Same open weights, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-06-11 | Qwen/Qwen3.5-0.8B | standardFull precision | $0.01 | $0.05 | โ | $0.02 | Verified 12h ago ยท Changed 40d ago | |
DeepInfra Deprecated, 2026-06-11 | Qwen/Qwen3.5-0.8B | priorityFull precision1.5ร standard | $0.015 | $0.075 | โ | $0.03 | Verified 12h ago ยท Changed 40d 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 bfloat16 | $2/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.