OpenAI · Released Apr 14, 2025GPT-4.1
Long-lived GPT workhorse for coding, instruction following, and production apps.
- Capability
- 136.8ECI · #111 of 148
- Input
- $2.00per 1M tokens
- Output
- $8.00per 1M tokens
- Context
- 1.05M33K max output
What it costs
- Input
- $2.00per million tokens
- Output
- $8.00per million tokens
- Cached input
- $0.50per million tokens
- Blended (3:1)
- $3.50pricier than 80% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $8.00 |
| Team assistant25M input + 5M output tokens | $90.00 |
| Production app250M input + 50M output tokens | $900.00 |
Official OpenAI API price, as listed on models.dev.
Independent benchmarks
#111 of 148 scored models
The shaded band is Epoch AI’s confidence range (133.6–138.4); the tick marks the median scored model.
Scores from Epoch AI, run independently of OpenAI.
The details
- Lab
- OpenAI
- Released
- Apr 14, 2025
- Knowledge cutoff
- Apr 2024
- Context window
- 1,047,576 tokens
- Max output
- 32,768 tokens
- Inputs
- Text, Images, PDFs
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- Yes
- Weights
- Proprietary
- API model ID
gpt-4.1on OpenAI- Availability
- 25 API providerslisted on models.dev
What OpenAI claims
Published by the lab at launch. Settings vary, so compare these only with care.
| Benchmark | Score | Setting | Source |
|---|---|---|---|
| Aider Polyglot | 52.4 percent correct | — | Source |
More from OpenAI
About GPT-4.1
How much does GPT-4.1 cost?
GPT-4.1 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price). Cached input is $0.50 per million tokens. At a 3:1 input-to-output mix that is $3.50 per million tokens, more expensive than 80% of the 360 priced models we track.
What is the context window of GPT-4.1?
GPT-4.1 accepts up to 1,047,576 tokens per request and can write up to 32,768 tokens in one response.
How good is GPT-4.1?
Epoch AI gives GPT-4.1 a Capabilities Index score of 136.8 (likely range 133.6–138.4), ranking it #111 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 66.9%, FrontierMath Tiers 1–3 6.0%, OTIS Mock AIME 2024–2025 38.3%, SWE-bench Verified 48.5%, SimpleQA Verified 31.1%.
Is GPT-4.1 open source?
No. GPT-4.1 is proprietary; you use it through OpenAI’s API or partner platforms.
What inputs does GPT-4.1 support?
GPT-4.1 accepts text, images and PDFs and replies in text. It is not a dedicated reasoning model, supports tool calling and can return structured JSON output.
When was GPT-4.1 released?
OpenAI released GPT-4.1 on Apr 14, 2025. Its training data runs to Apr 2024.
What are the best alternatives to GPT-4.1?
The closest current models from other labs on capability, price and release date are Qwen3 32B (Alibaba (Qwen), ECI 138.5, $0.70 / $2.80), Claude Sonnet 3.7 (Anthropic, ECI 141.2, $3.00 / $15.00), DeepSeek-R1-Distill-Qwen-32B (DeepSeek, ECI 137.4) and Gemini 2.5 Pro (Google, ECI 145.3, $1.25 / $10.00).