GPT-6.1 Sol

Overview

GPT-6.1 Sol is a general-purpose model in the official OpenAI model catalog, with model ID gpt-6.1-sol. It should be evaluated for text understanding, generation, coding assistance, structured processing and multimodal product capabilities rather than single-purpose image generation, transcription or TTS.

Best for

Use GPT-6.1 Sol as a core candidate for assistants, complex Q&A, coding, long-form analysis, workflow automation and vision-enabled applications. Before production, compare context length, pricing, latency, tool support and real output quality.

Official specifications and pricing

GPT-6.1 Sol launched on September 29, 2026 with API model ID gpt-6.1-sol as an upgrade to GPT-6 Sol. Near-Astra performance refers to OpenAI's specific evaluations; compare quality and cost on your own tasks.

Supports text and image input with text output, a 1,050,000-token context window and up to 128,000 output tokens. The knowledge cutoff is 2026-04-30.

reasoning.effort supports low, medium (default), high, xhigh and max, but not none or minimal. Streaming, function calling and structured outputs are supported. Tool calling requires the Responses API; Chat Completions is supported without tool calling.

As verified on 2026-09-30, standard text pricing per million tokens is $2 input, $0.10 cached input, $2.50 cache writes and $10 output. Prompts exceeding 272K input tokens incur 2x input and cache rates and 1.5x output rates for the full request. Fast costs 2x Standard; Batch and Flex cost 50% of Standard. Regional processing adds a 10% premium where available, and tool calls may incur additional fees.

Audio, video and fine-tuning are not supported. Image generation is a Responses API tool capability, not direct image output from the model.