Same open weights, served by 1 provider. Weights: stepfun-ai/Step-3.7-Flash.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-10-01Promo pricing | stepfun-ai/Step-3.7-Flash | flexMODELOPT0.8× standard | $0.16 | $0.92 | $0.032 | $0.35 | Verified 5h ago · Changed 7h ago | |
DeepInfra Deprecated, 2026-10-01Promo pricing | stepfun-ai/Step-3.7-Flash | standardMODELOPT | $0.20 | $1.15 | $0.04 | $0.438 | Verified 5h ago · Changed 7h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| DeepInfra modelopt | $43/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.