Text model
gpt-5-mini pricing
OpenAI charges $0.25 per million input tokens and $2.00 per million output tokens for gpt-5-mini, and $0.025 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.25/ 1M
- Output
- $2.00/ 1M
- Cached input
- $0.025/ 1M
- Context
- 272Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.25 | $2.00 | $0.025 | — |
| Batch | $0.125 | $1.00 | $0.0125 | — |
| Priority | $0.45 | $3.60 | $0.045 | — |
| Flex | $0.125 | $1.00 | $0.0125 | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00118 | 100,000 | $117.50 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.0016 | 100,000 | $160.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0028 | 250,000 | $700.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | $0.000675 | 1,000,000 | $675.00 |
Planning a mix of models? Simulate a workload with gpt-5-mini, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| openai/gpt-5.6-luna | $0.00078 | 34% |
| openai/gpt-4o-mini-search-preview | $0.000465 | 60% |
| together/Qwen/Qwen3.7-Plus | $0.000992 | 16% |
| deepinfra/google/gemini-3.1-flash-lite | $0.000975 | 17% |
Price history
No price changes since Veqen started tracking this model.
Also billed under: gpt-5-mini-2025-08-07.
Compare
- gpt-5 vs gpt-5-mini
- gpt-5-mini vs gpt-5.2
- gpt-5-mini vs gpt-4o
- gpt-5-mini vs gpt-4o-mini
- gpt-5-mini vs gpt-4.1
- gpt-5-mini vs claude-opus-5-5
Last verified with price book 2026-10-22. Sources: OpenAI pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.