o4-mini — pricing & specs
o4-mini is a fast model from OpenAI, at capability tier 3 of 8. Live $/M-token pricing and specs from the Mintok catalog.
$/M-token pricing
What o4-mini costs in practice
| Scenario | Est. cost |
|---|---|
| 1M input + 1M output tokens | $5.50 |
| A 10K-token request (8K in / 2K out) | $0.018 |
| 1,000 agent runs (~2K in / 500 out each) | $4.40 |
| 1M-token RAG chat session (900K cached in / 100K out) | $0.688 |
Estimated from list price at the token mixes shown; your real cost depends on prompt/response length and cache hit-rate. Model your own volume →
Specifications
- Vendor
- OpenAI
- Family
- o4-mini
- Capability tier
- 3 / 8
- Size class
- FAST
- Category
- GENERAL
- Parameters
- 70B total · 20B active (MoE)
- Context window
- 200,000 tokens
- Licensing
- Proprietary
Carbon footprint (modeled)
Modeled decode on a reference NVIDIA Rubin Ultra VR300 at 50% MBU, batch 32, global-avg grid. Compare all models & grids →
Alternatives at tier 3
Same capability tier, sorted by output price — the cheaper-capable options.
- Gemma 3 27BGoogle$0.33/M out
FAQ
How much does o4-mini cost per token?
o4-mini costs $1.10 per million input tokens and $4.40 per million output tokens (cached input $0.28/M).
What does a typical request with o4-mini cost?
At list price, a 10K-token request (8K in / 2K out) with o4-mini costs about $0.018, and 1,000 agent runs (~2K in / 500 out each) about $4.40.
What is o4-mini's context window?
o4-mini supports a 200,000-token context window.
What capability tier is o4-mini?
o4-mini sits at capability tier 3 of 8 on the Mintok scale (FAST size class).
Is o4-mini open-source or proprietary?
o4-mini is a proprietary model from OpenAI, accessed via API.
Put o4-mini to work
Benchmark it on your prompts, or size a deployment and compare $/M-token against alternatives.
Pricing and specs are maintained by Mintok's catalog watchers from public sources. Not investment advice. Methodology.