Providers/Phala
Phala logo

Phala

Inference providerredpill.ai ↗Status ↗
MODELS
20
ENDPOINTS
20
MIN INPUT
$0.07
MEDIAN BLENDED
$0.742
AVG UPTIME
98.7%
CHEAPEST FOR
2 models
Models on Phala · prices & measurements for models served by Phala’s APIUSD / MTOK · VERIFIED 23 MINUTES AGO
MODELINPUTOUTPUTCONTEXTQUANTTTFTTPSSMOKEVS BEST ELSEWHERE
NVIDIA logoNemotron 3.5 LightningNVIDIA$0.07$0.20262K—0.84s°166° tok/s—$0.039 elsewhere
Qwen logoQwen2.5 7B InstructQwen$0.10$0.2033K—0.65s°142° tok/s—only provider
Z.ai logoGLM 5.3 FlashZ.ai$0.113$0.3751.05Mnvfp4✕✕—$0.032 elsewhere
Qwen logoQwen3.8 27BQwen$0.15$1.881M—0.91s°127° tok/s—$0.024 elsewhere
Tencent logoHy3Tencent$0.15$0.64262K—2.1s°87° tok/s2/5$0.13 elsewhere
OpenAI logogpt-oss-120bOpenAI$0.15$0.60131K—0.93s°193° tok/s—$0.03 elsewhere
Qwen logoQwen3.6 35B A3BQwen$0.20$1.27262K—0.74s°157° tok/s—$0.05 elsewhere
DeepSeek logoDeepSeek V4.1 FlashDeepSeek$0.21$0.841.05M—✕✕—$0.018 elsewhere
Meta logoMuse Glimmer 30BMetaBEST PRICE$0.30$1.10131K—✕✕—cheapest here
Qwen logoQwen3.5-27BQwen$0.30$2.40262K—2s°40° tok/s1/5$0.195 elsewhere
Qwen logoQwen3.6 27BQwen$0.32$3.25262K—✕✕1/5$0.30 elsewhere
DeepSeek logoDeepSeek V4 Flash 0731DeepSeek$0.44$1.321.05M—✕✕—$0.01 elsewhere
Qwen logoQwen3.5 397B A17BQwen$0.55$3.50262K—3.2s°85° tok/s3/5$0.39 elsewhere
Z.ai logoGLM 5.3Z.ai$0.84$2.641.05M—0.55s°158° tok/s—$0.039 elsewhere
DeepSeek logoDeepSeek V3.2DeepSeek$1.00$1.00164K—3.3s°19° tok/s—$0.209 elsewhere
Moonshot AI logoKimi K2.6Moonshot AI$1.09$4.60262K—1.8s°67° tok/s—$0.465 elsewhere
Z.ai logoGLM 5.1Z.ai$1.21$4.20203K—✕✕—$0.966 elsewhere
Z.ai logoGLM 5.2Z.ai$1.26$3.001.05Mfp8✕✕—$0.03 elsewhere
DeepSeek logoDeepSeek V4 Pro 0813DeepSeek$1.45$4.361.05M—3.2s°65° tok/s—$0.158 elsewhere
Moonshot AI logoKimi K3Moonshot AI$1.95$9.751.05M—2.8s°74° tok/s—$0.68 elsewhere
TTFT/TPS: ModelIndex-measured medians (P50, trailing 21d) for Phala’s endpoints · ° = measured via OpenRouter routing · ✕ = probed, no measurable stream · SMOKE: of 5 capability probes passed · methodology on each model page