# GPT-6 Sol

> GPT-6 Sol is the middle tier of OpenAI's GPT-6 family, released in September 2026 alongside GPT-6 Luna. It brings much of GPT-6 Astra's capability to a faster, cheaper model, and OpenAI positions it for complex coding and professional work at scale: multi-file changes, agent loops that call tools many times, and analysis over long documents.

Canonical: https://routemux.com/openai/gpt-6-sol
Provider: OpenAI

## Key facts

| Field | Value |
| --- | --- |
| Model ID | openai/gpt-6-sol |
| Official model ID | gpt-6-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, Normalize Openai Envelope, Strip Responses Summary Input |
| Upstream release | 2026-09-22 |
| 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: $0.02 per 1M tokens
- Cache write: $0.25 per 1M tokens
- Saving vs official: 90%
- Official price source: openai_x0.10, verified 2026-09-23

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 Sol

GPT-6 Sol is the middle tier of OpenAI's GPT-6 family, released in September 2026 alongside GPT-6 Luna. It brings much of GPT-6 Astra's capability to a faster, cheaper model, and OpenAI positions it for complex coding and professional work at scale: multi-file changes, agent loops that call tools many times, and analysis over long documents.

It accepts text and image input, supports tool calling and explicit prompt caching, and exposes reasoning effort as a request parameter from none all the way to max. That range lets one deployment answer quick turns without reasoning and still think hard on the steps that need it.

Through RouteMux it is $0.20 per 1M input tokens against OpenAI's $2, and $1.00 against $10 on output. 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

- **Built for complex work** — Aimed at coding, agent workflows and professional knowledge work where Luna is not enough but Astra is more than the task needs.
- **Reasoning from none to max** — Effort is a request parameter spanning none, low, medium, high, xhigh and max.
- **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 Luna (`openai/gpt-6-luna`)

## Sources

- [OpenAI — Models](https://platform.openai.com/docs/models)
- [OpenAI — API pricing](https://developers.openai.com/api/docs/pricing)

_Content reviewed by Jerry Fan on 2026-09-23._