Qwen · Model identity
Qwen3.8 2.4T A95B
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...
2pricing routes
What published route metadata supports
CachingHugging FaceReasoningStructured outputTool use
Input modalities
Text
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Only source-backed fields are filled
Release dateNot independently verified
Knowledge cutoffNot independently verified
Open weightsNot independently verified
OpenRouter catalog date2026-08-12
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
Could this workload cost less?Compare Qwen3.8 2.4T A95B with cheaper models using the same workload.
Find cheaper alternatives →| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterStandard | qwen/qwen3.8-2.4t-a95b | $2 | $0.25 | $6 | 1.05M | OpenRouter API ↗ |
| OpenRouterBatch | qwen/qwen3.8-2.4t-a95b:batch | $2 | $0.25 | $6 | 1.01M | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
4 verified price changes since Aug 26, 2026
1 route availability change recorded. No earlier prices are inferred.
- Sep 3, 2026OpenRouter · Batch
Input $2.5 → $2 · Cached input $0.5 → $0.25 · Output $6.25 → $6
- Aug 29, 2026OpenRouter · Standard
Cached input $0.2 → $0.25
- Aug 29, 2026OpenRouter · Batch
Input $2 → $2.5 · Cached input $0.25 → $0.5 · Output $6 → $6.25
- Aug 28, 2026OpenRouter · Batch
New pricing route added
- Aug 28, 2026OpenRouter · Standard
Cached input $0.25 → $0.2