Qwen3.5-35B-A3B
Qwen · Open weights · Released Feb 25, 2026 · qwen/qwen3.5-35b-a3b
Best $0.065 in / $0.75 out via Darkbloom · fp4
262K contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 7 providersUSD / MTOK · PRICES 15 MINUTES AGO · SPEED 9 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
| $0.065 | $0.75 | $0.033 | 262K | fp4 | 1.9s | 123 tok/s | — | 100.0% | |
| $0.112 | $0.80 | $0.04 | 262K | fp8 | — | — | 3/5 | 0.0% | |
| $0.14 | $1.00 | $0.05 | 262K | fp8 | 4.2s | 62 tok/s | — | 99.7% | |
| $0.15 | $1.00 | $0.05 | 262K | fp8 | 0.88s | 213 tok/s | 3/5 | 99.2% | |
| $0.15 | $1.00 | $0.05 | 256K | — | 0.77s | 269 tok/s | — | 99.9% | |
| $0.163 | $1.30 | — | 262K | — | 1.1s | 210 tok/s | 5/5 | 100.0% | |
| $0.24 | $1.80 | $0.15 | 262K | fp8 | 1.1s | 87 tok/s | 3/5 | 98.6% |
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 9 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Input price history · best listed price, observed
↓ 19% SINCE OCT 15, 2026
$0.08 · OCT 15, 2026$0.065 · TODAY
Pricing variants · USD / MTok in / out
STANDARD
$0.065 / $0.75
per MTok in / out
CACHE READ $0.033
Recent changesRSS ↗
Nov 21, 2026endpoint removed · atlascloud8 → 7
Oct 15, 2026price decreased · input0.08 → 0.065
Oct 6, 2026endpoint removed · cheaperinference8 → 7
Sep 23, 2026endpoint added · cheaperinference7 → 8
About
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Specifications
Context window262,144
Max output81,920
Modalities intext, image, video
Modalities outtext
LicenseOpen weights
ReleasedFeb 25, 2026
TokenizerQwen3
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3.5-35b-a3b)Sources
OpenRouter API15 minutes ago
AGGREGATORHugging Face15 minutes ago
COMMUNITYModelIndex benchmarks9 minutes ago
MEASUREDVerified 15 minutes ago · list prices, not negotiated rates.