Cerebras
Listed at https://inference.cerebras.ai
Overall Rank #14 ⭐ Consider
❌ Proxy required | 🌍 International
💰 Token Pricing
| Type | Price | Note |
|---|---|---|
| Input | $0.10/M to $0.60/M tokens（所有模型统一 $0.60/M input） | per million tokens |
| Output | $0.10/M to $0.60/M tokens（统一 $0.60/M output） | per million tokens |
💡 Free Credits:
🤖 Supported Models (6)
Cerebras Llama 3.3 70BCerebras Llama 3.1 405BCerebras Llama 3.3 8BCerebras Qwen 2.5 72BCerebras Qwen 2.5 32BCerebras DeepSeek-R1 Distill
✨ Pros
- ✓WSE-3 wafer-scale chip, 2000+ tok/s inference
- ✓Llama 3.3 70B reaches 2,000+ tok/s, industry fastest
- ✓Zero cold start
- ✓OpenAI-compatible API
- ✓Reasonable pricing ($0.60/M tokens flat)
- ✓GPU alternative with unique inference chip design
⚠️ Cons
- ×China requires proxy
- ×Limited model selection (only 6)
- ×No Function Calling support
- ×Speed dependent on Llama/Qwen base model performance
- ×Non-general-purpose inference chip, limited third-party support
- ×No multimodal models
🎯 Best For
Applications demanding extreme inference speed; high-throughput real-time scenarios; high-performance Llama inference