o3-mini is our newest small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini supports key developer features, like Structured Outputs, function calling, and Batch API.
function_callingfile_searchcode_interpretermcpimage_generationhttps://api.openai.com/v1/chat/completionshttps://api.openai.com/v1/responseshttps://api.openai.com/v1/assistantshttps://api.openai.com/v1/batches| Input | Cached input | Output | |
|---|---|---|---|
| Standard | $1.1 | $0.55 | $4.4 |
| Batch | $0.55 | — | $2.2 |
| Model | Perf | Speed | Context | Max out | Input | Output |
|---|---|---|---|---|---|---|
o3-miniRVTS | 200K | 100K | $1.1 | $4.4 | ||
o3RVTS | 200K | 100K | $2 | $8 | ||
| 200K | 100K | $10 | $40 | |||
o3-proRVT | 200K | 100K | $20 | $80 |
/v1/models/openai/o3-mini