-1-sol-api-tools-pricing)
- [GPT API pricing and SDK migration](https://keeprouter.com/blog/gpt-api-pricing-sdk-migration)
- [Calculate your API workload cost](https://keeprouter.com/tools/api-cost-calculator)
- [KeepRouter API keys: move from free to paid models](https://keeprouter.com/blog/keeprouter-api-key-free-to-paid)

## Guides

- [Call GPT-6 Luna with the OpenAI SDK](https://keeprouter.com/use-cases/openai-sdk.md)

## Related models

- [GPT-6 Sol](https://keeprouter.com/models/gpt-6-sol.md) by OpenAI — $5.00 per 1M input tokens and $15.00 per 1M output tokens
- [GPT-6 Astra](https://keeprouter.com/models/gpt-6-astra.md) by OpenAI — $25.00 per 1M input tokens and $75.00 per 1M output tokens
- [GPT-6.1 Sol](https://keeprouter.com/models/gpt-6.1-sol.md) by OpenAI — $5.00 per 1M input tokens and $15.00 per 1M output tokens
- [GPT-5.5](https://keeprouter.com/models/gpt-5.5.md) by OpenAI — $5.00 per 1M input tokens and $30.00 per 1M output tokens
- [GPT Image 1.5](https://keeprouter.com/models/gpt-image-1.5.md) by OpenAI — $8.00 per 1M input tokens and $32.00 per 1M output tokens
- [GPT-4o](https://keeprouter.com/models/gpt-4o.md) by OpenAI — $2.50 per 1M input tokens and $10.00 per 1M output tokens

## More

- [All models & pricing](https://keeprouter.com/models.md)
- [Quickstart](https://keeprouter.com/docs/quickstart.md)
- [Get an API key](https://keeprouter.com/login?returnTo=%2Fconsole%2Fkeys%3Fmodel%3Dgpt-6-luna)

_Catalog facts and prices last changed 2026-10-03._
_Page content reviewed 2026-10-03._