o3
OpenAI's most powerful reasoning model. State-of-the-art on MATH, coding, and science benchmarks.
200K
tokens
100K
tokens
$2
per 1M tokens
$8
per 1M tokens
68
tokens/sec
Apr 2025
2025-04-16
$5.00
per 1M tokens
18.8
quality per $
Capabilities
Benchmarks
Price vs Quality
Context Window in Context
- Codestral256K
- ▸ o3200K
- o3 Mini200K
- Claude Opus 4200K
- Claude Sonnet 4200K
- Claude 3.5 Haiku200K
- Sonar Pro200K
- GLM-5.1200K
Pricing History
尚未接入我们的网关
Swfte Connect 尚未持有 o3 的密钥，因此这里没有可运行的内容。添加你自己的提供商密钥，就能用与本目录中其他模型相同的 API 调用它。
curl https://api.swfte.com/agents/v2/gateway/chat/completions \
-H "Authorization: Bearer $SWFTE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai:o3",
"messages": [{"role": "user", "content": "Hello"}]
}'About o3
o3 is a reasoning AI model by OpenAI, released on April 16, 2025. It supports a context window of 200K tokens and can generate up to 100K output tokens.
At $2 per million input tokens and $8 per million output tokens, its blended cost of $5.00/1M tokens places it in the premium pricing tier. Its value score of 18.8 reflects the balance of quality and cost.
Using o3 with Swfte
Access o3 through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try o3 in our AI Playground before integrating.