Qwen3.5-122B-A10B
Qwen · Open weights · Released Feb 25, 2026 · qwen/qwen3.5-122b-a10b
Best $0.26 in / $2.08 out via Alibaba
262K contextVisionToolsReasoningStructured outputOpen weights
Available from 3 providersUSD / MTOK · PRICES 15 MINUTES AGO · SPEED 3 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
| $0.26 | $2.08 | — | 262K | — | 1.9s | 149 tok/s | 5/5 | 100.0% | |
| $0.26 | $2.08 | — | 262K | fp8 | 1.6s | 115 tok/s | 2/5 | 91.8% | |
| $0.40 | $3.20 | — | 262K | bf16 | 2.5s | 103 tok/s | 4/5 | 98.8% |
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 3 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Nov 21, 2026endpoint removed · atlascloud4 → 3
Nov 5, 2026endpoint removed · cheaperinference5 → 4
Oct 23, 2026endpoint added · cheaperinference4 → 5
Oct 2, 2026endpoint removed · deepinfra5 → 4
About
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Specifications
Context window262,144
Max output65,536
Modalities intext, image, video
Modalities outtext
LicenseOpen weights
ReleasedFeb 25, 2026
TokenizerQwen3
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3.5-122b-a10b)Sources
OpenRouter API15 minutes ago
AGGREGATORHugging Face15 minutes ago
COMMUNITYModelIndex benchmarks18 days ago
MEASUREDVerified 15 minutes ago · list prices, not negotiated rates.