FriendliAI
Listed at https://friendli.ai
Overall Rank # ⭐ Consider
⚠️ US + Korea servers, ~200-400ms latency from China | 🌍 International
💰 Token Pricing
| Type | Price | Note |
|---|---|---|
| Input | GLM-5.2/5.1: $1.4/M, DeepSeek-V3.2: $0.5/M, Qwen3-235B: $0.2/M, MiniMax-M2.5: $0.3/M, Gemma-4-31B: $0.14/M | per million tokens |
| Output | GLM-5.2/5.1: $4.4/M, DeepSeek-V3.2: $1.5/M, Qwen3-235B: $0.8/M, MiniMax-M2.5: $1.2/M, Gemma-4-31B: $0.4/M | per million tokens |
💡 Free Credits: No free tier — per-token billing, no minimum
🤖 Supported Models (8)
GLM-5.2GLM-5.1DeepSeek-V3.2Qwen3-235B-A22B-2507MiniMax-M2.5Gemma-4-31B-itK-EXAONE-236BWhisper-large-v3
✨ Pros
- ✓593K+ open models across Model APIs & Dedicated Endpoints
- ✓SOC 2 Type II & HIPAA compliance
- ✓Pay-per-token + per-second GPU billing
- ✓Prompt caching — cached reads at 0.1x-0.5x input
⚠️ Cons
- ×Korean-based — smaller ecosystem than US peers
- ×No free tier for Model API access
- ×Fewer third-party integrations vs Fireworks/Together
🎯 Best For
Teams needing front-tier inference API or dedicated GPU endpoints, especially Asia-based