All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

gpt-6.1-terra

OpenAIActive

First listed October 26, 2026

gpt-6.1-terra is an OpenAI model, released October 2026. It has a 1,050,000-token context window and up to 128,000 output tokens. It takes image input and supports function calling, structured outputs and reasoning.

Status
Active
Released October 2026
Shutdown
none announced
Context window
1.05Mtokens
Up to 128K output tokens

No deprecation or shutdown date has been announced as of October 26, 2026.

Features

Compare models
FeatureValueSinceSource
Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup.Supportedfirst seen October 26, 2026source
Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result.Supportedfirst seen October 26, 2026source
Prompt cachingA prompt prefix you send again and again (system prompt, documents, tools) is cached, so later requests cost less and start faster.Supportedfirst seen October 26, 2026source
Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests.Supportedfirst seen October 26, 2026source
Image inputImages such as screenshots, photos and charts can go in the prompt for the model to read.Supportedfirst seen October 26, 2026source
Reasoning / thinkingThe model can work through a problem step by step before it answers: usually better answers to hard questions, at the cost of more tokens and time.Supportedfirst seen October 26, 2026source
Fine-tuningYou can train your own version of the model on your examples through the company's API, then call it like any other model.Not supportedfirst seen October 26, 2026source
Built-in web searchThe company's API can search the web for the model during a request and cite its sources; you don't need a search service of your own.Supportedfirst seen October 26, 2026source
Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word.1,050,000 tokensfirst seen October 26, 2026source
Max output tokensThe longest reply the model can write in one response, in tokens. A token is about three-quarters of an English word.128,000 tokensfirst seen October 26, 2026source

Not published by OpenAI: PDF input, temperature parameter, top_p parameter, logprobs.

Price history

USD per 1M tokens, standard tier

No price history yet.

Prices

USD per 1M tokens, every type and band, by tier

No published prices.

Changelog

Changes we detected on OpenAI's pages
  1. Feature listed

    gpt-6.1-terra: Max output tokens 128,000 tokens

    Info

  2. Feature listed

    gpt-6.1-terra: Context window 1,050,000 tokens

    Info

  3. Feature listed

    gpt-6.1-terra: Built-in web search supported

    Info

  4. Feature listed

    gpt-6.1-terra: Fine-tuning not supported

    Info

  5. Feature listed

    gpt-6.1-terra: Reasoning / thinking supported

    Info

  6. Feature listed

    gpt-6.1-terra: Image input supported

    Info

  7. Feature listed

    gpt-6.1-terra: Batch API supported

    Info

  8. Feature listed

    gpt-6.1-terra: Prompt caching supported

    Info

  9. Feature listed

    gpt-6.1-terra: Function calling supported

    Info

  10. Feature listed

    gpt-6.1-terra: Structured outputs supported

    Info

  11. Added

    OpenAI added gpt-6.1-terra

    Info

Related news

Email alerts

Get an email if gpt-6.1-terra changes

We'll email you the same morning we spot a deprecation notice, a new or moved shutdown date, a price change, or the model leaving OpenAI's model list.

No password: one email to confirm, and you can unsubscribe any time. Privacy

Last checked · Sources: OpenAI deprecations, OpenAI pricing, OpenAI models