Same open weights, served by 2 providers. Weights: Qwen/Qwen3-32B.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3-32B | flexFP80.8× standard | $0.064 | $0.224 | — | $0.104 | Verified 8h ago · Changed 10h ago | |
DeepInfra | Qwen/Qwen3-32B | standardFP8 | $0.08 | $0.28 | — | $0.13 | Verified 8h ago · Changed 10h ago | |
DeepInfra | Qwen/Qwen3-32B | priorityFP81.5× standard | $0.12 | $0.42 | — | $0.195 | Verified 8h ago · Changed 10h ago | |
AWS Bedrock | qwen.qwen3-32b-v1:0 | standardQuantization not disclosedReduced context (33k of 41k) | $0.15 | $0.60 | — | $0.262 | Verified 10h ago · Changed 10h 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 | $13.6/mo |
| AWS Bedrock | $27/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.