OpenAI: OpenAI o3
o3
OpenAI o3 costs $2.60 per million input tokens and $10.40 per million output tokens, supports 200K context, and is available through the OpenAI-compatible API.
OpenAI o3 is a reasoning model for complex analytical, coding, mathematical, and scientific tasks.
Modalities
Text → Text
Input / output price
$2.60 / $10.40 per 1M
Context
200K · max output 100K
Capabilities
Pricing
Billed per token actually used and deducted from your credits.
| Item | USD per 1M tokens |
|---|---|
| Input | $2.60 |
| Output | $10.40 |
| Cached input | $1.30 |
Calculator
Drag the sliders to estimate what this model will cost.
- Per request
- $0.0161
- Per day
- $8.06
- Per month (30 days)
- $241.80
OpenAI o3: input $2.6/M · output $10.4/M · cached input $1.3/M
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "o3", "max_tokens": 800,
"messages": [{"role": "user", "content": "…"}]}'Code samples
OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to o3.
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "o3",
"stream": true,
"messages": [{"role": "user", "content": "Hello"}]
}'Use it in a client: Cursor · Cline · SillyTavern · Codex
Parameters
Common OpenAI parameters can be passed as-is.
temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseedRelated models
More from OpenAI
Similar capabilities and price
FAQ
- How is OpenAI o3 billed?
- Input is $2.60 and output is $10.40 per million tokens; cached input is $1.30. The charge for every request is listed in Usage Logs in the console.
- How long is the context window?
- 200K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
- Does it support streaming?
- Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.