GPT-4.1
A prior-generation model that stays popular for its long context and dependable, low-friction behavior. A pragmatic choice for teams that value stability and a large window over frontier capability.
At a glance
Released
Apr 14, 2025
Provider
OpenAI
Context window
1,000,000 tokens
Max output
32,000 tokens
Modalities
Text + image → text
Knowledge cutoff
June 2024
API model ID
gpt-4.1License
Proprietary (API only)
Pricing
Standard
Input$2 / 1M
Output$8 / 1M
Batch (50% off)
Input$1 / 1M
Output$4 / 1M
A typical 1,500-token prompt with a 650-token answer costs ≈ $0.008 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared withGPT-4o (May 2024)
- Much larger context window than GPT-4o
- Better instruction following and coding
- More predictable, steerable outputs
- Older knowledge cutoff than newer generations
Best use cases
Long-context tasks
Processes very large documents in a single pass.
Stable production
Runs mature apps that value predictable behavior.
General coding
Handles routine development work reliably.
Strengths & limitations
Strengths
- Very large context
- Reliable and steerable
- Good value
- Mature ecosystem
Limitations
- Older cutoff
- Behind current frontier models
How to test it
- No-code: open chatgpt.com and pick GPT-4.1 from the model switcher — no API key needed.
- Playground: sign in to the OpenAI Platform and run prompts in the workbench, then copy the generated code.
- API: create a key in the OpenAI Platform and call the API (example below).
curl https://api.openai.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4.1",
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'