← All Models

GPT-6 Sol

OpenAI Text

OpenAI's model for complex coding and agentic workflows. Text and image input, 1,050,000-token context, 922,000-token maximum input, and 128,000-token maximum output including reasoning. Medium default effort; none, low, high, xhigh, and max are also supported. Above 272K total input, all input/cache rates double and output rates increase 1.5x.

Web Search Code Interpreter File Search

Specifications

ProviderOpenAI
CategoryText
Context window1.1M tokens

Pricing (Starter tier)

260.00 credits / 1M input tokens
26.00 credits / 1M cached input tokens
325.00 credits / 1M cache-write tokens
1,300.00 credits / 1M output tokens
Above 272K input: 2x input/cache rates and 1.5x output rates

Higher tiers get volume discounts. See tiers

Quick Start

curl -N https://query.genx.sh/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"gpt-6-sol","messages":[{"role":"user","content":"Review this function for bugs: function median(a) { a.sort(); return a[a.length / 2]; }"}],"max_tokens":8192,"reasoning_effort":"medium","stream":true}'

Parameters

NameTypeRequiredDefaultDescription
prompt string required The input text prompt
system_prompt string optional System instructions
image_url string optional Image URL to analyze
max_tokens number optional 16 to 128000 output tokens, including reasoning. max_completion_tokens and max_output_tokens are also accepted.
reasoning_effort string optional medium none, low, medium, high, xhigh, or max. minimal is not supported.
temperature number optional Only applied with reasoning_effort none
top_p number optional Only applied with reasoning_effort none
tools array optional Built-in web_search, code_interpreter, file_search. Queue sessions do not support custom function tools.

Availability

GPT-6 Sol is available in the GenX Pro App and via the GenX Router API.

Try GPT-6 Sol on GenX Router

Pay only for what you use. No credit card required.