Same open weights, served by 2 providers. Weights: Qwen/Qwen3-Coder-30B-A3B-Instruct.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2025-11-15 | Qwen/Qwen3-Coder-30B-A3B-Instruct | standardFP8 | $0.07 | $0.26 | — | $0.118 | Verified 6h ago · Changed 8h ago | |
AWS Bedrock | qwen.qwen3-coder-30b-a3b-v1:0 | standardQuantization not disclosed | $0.15 | $0.60 | — | $0.262 | Verified 8h 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 | $12.2/mo |
| AWS Bedrock | $27/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.