Text model
openai/o4-mini pricing
Replicate charges $1.00 per million input tokens and $4.00 per million output tokens for openai/o4-mini. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $1.00/ 1M
- Output
- $4.00/ 1M
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $1.00 | $4.00 | — | — |
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 | $0.0031 | 100,000 | $310.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.008 | 100,000 | $800.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.02 | 250,000 | $3,800.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with openai/o4-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 |
|---|---|---|
| replicate/meta/llama-2-70b | $0.00208 | 33% |
| replicate/meta/llama-2-70b-chat | $0.00208 | 33% |
| deepinfra/google/gemini-3.7-flash | $0.00263 | 15% |
| google/gemini-3.6-flash | $0.00263 | 15% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Replicate pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.