GPT-5 Mini: Pricing, Context, and Benchmarks
GPT-5 Mini is OpenAI's GPT-5 model released on 2025-08-07. It runs on a 400K-token context window, priced at $0.25/M input and $2.00/M output. Smaller, cheaper, faster GPT-5 variant. Good default for high-volume API workloads.
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 |
| Tokenizer | o200k_base |
| API endpoint | https://api.openai.com/v1/responses |
| Documentation | Official docs ↗ |
| Last updated | 2026-05-29 |
What this model is good for
Based on benchmark scores and capability fit, GPT-5 Mini ranks well for:
- Customer Support — rank #1. $0.25/M input is hard to beat. Reliable instruction following.
Cost calculator
For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0023 per call. For typical usage:
| Workload | Tokens / call (in/out) | $/call | $/1K calls | $/1M calls |
|---|---|---|---|---|
| Short Q&A | 200 / 100 | $0.000250 | $0.25 | $250 |
| Standard chat | 1K / 500 | $0.001250 | $1.25 | $1,250 |
| RAG with retrieval | 4K / 500 | $0.002000 | $2.00 | $2,000 |
| Long doc summary | 20K / 1K | $0.007000 | $7.00 | $7,000 |
| Long context (100K input) | 100K / 2K | $0.028000 | $28.00 | $28,000 |
For more precise estimates including caching discounts, use the LLM API Cost Calculator.
Other OpenAI models
Common comparisons
- GPT-5 Mini vs DeepSeek-V3 Side-by-side specs, pricing, and benchmarks
- GPT-5 Mini vs Gemini 2.5 Flash Side-by-side specs, pricing, and benchmarks
- GPT-5 Mini vs Codestral Side-by-side specs, pricing, and benchmarks
- GPT-5 Mini vs Qwen3-235B 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-mini", "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.