CO
Aya Expanse 32B
Cohere
Alibaba Cloud / Qwen Team model product
Qwen3.8 2.4T A95B
4 trillion total parameters and 95 billion active parameters.
Updated Sep 8, 2026. Default version: Qwen3.8-2.4T-A95B
LLMBoard ScoreN/ANot scored
CoverageN/ANot scored
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Qwen3.8 2.4T A95B Benchmark Results
Benchmark scores for the scored version.
No benchmark results
No benchmark result is linked to the scored version.
Qwen3.8 2.4T A95B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Qwen3.8 2.4T A95B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $2 input, $6 output per 1M via Deep Infra
- Tracked offerings
- 12
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderDeep Infra | Provider model IDQwen/Qwen3.8-2.4T-A95B | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3.8-2.4t-a95b | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderRequesty | Provider model IDqwen3.8-2.4T-A95B | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderCharm Hyper | Provider model IDqwen3.8-2.4t-a95b | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderAIHubMix | Provider model IDqwen3.8-2.4t-a95b | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context262K | Updated |
| ProviderVercel AI Gateway | Provider model IDalibaba/qwen3.8-2.4t-a95b | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderEden AI | Provider model IDqwen/qwen3.8-2.4t-a95b | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3.8-2.4t-a95b | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context1M | Updated |
| ProviderFireworks AI | Provider model IDaccounts/fireworks/models/qwen3p8-2p4t-a95b | Regionglobal | Input / 1M$2 | Output / 1M$6 | Context262.1K | Updated |
| ProviderCortecs | Provider model IDqwen3.8-2.4t-a95b | Regionglobal | Input / 1M$2.5 | Output / 1M$6 | Context262.1K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3.8-2.4T-A95B | Regionglobal | Input / 1M$2.5 | Output / 1M$6.25 | Context262.1K | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3.8-2.4t-a95b | Regionglobal | Input / 1M$2.5 | Output / 1M$6.25 | Context262.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen3.8 2.4T A95B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3.8-2.4T-A95B. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3.8 2.4T A95B Specifications
Technical details for the model's default version.
- Version
- Qwen3.8-2.4T-A95B
- Released
- Aug 12, 2026
- Knowledge cutoff
- Unknown
- Parameters
- 2.4T
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- Qwen3.8-Max License
Qwen3.8 2.4T A95B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionQwen3.8-2.4T-A95B | Released | LLMBoardN/A | Parameters2.4T | ContextN/A | Max outputN/A | Open weightsYes | LicenseQwen3.8-Max License |
Models similar to Qwen3.8 2.4T A95B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
CO
Aya Expanse 8B
Cohere
CO
Aya Vision 32B
Cohere
AN
Claude Fable 5
Anthropic
AN
Claude Fable 5.1
Anthropic
AN
Claude Haiku 3
Anthropic
What is Qwen3.8 2.4T A95B?
Key information about Qwen3.8 2.4T A95B and its available data.
8-Max from Alibaba Cloud / Qwen Team. It has a native context length of 262,144 tokens, extensible to about 1 million, and thinking is always on.
Data as of 2026-09-08.
FAQ
Common questions about Qwen3.8 2.4T A95B.
When was Qwen3.8 2.4T A95B released?
Qwen3.8 2.4T A95B's default version was released on Aug 12, 2026.
How much does Qwen3.8 2.4T A95B cost?
No official standard PAYG price is currently available for Qwen3.8 2.4T A95B. The lowest tracked third-party offer starts at $2 input and $6 output via Deep Infra.
Who created Qwen3.8 2.4T A95B?
Qwen3.8 2.4T A95B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3.8 2.4T A95B?
A context window is not available for the default version.
Is Qwen3.8 2.4T A95B open weight?
Yes. The default version is marked as open weight under Qwen3.8-Max License.