Qwen3.8 2.4T A95B
Qwen · Open weights · Released Aug 12, 2026 · qwen/qwen3.8-2.4t-a95b
Best $2.00 in / $6.00 out via Alibaba · 1M ctx at this price (headline 1.05M)
1.05M contextToolsReasoningStructured outputPrompt cachingOpen weights
Available from 5 providersUSD / MTOK · PRICES 15 MINUTES AGO · SPEED 2 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
| $2.00 | $6.00 | $0.25 | 1M | — | 2.2s | 51 tok/s | 5/5 | 100.0% | |
| $2.00 | $6.00 | $0.25 | 1M | — | — | — | — | 100.0% | |
| $2.00 | $6.00 | $0.25 | 1M | — | 2.9s | 34 tok/s | — | 100.0% | |
| $2.00 | $6.00 | $0.25 | 1.05M | fp8 | 1.8s | 44 tok/s | 5/5 | 100.0% | |
| $2.00 | $6.00 | $0.25 | 262K | — | 1.6s | 200 tok/s | 3/5 | 99.9% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.2 · methodology v1.1 · measured 2 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$2.00 / $6.00
per MTok in / out
CACHE READ $0.25CACHE WRITE $2.50
Recent changesRSS ↗
Nov 22, 2026endpoint added · fireworks4 → 5
Nov 5, 2026endpoint removed · cheaperinference5 → 4
Nov 5, 2026endpoint removed · together6 → 5
Oct 23, 2026endpoint added · cheaperinference5 → 6
Oct 14, 2026endpoint removed · modal6 → 5
Oct 13, 2026endpoint removed · deepinfra7 → 6
About
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
Context window1,048,576
Max output65,536
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedAug 12, 2026
TokenizerQwen
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3.8-2.4t-a95b)Sources
OpenRouter API15 minutes ago
AGGREGATORHugging Face15 minutes ago
COMMUNITYModelIndex benchmarks20 days ago
MEASUREDVerified 15 minutes ago · list prices, not negotiated rates.