GPT-4.1: Pricing, Context, and Benchmarks
GPT-4.1 is OpenAI's GPT-4 model released on 2025-04-14. It runs on a 1.0M-token context window, priced at $2.00/M input and $8.00/M output. 1M-token context window. Best OpenAI choice for long-context coding and document tasks.
Specifications
| Provider | OpenAI |
|---|---|
| Family | GPT-4 |
| Released | 2025-04-14 |
| Status | active |
| Context window | 1.0M tokens |
| Max output | 33K tokens |
| Modalities | text image |
| Capabilities | function calling json mode vision streaming |
| Tokenizer | o200k_base |
| API endpoint | https://api.openai.com/v1/chat/completions |
| Documentation | Official docs ↗ |
| Last updated | 2026-05-29 |
What this model is good for
Based on benchmark scores and capability fit, GPT-4.1 ranks well for:
- Long Context Summarization — rank #3. 1M context with stronger reasoning than Gemini on synthesis-heavy tasks.
- Code Generation — rank #6. 1M context advantage when the whole codebase needs to fit in the prompt.
Cost calculator
For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0100 per call. For typical usage:
| Workload | Tokens / call (in/out) | $/call | $/1K calls | $/1M calls |
|---|---|---|---|---|
| Short Q&A | 200 / 100 | $0.001200 | $1.20 | $1,200 |
| Standard chat | 1K / 500 | $0.006000 | $6.00 | $6,000 |
| RAG with retrieval | 4K / 500 | $0.012000 | $12.00 | $12,000 |
| Long doc summary | 20K / 1K | $0.048000 | $48.00 | $48,000 |
| Long context (100K input) | 100K / 2K | $0.212000 | $212.00 | $212,000 |
For more precise estimates including caching discounts, use the LLM API Cost Calculator.
Other OpenAI models
Common comparisons
- GPT-4.1 vs Mistral Large 2 Side-by-side specs, pricing, and benchmarks
- GPT-4.1 vs Qwen3-Coder-480B Side-by-side specs, pricing, and benchmarks
- GPT-4.1 vs Command R+ Side-by-side specs, pricing, and benchmarks
- GPT-4.1 vs Gemini 2.5 Pro Side-by-side specs, pricing, and benchmarks
API setup
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": "Hello"}]}'See the official documentation for the full request/response schema. For pre-flight token counting before paying, use the appropriate token counter.