Text model
gpt-4o pricing
OpenAI charges $2.50 per million input tokens and $10.00 per million output tokens for gpt-4o, and $1.25 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $2.50/ 1M
- Output
- $10.00/ 1M
- Cached input
- $1.25/ 1M
- Context
- 128Ktokens
Retires 2027-01-14. Move to Pin a current model. This alias's dated snapshots retire 2027-01-14; OpenAI doesn't say what the alias will point to.. npx @veqen/sdk scan finds every place your code uses it.
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $2.50 | $10.00 | $1.25 | — |
| Batch | $1.25 | $5.00 | — | — |
| Priority | $4.25 | $17.00 | $2.125 | — |
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 | $0.00775 | 100,000 | $775.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.01 | 100,000 | $1,500.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.03 | 250,000 | $7,000.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | $0.00525 | 1,000,000 | $5,250.00 |
Planning a mix of models? Simulate a workload with gpt-4o, 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/o3 | $0.0062 | 20% |
| openai/gpt-5 | $0.00588 | 24% |
| databricks/databricks-gemini-3-6-flash | $0.00656 | 15% |
| novita/qwen/qwen3-max | $0.00654 | 16% |
Price history
No price changes since Veqen started tracking this model.
Also billed under: gpt-4o-2024-05-13, gpt-4o-2024-08-06, gpt-4o-2024-11-20.
Compare
- gpt-5 vs gpt-4o
- gpt-5-mini vs gpt-4o
- gpt-5.2 vs gpt-4o
- gpt-4o vs gpt-4o-mini
- gpt-4o vs gpt-4.1
- gpt-4o 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.