o3 vs Gemini 3.5 Flash
74.6 overall · $3.38 / 1M
// openai
o3
openai/o3
reasoningtool callingimage inputfile inputprompt caching
o3 costs $2.00 per 1M input tokens and $8.00 per 1M output tokens with a 200K-token context window.
A reasoning, tool-calling model from openai, released Apr 16, 2025. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $2.00
- Output / 1M
- $8.00
- Context
- 200K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $2.00 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $8.00 |
| Blended price 3:1 input:output — #60 most expensive of 343 listed models | $3.50 |
| Cached input read Blank means not priced separately — not free | $0.500 |
| Cache write | — |
| Context window | 200,000 tokens |
| Max output | 100,000 tokens |
| Input modalities | image, text, file |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | 2024-06-30 |
| Listed | Apr 16, 2025 |
Also listed as openai/o3:batch ($1.75 blended)— the same model at a different price or rate limit.
What o3 costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,012/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,480/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,400/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,525/mo |
| Bulk classification 500 in / 20 out × 5M requests | $5,050/mo |
Compare o3 with
Benchmarked models at a similar price.
o3 FAQ
How much does o3 cost?
o3 lists at $2.00 per 1M input tokens and $8.00 per 1M output tokens, with cached input reads at $0.500 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $1,480 at list price.
What is the context window of o3?
o3 accepts up to 200,000 tokens of context and can return up to 100,000 output tokens per response.
Does o3 support tool calling?
Yes — o3 supports tool (function) calling and exposes extended reasoning. It accepts image, text, file input.
How does o3 score on benchmarks?
LiveBench has not published a run for o3 yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for o3?
On OpenRouter the model ID is "openai/o3". It was listed on Apr 16, 2025.
More from openai
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.