Identity
- Status
- active
- Developer ID
gpt-4.1-mini- Released
- Not reported
- Version
- GPT-4.1 Mini
- License
- Unknown
GPT-4.1 Mini is the smaller, faster GPT-4.1 model for instruction following and tool calling.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
OpenaiAvailable | $0.40 | $1.60 | $0.10 | — | Sep 3, 2026 | Provider-reported |
OpenrouterAvailable | $0.40 | $1.60 | $0.10 | — | Oct 20, 2026 | Provider-reported |
OpenrouterAvailable | $0.20 | $0.80 | $0.050 | — | Sep 3, 2026 | Provider-reported |
| Aider Polyglotpolyglot-225-5dc9490bb35f | 32.44 | — | 225 | diff; aider 0.81.4.devunknown | Recomputedwinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 50.45 | — | — | GPT-4.1-mini-2025-04-14 (FC)unknown | Recomputedwinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 29.73 | — | — | GPT-4.1-mini-2025-04-14 (Prompt)unknown | Recomputedwinner eligible | Third-party benchmark |
| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e | 1,340.50 | — | 38,709 | gpt-4.1-mini-2025-04-14; 95% CI [1336.20142291, 1344.80800339]; votes 38709; rank 211unknown | Original sourcewinner eligible | Third-party benchmark |
| LMArena Vision Arenavision-2026-10-09-a64ca3b12b6e | 1,181.35 | — | 40,221 | gpt-4.1-mini-2025-04-14; 95% CI [1173.87762706, 1188.81616531]; votes 40221; rank 101unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
gpt-4.1-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-4.1 MiniOpenAI | vs | MiniMax M3MiniMax | cross-developer peersimage, text |
GPT-4.1 MiniOpenAI | vs | Nova 2 LiteAmazon | cross-developer peersimage, text |
GPT-4.1 MiniOpenAI | vs | MolmoWeb 8BAi2 | cross-developer peersimage, text |
GPT-4.1 MiniOpenAI | vs | Claude Fable 5Anthropic | cross-developer peersimage, text |
GPT-4.1 MiniOpenAI | vs | Claude Opus 4.8Anthropic | cross-developer peersimage, text |
GPT-4.1 MiniOpenAI | vs | Gemini 3.5 FlashGoogle DeepMind | cross-developer peerstext |
GPT-4.1 MiniOpenAI | vs | cross-developer peersimage, text | |
GPT-4.1 MiniOpenAI | vs | GPT-4o MiniOpenAI | family variantsimage, text |
GPT-4.1 MiniOpenAI | vs | GPT-5.4OpenAI | family variantsimage, text |
GPT-4.1 MiniOpenAI | vs | GPT-5.5 ProOpenAI | family variantsimage, text |
Questions
GPT-4.1 Mini is the smaller, faster GPT-4.1 model for instruction following and tool calling. It is developed by OpenAI and its current sourced lifecycle status is active.
GPT-4.1 Mini's current record lists Text and Image as input and Text as output.
The current record lists a 1,048K-token context window and a maximum output of 33K tokens.
GPT-4.1 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-4.1 Mini are $0.20 per million input tokens through Openrouter and $0.80 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
GPT-4.1 Mini's recorded capabilities are chat, generation, and tools. Its supported tasks are image and text.
GPT-4.1 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-4.1-mini and gpt-4.1-mini-2025-04-14.
The current compatible peer set includes MiniMax M3, Nova 2 Lite, MolmoWeb 8B, Claude Fable 5, and Claude Opus 4.8. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
GPT-4.1 Mini was last verified Aug 29, 2026 from OpenAI's primary source, “GPT-4.1 Mini Model | OpenAI API.” The evidence is classified as official fact.