Same open weights, served by 2 providers. Weights: Qwen/Qwen3-235B-A22B-Instruct-2507.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3-235B-A22B-Instruct-2507 | flexFP80.8× standard | $0.072 | $0.44 | — | $0.164 | Verified 7h ago · Changed 9h ago | |
DeepInfra | Qwen/Qwen3-235B-A22B-Instruct-2507 | standardFP8 | $0.09 | $0.55 | — | $0.205 | Verified 7h ago · Changed 9h ago | |
DeepInfra | Qwen/Qwen3-235B-A22B-Instruct-2507 | priorityFP81.5× standard | $0.135 | $0.825 | — | $0.307 | Verified 7h ago · Changed 9h ago | |
AWS Bedrock | qwen.qwen3-235b-a22b-2507-v1:0 | standardQuantization not disclosed | $0.22 | $0.88 | — | $0.385 | Verified 9h ago · Changed 9h 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 | $20/mo |
| AWS Bedrock | $39.6/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.