Same open weights, served by 1 provider. Weights: Qwen/Qwen3.5-122B-A10B.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-10-01 | Qwen/Qwen3.5-122B-A10B | flexFP40.8× standard | $0.232 | $1.92 | — | $0.654 | Verified 7h ago · Changed 9h ago | |
DeepInfra Deprecated, 2026-10-01 | Qwen/Qwen3.5-122B-A10B | standardFP4 | $0.29 | $2.4 | — | $0.817 | Verified 7h ago · Changed 9h ago | |
DeepInfra Deprecated, 2026-10-01 | Qwen/Qwen3.5-122B-A10B | priorityFP41.5× standard | $0.435 | $3.6 | — | $1.23 | Verified 7h 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 fp4 | $77/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.