Same open weights, served by 2 providers. Weights: Qwen/Qwen3-Next-80B-A3B-Instruct.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3-Next-80B-A3B-Instruct | flexFP80.8× standard | $0.072 | $0.88 | — | $0.274 | Verified 5h ago · Changed 7h ago | |
DeepInfra | Qwen/Qwen3-Next-80B-A3B-Instruct | standardFP8 | $0.09 | $1.1 | — | $0.343 | Verified 5h ago · Changed 7h ago | |
AWS Bedrock | qwen.qwen3-next-80b-a3b | standardQuantization not disclosed | $0.15 | $1.2 | — | $0.412 | Verified 7h ago · Changed 7h ago | |
DeepInfra | Qwen/Qwen3-Next-80B-A3B-Instruct | priorityFP81.5× standard | $0.135 | $1.65 | — | $0.514 | 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 fp8 | $31/mo |
| AWS Bedrock | $39/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.