Identity
- Status
- active
- Developer ID
gpt-5-mini- Released
- Aug 7, 2025
- Version
- GPT-5 Mini
- License
- Unknown
GPT-5 Mini balances reasoning quality, latency, and cost for high-volume workloads.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
OpenaiAvailable | $0.25 | $2.00 | $0.025 | — | Sep 3, 2026 | Provider-reported |
OpenrouterAvailable | $0.125 | $1.00 | $0.0125 | — | Sep 3, 2026 | Provider-reported |
OpenrouterAvailable | $0.25 | $2.00 | $0.025 | — | Oct 20, 2026 | Provider-reported |
| ARC-AGI-1verified-v1-302d8267c052 | 54.33 | — | — | GPT-5 Mini (High)unknown | Original sourcewinner eligible | Third-party benchmark |
| ARC-AGI-2verified-v2-bca68e12cc9a | 4.44 | — | — | GPT-5 Mini (High)unknown | Original sourcewinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 55.46 | — | — | GPT-5-mini-2025-08-07 (FC)unknown | Recomputedwinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 27.83 | — | — | GPT-5-mini-2025-08-07 (Prompt)unknown | Recomputedwinner eligible | Third-party benchmark |
| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e | 1,373.28 | — | 26,804 | gpt-5-mini-high; 95% CI [1368.72762571, 1377.83899204]; votes 26804; rank 180unknown | Original sourcewinner eligible | Third-party benchmark |
| LMArena Vision Arenavision-2026-10-09-a64ca3b12b6e | 1,202.14 | — | 28,959 | gpt-5-mini-high; 95% CI [1194.33907236, 1209.93452091]; votes 28959; rank 91unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
gpt-5-miniThis page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
GPT-5 MiniOpenAI | vs | Grok 4.6xAI | cross-developer peersimage, text |
GPT-5 MiniOpenAI | vs | Claude Sonnet 5Anthropic | cross-developer peersimage, text |
GPT-5 MiniOpenAI | vs | Claude Sonnet 4.6Anthropic | cross-developer peersimage, text |
GPT-5 MiniOpenAI | vs | Command A VisionCohere | cross-developer peersimage, text |
GPT-5 MiniOpenAI | vs | Gemini Computer UseGoogle DeepMind | cross-developer peerstext |
GPT-5 MiniOpenAI | vs | Pixtral LargeMistral AI | cross-developer peersimage, text |
GPT-5 MiniOpenAI | vs | GPT-5OpenAI | family variantsimage, text |
GPT-5 MiniOpenAI | vs | GPT-5 ProOpenAI | family variantsimage, text |
GPT-5 MiniOpenAI | vs | GPT-5.2 ProOpenAI | family variantsimage, text |
GPT-5 MiniOpenAI | vs | GPT-5.4 MiniOpenAI | family variantsimage, text |
GPT-5 MiniOpenAI | vs | Qwen3 VL PlusQwen | cross-developer peersimage, text |
GPT-5 MiniOpenAI | vs | Grok 4.5xAI | cross-developer peersimage, text |
Questions
GPT-5 Mini balances reasoning quality, latency, and cost for high-volume workloads. It is developed by OpenAI and its current sourced lifecycle status is active.
GPT-5 Mini's current record lists Text and Image as input and Text as output.
The current record lists a 400K-token context window and a maximum output of 128K tokens.
GPT-5 Mini is marked as API-available. The directly sourced provider records currently include Openai and Openrouter.
The lowest directly sourced prices currently attached to GPT-5 Mini are $0.125 per million input tokens through Openrouter and $1.00 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
GPT-5 Mini's recorded capabilities are chat, generation, reasoning, structured outputs, and tools. Its supported tasks are image, reasoning, and text.
GPT-5 Mini is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
No predecessor is recorded. No successor is recorded. Recorded aliases are gpt-5-mini and gpt-5-mini-2025-08-07.
The current compatible peer set includes Grok 4.6, Claude Sonnet 5, Claude Sonnet 4.6, Command A Vision, and Gemini Computer Use. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
GPT-5 Mini was last verified Sep 3, 2026 from OpenAI's primary source, “GPT-5 Mini Model | OpenAI API.” The evidence is classified as official fact.