Same open weights, served by 1 provider. Weights: Qwen/Qwen3.5-35B-A3B.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3.5-35B-A3B | flexFP80.8× standard | $0.112 | $0.80 | $0.04 | $0.284 | Verified 5h ago · Changed 8h ago | |
DeepInfra | Qwen/Qwen3.5-35B-A3B | standardFP8 | $0.14 | $1.0 | $0.05 | $0.355 | Verified 5h ago · Changed 8h ago | |
DeepInfra | Qwen/Qwen3.5-35B-A3B | priorityFP81.5× standard | $0.21 | $1.5 | $0.075 | $0.532 | Verified 5h ago · Changed 8h 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 fp8 | $34/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.