Start calling this model with endpoint-specific examples.
Headline benchmark standings and comparison context.
Key dates, capabilities, and model metadata.
Effective pricing across providers over the past hour and 30-day pricing history by meter.
Based on the last hour of usage: we total provider spend, divide by total token volume, and express it as USD per 1M tokens. Providers with more traffic naturally carry more weight.
Weighted Avg Input Price
--
per 1M tokens (past hour)
Weighted Avg Output Price
--
per 1M tokens (past hour)
| Provider | Input $/Million | Output $/Million | Cache Token % |
|---|---|---|---|
Amazon Bedrock | $0.150 | $0.600 | -- |
AtlasCloud | $0.100 | $0.400 | -- |
Azure | $0.150 | $0.600 | -- |
Baseten | $0.100 | $0.500 | -- |
Cerebras | $0.350 | $0.750 | -- |
Cloudflare | $0.350 | $0.750 | -- |
Fireworks | $0.150 | $0.600 | -- |
Groq | $0.150 | $0.600 | -- |
IonRouter | $0.020 | $0.095 | -- |
Nebius Token Factory | $0.100 | $0.500 | -- |
NovitaAI | $0.050 | $0.250 | -- |
SiliconFlow | $0.050 | $0.450 | -- |
Together | $0.150 | $0.600 | -- |
Venice | $0.070 | $0.300 | -- |
Venice (E2EE) | $0.130 | $0.650 | -- |
Weights & Biases | $0.150 | $0.600 | -- |
Meter
