Same open weights, served by 2 providers. Weights: Qwen/Qwen3-VL-235B-A22B-Instruct.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3-VL-235B-A22B-Instruct | flexFP80.8× standard | $0.16 | $0.704 | $0.088 | $0.296 | Verified 7h ago · Changed 9h ago | |
DeepInfra | Qwen/Qwen3-VL-235B-A22B-Instruct | standardFP8 | $0.20 | $0.88 | $0.11 | $0.37 | Verified 7h ago · Changed 9h ago | |
DeepInfra | Qwen/Qwen3-VL-235B-A22B-Instruct | priorityFP81.5× standard | $0.30 | $1.32 | $0.165 | $0.555 | Verified 7h ago · Changed 9h ago | |
AWS Bedrock | qwen.qwen3-vl-235b-a22b | standardQuantization not disclosed | $0.53 | $2.66 | — | $1.06 | 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 | $37.6/mo |
| AWS Bedrock | $106.2/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.