Same open weights, served by 3 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra | Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo | standardFP4 | $0.30 | $1.0 | $0.10 | $0.475 | Verified 6h ago · Changed 8h ago | |
DeepInfra Deprecated, 2026-04-30 | Qwen/Qwen3-Coder-480B-A35B-Instruct | standardFP8 | $0.40 | $1.6 | — | $0.70 | Verified 6h ago · Changed 8h ago | |
AWS Bedrock | qwen.qwen3-coder-480b-a35b-v1:0 | standardQuantization not disclosedReduced context (131k of 262k) | $0.45 | $1.8 | — | $0.788 | Verified 8h ago · Changed 8h ago | |
Together AI Deprecated | Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | standardQuantization not disclosed | $2.0 | $2.0 | — | $2.0 | 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 fp4 | $50/mo |
| DeepInfra fp8 | $72/mo |
| AWS Bedrock | $81/mo |
| Together AI | $240/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.