# GPT-6.1 Sol

> GPT-6.1 Sol is an upgrade to GPT-6 Sol, released by OpenAI on September 29, 2026. OpenAI describes it as near-Astra performance for complex coding, computer use and professional work, at the cost of the Sol tier rather than the flagship.

Canonical: https://routemux.com/openai/gpt-6.1-sol
Provider: OpenAI

## Key facts

| Field | Value |
| --- | --- |
| Model ID | openai/gpt-6.1-sol |
| Official model ID | gpt-6.1-sol |
| Context window | 1.1M |
| Max output | 128K |
| Input modalities | text, image |
| Output modalities | text |
| Capabilities | Vision, Reasoning, Tool Calling, Coding, Cache, Paid Cache Write |
| Upstream release | 2026-09-29 |
| Availability | available |

## Pricing

- RouteMux input: $0.2 per 1M tokens
- RouteMux output: $1 per 1M tokens
- Official input: $2 per 1M tokens
- Official output: $10 per 1M tokens
- Cache read: $0.01 per 1M tokens
- Cache write: $0.25 per 1M tokens
- Saving vs official: 90%
- Official price source: openai_x0.10, verified 2026-09-30

Billing is prepaid wallet, charged per successful request only.

## API access

Base URL: https://api.routemux.com

Supported protocols:

- openai_chat
- openai_responses
- anthropic_messages

## What is GPT-6.1 Sol

GPT-6.1 Sol is an upgrade to GPT-6 Sol, released by OpenAI on September 29, 2026. OpenAI describes it as near-Astra performance for complex coding, computer use and professional work, at the cost of the Sol tier rather than the flagship.

It accepts text and image input, supports tool calling and explicit prompt caching, and exposes reasoning effort as a request parameter from low to max. Unlike GPT-6 Sol it does not accept an effort of none, so every request does at least some reasoning.

Through RouteMux it is $0.20 per 1M input tokens against OpenAI's $2, $1.00 against $10 on output, and $0.01 against $0.10 for cached input. It is reachable over OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages, so an Anthropic-shaped client can call it without rewriting its request layer.

## Key capabilities

- **Near-Astra on agentic work** — OpenAI positions it close to GPT-6 Astra on agentic coding, computer use and professional work.
- **Reasoning from low to max** — Effort is a request parameter spanning low, medium, high, xhigh and max. None is not accepted.
- **Vision and tools included** — Image input, tool calling and explicit prompt caching are all supported.
- **Three protocols** — OpenAI Chat, OpenAI Responses, and Anthropic Messages all route to this model.

## Other variants in this family

- GPT-6 Astra (`openai/gpt-6-astra`)
- GPT-6 Sol (`openai/gpt-6-sol`)
- GPT-6 Luna (`openai/gpt-6-luna`)

## Sources

- [OpenAI — Introducing GPT-6.1 Sol](https://openai.com/index/introducing-gpt-6-1-sol/)
- [OpenAI — GPT-6.1 Sol](https://developers.openai.com/api/docs/models/gpt-6.1-sol)
- [OpenAI — API pricing](https://developers.openai.com/api/docs/pricing)

_Content reviewed by Jerry Fan on 2026-09-30._