> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.beatapi.io/text-api/gpt-6-1-sol/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.beatapi.io/_mcp/server.

# GPT-6.1 Sol API

> Use GPT-6.1 Sol for coding and agent workflows through the BeatAPI Responses API, with current token pricing and reasoning settings.

Use the exact model ID `gpt-6.1-sol`. GPT-6.1 Sol has a 1,050,000-token context window and a model output limit of 128,000 tokens. New integrations and tool-calling workflows should use **OpenAI Responses**.

## Quick start

`POST https://api.beatapi.io/v1/responses`

```typescript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.BEATAPI_API_KEY,
  baseURL: "https://api.beatapi.io/v1"
});

const response = await client.responses.create({
  model: "gpt-6.1-sol",
  input: "Suggest a minimal fix for a webhook handler that processes duplicate events.",
  reasoning: { effort: "medium" }
});

console.log(response.output_text);
```

```bash
curl --request POST \
  --url https://api.beatapi.io/v1/responses \
  --header 'Authorization: Bearer <BEATAPI_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "gpt-6.1-sol",
    "input": "Suggest a minimal fix for a webhook handler that processes duplicate events.",
    "reasoning": { "effort": "medium" }
  }'
```

## Reasoning and request formats

Supported reasoning efforts are `low`, `medium`, `high`, `xhigh`, and `max`. Start with `medium` and evaluate the latency and answer quality for your workload. `none` and `minimal` are not supported by this model.

Use Responses for tool calls. For an existing SDK integration, consult the [Text API format guide](/text-api) and the `supported_endpoint_types` returned by `GET /v1/models`. Request-format compatibility does not imply that every provider-specific option or tool is supported.

## BeatAPI pricing

Prices below are USD per **1 million tokens**, checked on September 30, 2026.

| Token type   | Input up to 272K | Input over 272K |
| ------------ | ---------------: | --------------: |
| Input        |           \$0.80 |          \$1.60 |
| Cached input |           \$0.04 |          \$0.08 |
| Cache write  |           \$1.00 |          \$2.00 |
| Output       |           \$4.00 |          \$6.00 |

When input exceeds 272,000 tokens, the higher tier applies to the full request. Cache rates apply when the corresponding cache usage is reported. See the [current price table](https://beatapi.io/pricing) before budgeting a workload.

## Availability and usage

Call `GET https://api.beatapi.io/v1/models` with your BeatAPI key and confirm `gpt-6.1-sol` is enabled for the key's group. Model availability and free-credit eligibility follow your account and key settings.

The same BeatAPI key and USD balance cover supported text models and other BeatAPI capabilities. Inspect the request ID, token usage, status, and settled charge in Dashboard usage logs.

Model limits and reasoning options: [OpenAI GPT-6.1 Sol reference](https://developers.openai.com/api/docs/models/gpt-6.1-sol).

> Use GPT-6.1 Sol for coding and agent workflows through the BeatAPI Responses API, with current token pricing and reasoning settings.