QwenGeneralReleased 12 August 2026
Qwen3.8 2.4T A95B pricing, context and benchmark
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.
1.05M
Input context
131K
Output context
$2
Official input
$6
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Qwen3.8 2.4T A95B |
| Model ID | qwen/qwen3.8-2.4t-a95b |
| Provider | Qwen |
| Release date | 12 August 2026 |
| Status | Generally available |
| Input context | 1,048,576 tokens |
| Output context | 131,072 tokens |
| Official input pricing | $2 per 1M tokens |
| Official output pricing | $6 per 1M tokens |
| Cache read pricing | $0.24 per 1M tokens (88% off input) |
| Market input pricing | $2 per 1M (cheapest route) |
| Market output pricing | $6 per 1M (cheapest route) |
| Input modalities | text |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Qwen |
| Provider routes | 4 endpoints |
| Artificial Analysis index | Not published |
| Speed | 40 tokens/s, 108.98s to first token |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $2 in |
| Image | no | no | not supported |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is 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...
Qwen3.8 2.4T A95B carries a 1.05M token window, uses the Qwen tokenizer and is served by Qwen. On Hoodgen it sits in the General tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released12 August 2026
| Property | Qwen3.7 Flash | Qwen3.8 2.4T A95B | Change |
|---|---|---|---|
| Released | 2026 | 2026 | Same release window |
| Context | 1M | 1.05M | Changed |
| Max output | 66K | 131K | Changed |
| Input price | $0.03 | $2 | Higher |
| Output price | $0.13 | $6 | Higher |
| Input modalities | text, image, video | text | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
⚡
Prompt caching
Cached input costs $0.24 per million instead of $2, so stable prefixes get cheaper.
07 · Use cases
What can you do with Qwen3.8 2.4T A95B?
Everyday writing
Drafts, rewrites, summaries and replies.
Research
Source material condensed with the key numbers kept.
Chat
General questions where latency and cost both matter.
Tooling inside Hoodgen
Writer, Humanizer, Coding and the rest of the tool suite.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.24 per million instead of $2, a 88% discount. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
Qwen3.8 2.4T A95B pricing
Official pricing
List price
$2 / 1M in
$6 / 1M out
- $0.24 cached input
- 1.05M context
- text input
Cheapest route
$2 / 1M in
$6 / 1M out
- 4 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Novita | standard | $2 | $6 | $0.25 | 99.9% |
| Alibaba | standard | $2 | $6 | $0.25 | 99.8% |
| SiliconFlow | standard | $2 | $6 | $0.25 | 100.0% |
| Venice | standard | $2 | $6 | $0.25 | 86.4% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0280 | $14.00 | 13300 |
| List price | $0.0279 | $13.94 | 13244 |
10 · Developers
API and developer information
| Model ID | qwen/qwen3.8-2.4t-a95b |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text->text |
| Max prompt tokens | 1,048,576 |
| Max completion tokens | 131,072 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3.8-2.4t-a95b",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 131,072 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
Qwen3.8 2.4T A95B vs other Qwen models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Qwen3.8 2.4T A95B | 1.05M | $2 | $6 | n/a | 2026 |
| Qwen3.8 Max Prime | 1M | $4 | $12 | n/a | Sep 2026 |
| Qwen3.8 Max | n/a | $2 | $6 | 34 | 2026 |
| Qwen3.8 Max (0902) | 1M | $2 | $6 | n/a | Sep 2026 |
| Qwen3.7 Max | 1M | $1.475 | $4.425 | n/a | 2026 |
| Qwen3.7 Plus | 1M | $0.32 | $1.28 | n/a | 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Qwen and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Qwen3.8 2.4T A95B questions, answered
Qwen3.8 2.4T A95B is a general model from Qwen, released 12 August 2026. 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.
✦
Start chatting with Qwen3.8 2.4T A95B
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.