o3 API pricing
OpenAI charges $2 per million input tokens and $8 per million output tokens for o3 (o3), and $0.5 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.006, or $0.003 through the batch API.
o3 price per million tokens
| Token type | Standard | Batch API |
|---|---|---|
| Input | $2 | $1 |
| Cached input | $0.5 | – |
| Output | $8 | $4 |
API model id: o3. o3 supports a 200K-token context window, up to 100K output tokens, image input, tool calling and reasoning.
What o3 costs per request
| Request | 1 request | 1,000 requests | 1M requests |
|---|---|---|---|
| Short chat message (300 in, 200 out) | $0.0022 | $2.20 | $2,200.00 |
| Typical request (1K in, 500 out) | $0.006 | $6.00 | $6,000.00 |
| Long document summary (20K in, 1K out) | $0.048 | $48.00 | $48,000.00 |
| Coding agent step (50K in, 2K out) | $0.12 | $116.00 | $116,000.00 |
At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words.
How o3 compares
- For a typical request, o3 is cheaper than 37% of the other models on apicost.app.
- Claude Sonnet 5 from Anthropic costs $2 input and $10 output per million tokens, so a typical request is $0.007: 1.2× the price of o3.
- Gemini 3.5 Flash from Google Gemini costs $1.5 input and $9 output per million tokens, so a typical request is $0.006: about the same price as o3.
- DeepSeek V4 Pro from DeepSeek costs $1.32 input and $3.96 output per million tokens, so a typical request is $0.0033: 1.8× cheaper than o3.
o3 price history
o3 has cost $2 per million input tokens and $8 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Every LLM API price increase, cut, new and retired model, dated: LLM API price changes.
Models with a similar price
| Model | Provider | Input / 1M | Cached input / 1M | Output / 1M | Typical request |
|---|---|---|---|---|---|
| Gemini 4 Hydrogen | Google Gemini | $1.5 | $0.075 | $7.5 | $0.00525 |
| GPT-4.1 | OpenAI | $2 | $0.5 | $8 | $0.006 |
| Gemini 3.5 Flash | Google Gemini | $1.5 | $0.15 | $9 | $0.006 |
| Gemini Omni 1.1 Flash | Google Gemini | $1.5 | – | $9 | $0.006 |
| Gemini Omni 1.2 Flash | Google Gemini | $1.5 | – | $9 | $0.006 |
| GPT-5 | OpenAI | $1.25 | $0.125 | $10 | $0.00625 |
| GPT-5.1 | OpenAI | $1.25 | $0.125 | $10 | $0.00625 |
| Gemini 2.5 Pro | Google Gemini | $1.25 | $0.125 | $10 | $0.00625 |
Other OpenAI models
- GPT-4.1 $2 / $8
- GPT-4.1 mini $0.4 / $1.6
- GPT-4o $2.5 / $10
- GPT-4o mini $0.15 / $0.6
- GPT-5 $1.25 / $10
- GPT-5 mini $0.25 / $2
- GPT-5 nano $0.05 / $0.4
- GPT-5.1 $1.25 / $10
- GPT-5.2 $1.75 / $14
- GPT-5.4 $2.5 / $15
- GPT-5.4 mini $0.75 / $4.5
- GPT-5.4 nano $0.2 / $1.25
- GPT-5.5 $5 / $30
- GPT-5.6 $4 / $20
- GPT-5.6 Luna $0.2 / $1.2
- GPT-5.6 Terra $2 / $12
- GPT-6 Astra $10 / $50
- GPT-6 Astra Law $10 / $50
- GPT-6 Luna $0.1 / $0.5
- GPT-6 Sol $2 / $10
- GPT-6.1 Sol $2 / $10
- GPT-6.1 Terra $1 / $5
Every OpenAI model side by side, with batch, caching and long-context prices: OpenAI API pricing. Ways to pay less: batch API, prompt caching, the cheapest models.
Questions and answers
How much does the o3 API cost?
OpenAI charges $2 per million input tokens and $8 per million output tokens for o3 (o3), and $0.5 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.006, or $0.003 through the batch API.
Has the o3 API price changed?
No. o3 has cost $2 per million input tokens and $8 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Is there a cheaper way to use o3?
Yes. The OpenAI batch API runs requests within 24 hours for $1 per million input tokens and $4 per million output tokens. Prompt caching lowers the price of repeated input to $0.5 per million tokens.
What is the context window of o3?
o3 accepts up to 200,000 input tokens, roughly 150,000 words of English, and writes up to 100,000 output tokens per response. Filling the whole context window once costs $0.40 in input tokens.
Is o3 cheaper than Claude Sonnet 5?
Yes. Claude Sonnet 5 from Anthropic costs $2 input and $10 output per million tokens, so a typical request is $0.007: 1.2× the price of o3.
Source: OpenAI pricing, via the LiteLLM price list.