OpenAIGPT-6.1

GPT-6.1 Sol

GPT-6.1 Sol targets coding and other complex professional tasks. A useful distinction is that its API capability does not imply the same context setting or billing rules inside an OpenAI subscription product.

Check the endpoint before moving an existing agent

Sol’s documentation requires the Responses API for tool calls. A migration that only replaces a model ID can therefore leave an older tool loop incomplete.GPT-6.1 Sol model reference

The speed setting is also a price setting

Fast processing costs twice Standard; Ultrafast costs six times Standard. Batch and Flex are half the Standard rate. API prompts above 272,000 input tokens incur a full-request long-context adjustment; subscription usage follows separate rules.GPT-6.1 Sol model reference

Compare a finished change, not only generated code

Practical guidance. For a code maintenance task, give the model the failure, relevant source and acceptance conditions. Compare whether the change preserves existing behavior and whether its explanation identifies remaining uncertainty. Include human review time when judging the result.

Specifications & access

GPT-6.1 Sol specifications
DetailValue and conditions
AccessAPI
Model identifiersgpt-6.1-sol
Context window1,050,000 tokens

API context limit

GPT-6.1 Sol model reference
Context window500,000 tokens

Default in Codex and ChatGPT Work

GPT-6.1 Sol model reference
Maximum output128,000 tokens

Maximum API output

GPT-6.1 Sol model reference
Input price2 USD per million tokens

Standard text input; up to 272,000 input tokens

GPT-6.1 Sol model reference
Output price10 USD per million tokens

Standard text output; up to 272,000 input tokens

GPT-6.1 Sol model reference
Tool callsUse the Responses API for tool calling.GPT-6.1 Sol model reference
Default reasoning effortmediumGPT-6.1 Sol model reference
Input and outputText and images in; text outGPT-6.1 Sol model reference
Maximum input922,000 tokens within the total context window.GPT-6.1 Sol model reference

Related models

  • A lower-cost model for focused tasks at high volume.

    Launch date not confirmedAPI
  • A model for visual reasoning, screen interaction and writing with optional reasoning.

    Launch date not confirmedAPI
  • A reasoning model for complex problems and extended coding tasks.

    Launch date not confirmedAPI