Same open weights, served by 2 providers.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
Together AI Deprecated | Qwen/Qwen3-Coder-Next-FP8 | standardQuantization not disclosed | $0.50 | $1.2 | — | $0.675 | Verified 8h ago · Changed 8h ago | |
AWS Bedrock | qwen.qwen3-coder-next | standardQuantization not disclosed | $0.50 | $1.2 | — | $0.675 | 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.
| Together AI | $74/mo |
| AWS Bedrock | $74/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.