Identity
- Status
- active
- Developer ID
Qwen/Qwen3.8-2.4T-A95B- Released
- Not reported
- Version
- Qwen3.8-2.4T-A95B
- License
- other
QwenQwen3.8 2.4T A95B
Qwen3.8-2.4T-A95B is an open-weight language model published by Qwen.
- Token context
- 262K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Not reported
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $2.00 | $6.00 | $0.20 | — | Oct 5, 2026 | Provider-reported |
 OpenrouterAvailable | $2.00 | $6.00 | $0.25 | — | Oct 19, 2026 | Provider-reported |
At a Glance
Model Facts
Capacity
- Token context
- 262K tokens
- Maximum output
- Unknown
- Total parameters
- 2.45T
- Active parameters
- 95B
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- No
- Tool calling
- Yes
- Capabilities
- chat, generation, reasoning, tools
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
AliasesQwen/Qwen3.8-2.4T-A95B, Qwen/Qwen3.8-2.4T-A95B
Explicit Unknowns
- Release date
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
Qwen/Qwen3.8-2.4T-A95B developer model repositoryQwen · observed Aug 28, 2026Qwen/Qwen3.8-2.4T-A95B README.md at 207bd685a7e3Qwen · observed Aug 28, 2026Deepinfra catalogDeepinfra · observed Oct 19, 2026OpenRouter qwen/qwen3.8-2.4t-a95b model APIOpenRouter · observed Aug 28, 2026Qwen/Qwen3.8-2.4T-A95B Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026Qwen/Qwen3.8-2.4T-A95B config.json at 207bd685a7e3Qwen · observed Aug 28, 2026Qwen/Qwen3.8-2.4T-A95B immutable Hub API metadataQwen · observed Aug 28, 2026Qwen/Qwen3.8-2.4T-A95B tokenizer_config.json at 207bd685a7e3Qwen · observed Aug 28, 2026Fireworks Ai catalogFireworks Ai · observed Oct 19, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026Openrouter catalogOpenrouter · observed Oct 19, 2026Together Ai catalogTogether Ai · observed Oct 19, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
| vs |  Hy4 previewTencent | cross-developer peerstext | |
| vs |  DeepSeek V4 ProDeepSeek | cross-developer peerstext | |
| vs | Qwen3.8 27BQwen | family variantstext | |
| vs |  Kimi K2 InstructMoonshot AI | cross-developer peerstext | |
| vs | Kimi K2 ThinkingMoonshot AI | cross-developer peerstext | |
| vs | Kimi K2.5Moonshot AI | cross-developer peerstext | |
| vs | Kimi K2.6Moonshot AI | cross-developer peerstext | |
| vs | Qwen3 Coder NextQwen | family variantstext | |
| vs | family variantstext | ||
| vs | family variantstext | ||
| vs |  Inkling SmallThinking Machines Lab | cross-developer peerstext | |
| vs |  GLM 5Z.ai | cross-developer peerstext | |
| vs | GLM 5.1Z.ai | cross-developer peerstext |
Questions
Qwen3.8 2.4T A95B FAQs
What is Qwen3.8 2.4T A95B?+
Qwen3.8-2.4T-A95B is an open-weight language model published by Qwen. It is developed by Qwen and its current sourced lifecycle status is active.
What inputs and outputs does Qwen3.8 2.4T A95B support?+
Qwen3.8 2.4T A95B's current record lists Text as input and Text as output.
How much context does Qwen3.8 2.4T A95B support?+
The current record lists a 262K-token context window and does not report a maximum output length.
Is Qwen3.8 2.4T A95B available through an API?+
Qwen3.8 2.4T A95B is marked as API-available. The directly sourced provider records currently include Deepinfra, Fireworks Ai, Hugging Face, Openrouter, and Together Ai.
How large is Qwen3.8 2.4T A95B?+
The current record lists 2.45T total parameters and 95B active parameters. Its architecture is Qwen3_5MoeForCausalLM.
What capabilities and tasks does Qwen3.8 2.4T A95B support?+
Qwen3.8 2.4T A95B's recorded capabilities are chat, generation, reasoning, and tools. Its supported tasks are text.
How much does Qwen3.8 2.4T A95B cost through an API?+
The lowest directly sourced prices currently attached to Qwen3.8 2.4T A95B are $2.00 per million input tokens through Deepinfra and $6.00 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.
Can Qwen3.8 2.4T A95B be self-hosted?+
Qwen3.8 2.4T A95B is an open-weight model. Self-hosting is supported, and the recorded license is other.
Does Qwen3.8 2.4T A95B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are Qwen/Qwen3.8-2.4T-A95B.
Which models can Qwen3.8 2.4T A95B be compared with?+
The current compatible peer set includes Hy4 preview, DeepSeek V4 Pro, Qwen3.8 27B, Kimi K2 Instruct, and Kimi K2 Thinking. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →