o3-pro
OpenAI · Responses model
o3-pro is listed here as a responses model from OpenAI. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Provider and model identifiers are kept in their original form for accuracy.
openai-o3-pro
Catalog generated: Aug 10, 2026
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $20.0000 / 1M tokens |
| Output | $80.0000 / 1M tokens |
| Cached input | $2.0000 / 1M tokens |
| Cache write | $20.0000 / 1M tokens |
| Embedding | $20.0000 / 1M tokens |
| Batch input | $10.0000 / 1M tokens |
| Batch output | $40.0000 / 1M tokens |
Limits
Capabilities
| Capability | Supported |
|---|---|
| Vision | Supported |
| Function calling | Supported |
| Parallel function calling | - |
| Tool choice | Supported |
| Prompt caching | Supported |
| Reasoning | Supported |
| Response schema | Supported |
| System messages | - |
| Audio input | - |
| Audio output | - |
| Web search | Supported |
| PDF input | Supported |
| Video input | - |
| Native streaming | - |
| Computer use | - |
| Assistant prefill | - |
| Structured output | - |
| Output config | - |
| URL context | - |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| GPQA Diamond | 84.5% | accuracy | Base model: o3 Pro (openai/o3-pro) | 2026-05-31 | Link |
Similar models
Candidates below have the same known input/output modality shape and usable token pricing. Use the filters to change the ranking lens before opening a comparison.
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| o3-pro OpenAI | In $20.0000 / 1M tokens Out $80.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| o3-pro-2025-06-10 OpenAI | In $20.0000 / 1M tokens Out $80.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Same provider Overall 76% |
| gpt-5-pro OpenAI | In $15.0000 / 1M tokens Out $120.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 62% |
| gpt-5-pro-2025-10-06 OpenAI | In $15.0000 / 1M tokens Out $120.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 62% |
| gpt-5.2-pro Azure | In $21.0000 / 1M tokens Out $168.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Exact I/O shape Overall 62% |
| gpt-5.2-pro-2025-12-11 Azure | In $21.0000 / 1M tokens Out $168.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Exact I/O shape Overall 62% |
| gpt-5.2-pro OpenAI | In $21.0000 / 1M tokens Out $168.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 62% |
| gpt-5.2-pro-2025-12-11 OpenAI | In $21.0000 / 1M tokens Out $168.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 62% |
| gpt-5-pro Azure | In $15.0000 / 1M tokens Out $120.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Exact I/O shape Overall 59% |
| o3-deep-research OpenAI | In $10.0000 / 1M tokens Out $40.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Same provider Overall 59% |
| gpt-5.2-codex OpenAI | In $1.7500 / 1M tokens Out $14.0000 / 1M tokens | pdf Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Same provider Overall 53% |
No models match this filter.
Related articles
Articles relevant to this model's provider, capabilities, and use cases.
LLM API Provider Pricing Comparison
Compare OpenAI, Anthropic, Google, Mistral, and DeepSeek across cheapest chat, mid-range, and reasoning model pricing.
OpenAI Provider Guide
When to use GPT-4o, GPT-4.1, GPT-5, o3, and o4-mini across chat, reasoning, and coding workloads.
Cache and Batch Pricing Guide
How cached input and batch pricing change cost estimates across providers.
Reasoning LLM API Pricing Guide
Which reasoning models are cheapest, which are most expensive, and when to use reasoning vs non-reasoning models.
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
| Catalog generated | 2026-08-10T21:27:29.020Z |