Scan to join WeChat groupo3
o3: a o model from OpenAI, ~200K context, knowledge cutoff 2024-05
o3 is a o model from OpenAI (~200K context, input around $2/1M tokens). Suitable for assistants, content generation, knowledge Q&A and business automation
starsCapabilities
visibilityVision understandingcodeFunction callingdata_objectStructured output
paymentsContext and pricing
Context limit200,000
Max output100,000
Knowledge cutoff2024-05
Input price$2/ 1M tokens
Output price$8/ 1M tokens
Cached input price$0.5/ 1M tokens
descriptionOverview
Overview
o3 is provided by OpenAI, model ID o3
Key specs
- Context: 200K tokens
- Max output: 100K tokens
- Knowledge cutoff: 2024-05
- Input price: $2/1M
- Output price: $8/1M
Best for
Consider o3 when comparing context length, pricing, multimodal support and relay availability
lightbulbUse cases
- Image and multimodal Q&A
- Visual content analysis
- Document and screenshot understanding
thumb_upStrengths
- Very long context (~200K), good for long documents and codebases
- Supports image and multimodal input
- High single-response output limit (~100K)
infoLimitations
- Knowledge cutoff 2024-05; newer facts need external retrieval
- Pricing and availability vary by upstream and relay; verify with official docs and tests