Skip to content
OpenAI

GPT 5.6 Sol

GPT 5.6 Sol is the flagship of the GPT-5.6 family and the most capable of the three GPT-5.6 models on AI Gateway, with stronger agentic work across coding, biology, and cybersecurity than the previous generation, better token efficiency, and a context window of 1.1M tokens. Your use is subject to OpenAI's Terms & Privacy Policies.

ReasoningTool UseImplicit CachingFile InputVision (Image)Web SearchWebsockets
Use with AI GatewayView docs
import { streamText } from 'ai'


const result = streamText({
  model: 'openai/gpt-5.6-sol',
  prompt: 'Why is the sky blue?'
})
Read docs
OverviewAPIAboutProvidersThroughputLatencyUptimeStatusSimilarFAQ

About GPT 5.6 Sol

GPT 5.6 Sol became available on AI Gateway on July 9, 2026, alongside GPT-5.6 Terra and GPT-5.6 Luna. All three GPT-5.6 models handle agentic work across coding, biology, and cybersecurity better than the previous generation, and all three use fewer tokens to reach an answer. GPT 5.6 Sol is the most capable of the set.

OpenAI positions GPT 5.6 Sol as the frontier model of the family for complex professional work. It corresponds to the unsuffixed tier of earlier GPT-5 families, so teams running a standard GPT-5.5 model today are looking at the direct successor. OpenAI routes the gpt-5.6 alias to GPT 5.6 Sol.

GPT 5.6 Sol accepts text and image input and returns text. The context window is 1.1M tokens, with up to 272K tokens of output per request. Reasoning tokens, streaming, function calling, and structured outputs are supported, along with web search, file search, code interpreter, computer use, and MCP (Model Context Protocol) tools through the Responses API. A fast mode is available when you want quicker responses from the same model, and it got faster after launch. See the live metrics on this page for current throughput.

Set the model to openai/gpt-5.6-sol in the AI SDK, the Chat Completions API, the Responses API, or another supported API format, from TypeScript or Python. AI Gateway routing rules can also rewrite an existing model slug to openai/gpt-5.6-sol, which moves production traffic onto GPT 5.6 Sol without a code change. List pricing is $5 per million input tokens and $30 per million output tokens, with cached input at $0.5. AI Gateway mirrors provider pricing with no markup and adds no platform fee on inference, including for Bring Your Own Key requests.