The Orchestrator › Models › Qwen
Qwen: 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, with 95 billion active parameters out of 2.4 trillion total. It is...
Specifications
| Provider | Qwen |
| Model ID | qwen/qwen3.8-2.4t-a95b |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text → text |
| Tokenizer | Qwen |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2026-08-12 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | qwen/qwen3.8-2.4t-a95b | $2.00 | $6.00 | 1.0M |
| standard | TrustedRouter | qwen/qwen3.8-2.4t-a95b | $1.06 | $4.22 | 1M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $1.06 | $4.22 | 1M |
| 2026-11-14 | $2.00 | $6.00 | 1.0M |
Capabilities
Agentic tool useStructured outputsReasoning (always on)1M+ context windowControllable reasoningNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p