o1

OpenAI · OpenAI o-series · reasoning · released Dec 17, 2024 · deprecated Jun 1, 2026 · o1

OpenAI o-series family:o1·o3·o4-mini

OpenAI's original flagship reasoning model — now superseded by o3, but still available and capable.

Pricing

Input$15 / 1M checked Jul 19, 2026
Cached input$7.50 / 1M
Output$60 / 1M checked Jul 19, 2026

Superseded by o3 at lower cost.

Cost bandPremium
Free tierNo free API tier.

Limits

Context window200k checked Jul 19, 2026
Max output100k
Knowledge cutoffOct 1, 2023
DeploymentOpenAI API
OpenAI-compatible APIYes
ModalitiesText, Image input

Where it fits

Best forLegacy integrations and teams not yet migrated to o3/o4-mini.
Business fitMigrate to o3 or o4-mini for new projects.

Capabilities

Extended thinkingFunction callingVision

Benchmark scores

Composite86 / 100
Coding88 / 100 (SWE-bench Verified)
Reasoning90 / 100 (GPQA Diamond)
Long context82 / 100 (RULER 200K)
Vision80 / 100 (MMMU)
Instruction following88 / 100 (IFEval)

Editorial aggregate of published benchmark results as of Jan 1, 2025. These are not independent measurements run by this site.

Change history

No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.

Data

Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/openai/o1

Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.

Open in the comparison table JSON API