Inference host
Phala
LLM prices per million tokens
- Models
- 18
- Routes
- 18
- Cheapest
- $0.1
- Qwen2.5 7B Instruct input
- Batch
- n/a
- not stated
Models on Phala
- Qwen2.5 7B InstructPhala$0.1 / $0.2
- GLM 5.3 FlashPhala, fp8, fp8$0.128 / $0.425+194% vs headline
- gpt-oss-120bPhala$0.15 / $0.6+304% vs headline
- Qwen3.6 35B A3BPhala$0.2 / $1.27+120% vs headline
- DeepSeek V4.1 FlashPhala$0.276 / $1.1+84% vs headline
- Muse Glimmer 30BPhala$0.3 / $1.1
- DeepSeek V4 Flash 0731Phala$0.44 / $1.32+733% vs headline
- Qwen3.8 27BPhala$0.199 / $2.08-30% vs headline
- Qwen3.5-27BPhala$0.3 / $2.4+54% vs headline
- Qwen3.6 27BPhala$0.32 / $2.7-10% vs headline
- DeepSeek V3.2Phala$1 / $1+327% vs headline
- Qwen3.5 397B A17BPhala$0.55 / $3.5+47% vs headline
- GLM 5.3Phala$0.84 / $2.64+23% vs headline
- GLM 5.2Phala, fp8, fp8$1.26 / $3+94% vs headline
- GLM 5.1Phala$1.21 / $4.2+32% vs headline
- Kimi K2.6Phala$1.09 / $4.6+91% vs headline
- DeepSeek V4 Pro 0813Phala$1.45 / $4.36+120% vs headline
- Kimi K3Phala$2.1 / $10.5+12% vs headline
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.