Same open weights, served by 2 providers. Weights: Qwen/Qwen3.8-2.4T-A95B.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-10-12 | Qwen/Qwen3.8-2.4T-A95B | standardFP4Reduced context (262k of 1M) | $2.0 | $6.0 | $0.20 | $3.0 | Verified 3h ago · Changed 6h ago | |
Fireworks AI | accounts/fireworks/models/qwen3p8-2p4t-a95b | standardQuantization not disclosedReduced context (262k of 1M) | $2.0 | $6.0 | $0.25 | $3.0 | Verified 6h ago · Changed 6h 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 | $320/mo |
| Fireworks AI | $320/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.