GPT-5: Pricing, Context, and Benchmarks
GPT-5 is OpenAI's GPT-5 model released on 2025-08-07. It runs on a 400K-token context window, priced at $1.25/M input and $10.00/M output. OpenAI's flagship general-purpose model. Replaces GPT-4o for most users with stronger reasoning and tool use.
Specifications
| Provider | OpenAI |
|---|---|
| Family | GPT-5 |
| Released | 2025-08-07 |
| Status | active |
| Context window | 400K tokens |
| Max output | 128K tokens |
| Modalities | text image |
| Capabilities | function calling json mode vision streaming reasoning |
| Tokenizer | o200k_base |
| API endpoint | https://api.openai.com/v1/responses |
| Documentation | Official docs ↗ |
| Last updated | 2026-05-29 |
Benchmark scores
| Benchmark | Category | Score | Measured | Source |
|---|---|---|---|---|
| AIME 2025 | math | 94.6 | 2025-08-07 | ↗ |
| MMLU-Pro | general | 88.4 | 2025-08-07 | ↗ |
| GPQA Diamond | reasoning | 85.7 | 2025-08-07 | ↗ |
| SWE-bench Verified | coding | 74.9 | 2025-08-07 | ↗ |
Scores reflect single measurements on the date shown. Reproducibility varies; consult the linked source for methodology. Use the comparison tool for side-by-side analysis.
What this model is good for
Based on benchmark scores and capability fit, GPT-5 ranks well for:
- Math & STEM Reasoning — rank #1. AIME 2025: 94.6%. Reasoning tokens count toward output billing.
- Vision / Image Analysis — rank #1. Best vision model in the GPT line.
- Code Generation — rank #3. Frontier coding plus cheap input price (cached). Worth testing against Sonnet for your workload.
- Agentic Workflows — rank #3. Solid tool use. Responses API streamlines stateful agent code.
Cost calculator
For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0113 per call. For typical usage:
| Workload | Tokens / call (in/out) | $/call | $/1K calls | $/1M calls |
|---|---|---|---|---|
| Short Q&A | 200 / 100 | $0.001250 | $1.25 | $1,250 |
| Standard chat | 1K / 500 | $0.006250 | $6.25 | $6,250 |
| RAG with retrieval | 4K / 500 | $0.010000 | $10.00 | $10,000 |
| Long doc summary | 20K / 1K | $0.035000 | $35.00 | $35,000 |
| Long context (100K input) | 100K / 2K | $0.140000 | $140.00 | $140,000 |
For more precise estimates including caching discounts, use the LLM API Cost Calculator.
Other OpenAI models
Common comparisons
- GPT-5 vs Gemini 2.5 Pro Side-by-side specs, pricing, and benchmarks
- GPT-5 vs Gemini 1.5 Pro Side-by-side specs, pricing, and benchmarks
- GPT-5 vs Claude Haiku 4.5 Side-by-side specs, pricing, and benchmarks
- GPT-5 vs Llama 3.3 70B Side-by-side specs, pricing, and benchmarks
API setup
curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-5", "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.