# GPT-6 Sol

> OpenAI's reasoning model built for complex coding and agentic workflows, with image input and tools.

## Key facts

- Model author: OpenAI
- Input: $2.00 per 1M tokens (starting tier)
- Output: $10.00 per 1M tokens (starting tier)
- Cached input: $0.20 per 1M tokens
- Context window: 1,050,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: reasoning, structured_output, tools, vision
- Released: 2026-09-22
- Knowledge cutoff: Apr 20, 2026
- Model IDs: `jd/gpt-6-sol`, `openai/gpt-6-sol`
- Model page: https://www.realrelay.ai/model/openai/gpt-6-sol

## Overview

GPT-6 Sol is a reasoning model from OpenAI built for complex coding and agentic workflows. It reads text and image input, calls tools, returns structured output, and works within a 1.05M-token context window, so a long task can keep its code, documents and tool results together in one request.

It has a 1.05M-token context window and can generate up to 128,000 output tokens. It accepts text and image input and returns text. Its knowledge cutoff is April 20, 2026, and it was released on September 22, 2026.

## Capabilities

GPT-6 Sol supports reasoning, tool calling, structured output and image understanding. It accepts text and image input and returns text.

OpenAI notes that its image understanding applies to visual tasks, including computer use. Together with tool calling, this lets it work through multi-step jobs that mix reading, deciding and acting.

## Pricing

GPT-6 Sol is priced from $2.00 per 1M input tokens and from $10.00 per 1M output tokens. Cached input reads are priced from $0.20 per 1M tokens.

GPT-6 Sol is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-6 Sol for coding agents that read a repository, plan a change, call tools to edit and test code, and report back. The 1.05M-token context window keeps the code and the history of tool calls in one request.

It also suits agentic workflows that combine documents and screenshots, where image input is read alongside text and structured output feeds the next step.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-6-sol", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-6 Sol?

GPT-6 Sol is an OpenAI reasoning model built for complex coding and agentic workflows, with a 1.05M-token context window and image input.

### How much does GPT-6 Sol cost?

GPT-6 Sol is priced from $2.00 per 1M input tokens and from $10.00 per 1M output tokens. Cached input reads are priced from $0.20 per 1M tokens.

### What is the context window and maximum output of GPT-6 Sol?

GPT-6 Sol has a 1.05M-token context window and can generate up to 128,000 output tokens.

### What inputs and outputs does GPT-6 Sol support?

GPT-6 Sol accepts text and image input and returns text.

### What capabilities does GPT-6 Sol support?

GPT-6 Sol supports reasoning, tool calling, structured output and image understanding.

### When was GPT-6 Sol released?

GPT-6 Sol was released on September 22, 2026.

### How do I call GPT-6 Sol via the API?

Call GPT-6 Sol through RealRelay's OpenAI-compatible API using the model ID openai/gpt-6-sol.