GPT-5 Mini API pricing
As of October 22, 2026, OpenAI GPT-5 Mini costs $0.25 per million input tokens and $2.00 per million output tokens on OpenAI's own API, with cached input at $0.025 per million.
GPT-5 Mini benchmarks and specs · Every OpenAI model's price
- Input, per million tokens$0.25
- Output, per million tokens$2.00
- Cached input, per million$0.025
- Context window400K tokens
- Max output128K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0013 | $1.25 | Yes |
| Repository review | 50K input + 3K output tokens | $0.018 | $18.50 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.070 | $70.00 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.08 | $80.00 |
Price history
We have read OpenAI's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $0.25 input, $2.00 output
Cheaper models as good as GPT-5 Mini
Models within two points of GPT-5 Mini or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- Qwen3.5-Flash$0.26 Overall 50.1 against 43.7 · 87% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 43.7 · 86% cheaper output
- MiMo-V2.5$0.336 Overall 50.7 against 43.7 · 83% cheaper output
- DeepSeek V4 Flash 0731$0.396 Overall 55.2 against 43.7 · 80% cheaper output
- Gemma 4 31B$0.40 Overall 42.1 against 43.7 · 80% cheaper output
GPT-5 Mini pricing questions
- How much does GPT-5 Mini cost per million tokens?
- $0.25 per million input tokens and $2.00 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does GPT-5 Mini support prompt caching?
- Yes. OpenRouter lists cached input at $0.025 per million tokens, against $0.25 for uncached input.
- Is there a cheaper model as good as GPT-5 Mini?
- Qwen3.5-Flash scores 50.1 on the LLMBenchmark Index, within two points of GPT-5 Mini or above it, and costs $0.26 per million output tokens.
- Has the price of GPT-5 Mini changed?
- Not since we started recording it daily on October 21, 2026.