Identity
- Status
- active
- Developer ID
gpt-4.1- Released
- Not reported
- Version
- GPT-4.1
- License
- Unknown
OpenAIGPT-4.1
GPT-4.1 is OpenAI's non-reasoning model for instruction following and tool calling.
- Token context
- 1,048K tokens
- Inputs
- Text, Image
- Outputs
- Text
- Released
- Not reported
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
OpenaiAvailable | $2.00 | $8.00 | $0.50 | — | Sep 3, 2026 | Provider-reported |
 OpenrouterAvailable | $2.00 | $8.00 | $0.50 | — | Sep 4, 2026 | Provider-reported |
OpenrouterAvailable | $1.00 | $4.00 | $0.25 | — | Sep 3, 2026 | Provider-reported |
Benchmarks
All benchmark results →| Aider Polyglotpolyglot-225-5dc9490bb35f | 52.44 | — | 225 | diff; aider 0.81.4.devunknown | Recomputedwinner eligible | Third-party benchmark |
| ARC-AGI-1verified-v1-15fb467fd4fc | 5.50 | — | — | GPT-4.1unknown | Original sourcewinner eligible | Third-party benchmark |
| ARC-AGI-2verified-v2-9a3db289984e | 0.42 | — | — | GPT-4.1unknown | Original sourcewinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 53.96 | — | — | GPT-4.1-2025-04-14 (FC)unknown | Recomputedwinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 39.38 | — | — | GPT-4.1-2025-04-14 (Prompt)unknown | Recomputedwinner eligible | Third-party benchmark |
| LMArena Text Arenatext-2026-09-01-011508720696 | 1,382.71 | — | 49,913 | gpt-4.1-2025-04-14; 95% CI [1379.00467679, 1386.41941365]; votes 49913; rank 153unknown | Original sourcewinner eligible | Third-party benchmark |
| LMArena Vision Arenavision-2026-08-27-011508720696 | 1,210.32 | — | 41,034 | gpt-4.1-2025-04-14; 95% CI [1203.63813827, 1217.00696914]; votes 41034; rank 70unknown | Original sourcewinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Token context
- 1,048K tokens
- Maximum output
- 33K tokens
- Total parameters
- Unknown
- Active parameters
- Unknown
- Knowledge cutoff
- Jun 1, 2024
Interface and Access
- Inputs
- Text, Image
- Outputs
- Text
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- Reasoning
- No
- Vision
- Yes
- Tool calling
- Yes
- Capabilities
- chat, generation, tools
This 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.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesgpt-4.1, gpt-4.1-2025-04-14
Explicit Unknowns
- Release date
- Architecture
- Tokenizer
Primary Evidence
Sources and Observation Date
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
GPT-4.1OpenAI | vs | GPT-6 AstraOpenAI | family variantsimage, text |
GPT-4.1OpenAI | vs | Claude Fable 5.1Anthropic | cross-developer peersimage, text |
GPT-4.1OpenAI | vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peerstext |
GPT-4.1OpenAI | vs |  DeepSeek V4 ProDeepSeek | cross-developer peerstext |
GPT-4.1OpenAI | vs | Grok 4.6xAI | cross-developer peersimage, text |
GPT-4.1OpenAI | vs |  Qwen3.8 MaxQwen | cross-developer peersimage, text |
GPT-4.1OpenAI | vs |  Kimi K3Moonshot AI | cross-developer peersimage, text |
GPT-4.1OpenAI | vs |  MiniMax M3MiniMax | cross-developer peersimage, text |
GPT-4.1OpenAI | vs |  GLM 5.3Z.ai | cross-developer peerstext |
GPT-4.1OpenAI | vs |  Hy4 previewTencent | cross-developer peerstext |
GPT-4.1OpenAI | vs | Seed 2.1 ProByteDance Seed | cross-developer peersimage, text |
GPT-4.1OpenAI | vs |  Mistral Large 3Mistral AI | cross-developer peersimage, text |
GPT-4.1OpenAI | vs | cross-developer peersimage, text | |
GPT-4.1OpenAI | vs |  Nova 2 LiteAmazon | cross-developer peersimage, text |
GPT-4.1OpenAI | vs | cross-developer peersimage, text | |
GPT-4.1OpenAI | vs |  ERNIE 5.1Baidu | cross-developer peerstext |
GPT-4.1OpenAI | vs | cross-developer peerstext | |
GPT-4.1OpenAI | vs | cross-developer peerstext | |
GPT-4.1OpenAI | vs |  Phi-4 ReasoningMicrosoft | cross-developer peerstext |
GPT-4.1OpenAI | vs | cross-developer peerstext | |
GPT-4.1OpenAI | vs |  Sonar ProPerplexity | cross-developer peerstext |
GPT-4.1OpenAI | vs | Claude Opus 5Anthropic | cross-developer peersimage, text |
Questions
GPT-4.1 FAQs
What is GPT-4.1?+
GPT-4.1 is OpenAI's non-reasoning model for instruction following and tool calling. It is developed by OpenAI and its current sourced lifecycle status is active.
What inputs and outputs does GPT-4.1 support?+
GPT-4.1's current record lists Text and Image as input and Text as output.
How much context does GPT-4.1 support?+
The current record lists a 1,048K-token context window and a maximum output of 33K tokens.
Is GPT-4.1 available through an API?+
GPT-4.1 is marked as API-available. The directly sourced provider records currently include Openai and Openrouter.
How much does GPT-4.1 cost through an API?+
The lowest directly sourced prices currently attached to GPT-4.1 are $1.00 per million input tokens through Openrouter and $4.00 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
What capabilities and tasks does GPT-4.1 support?+
GPT-4.1's recorded capabilities are chat, generation, and tools. Its supported tasks are image and text.
Can GPT-4.1 be self-hosted?+
GPT-4.1 is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
Does GPT-4.1 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are gpt-4.1 and gpt-4.1-2025-04-14.
Which models can GPT-4.1 be compared with?+
The current compatible peer set includes GPT-6 Astra, Claude Fable 5.1, Gemini 3.1 Pro, DeepSeek V4 Pro, and Grok 4.6. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for GPT-4.1?+
GPT-4.1 was last verified Aug 29, 2026 from OpenAI's primary source, “GPT-4.1 Model | OpenAI API.” The evidence is classified as official fact.