Qwen3.6 35B A3B
Qwen · Open weights · Released Apr 27, 2026 · qwen/qwen3.6-35b-a3b
Best $0.05 in / $0.70 out via Darkbloom · fp4
262K contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 10 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 2 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
 Darkbloom | $0.05 | $0.70 | $0.025 | 262K | fp4 | 4.7s° | 99° tok/s | 1/5 | 100.0% |
 AkashML | $0.10 | $0.90 | $0.05 | 262K | fp8 | ✕ | ✕ | 2/5 | 100.0% |
 DeepInfra | $0.10 | $0.95 | $0.10 | 262K | fp8 | 0.62s° | 43° tok/s | 2/5 | 100.0% |
| DEDekaLLM | $0.10 | $1.00 | $0.05 | 262K | — | — | — | — | 99.9% |
 Venice | $0.10 | $1.00 | — | 256K | fp8 | 0.9s° | 305° tok/s | 1/5 | 99.7% |
 Parasail | $0.15 | $1.00 | $0.05 | 262K | fp8 | ✕ | ✕ | 2/5 | 99.7% |
 AtlasCloud | $0.186 | $1.11 | $0.186 | 262K | fp8 | ✕ | ✕ | 5/5 | 99.7% |
 Phala | $0.20 | $1.27 | $0.056 | 262K | — | 0.74s° | 157° tok/s | — | 97.6% |
 SiliconFlow | $0.24 | $1.80 | $0.15 | 262K | fp8 | 1.8s° | 95° tok/s | — | 99.6% |
 CoreWeave | $0.25 | $1.25 | $0.25 | 262K | fp8 | ✕ | ✕ | — | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured against the provider API directly; ° = routed via OpenRouter (adds a hop) · ✕ = probed, endpoint returned no measurable stream · 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 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Input price history · best listed price, observed
↓ 37% SINCE AUG 23, 2026
$0.08 · AUG 23, 2026$0.05 · TODAY
Pricing variants · USD / MTok in / out
STANDARD
$0.05 / $0.70
per MTok in / out
CACHE READ $0.025
Recent changesRSS ↗
Oct 6, 2026endpoint added · dekallm10 → 10
Oct 6, 2026endpoint removed · cheaperinference10 → 10
Oct 2, 2026endpoint removed · reka11 → 10
Sep 26, 2026endpoint added · reka10 → 11
Sep 23, 2026endpoint added · cheaperinference9 → 10
Sep 23, 2026endpoint removed · io-net10 → 9
Sep 19, 2026price decreased · input0.05 → 0.04
Sep 17, 2026endpoint removed · dekallm11 → 10
About
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
Specifications
Context window262,144
Max output235,929
Modalities intext, image, video
Modalities outtext
LicenseOpen weights
ReleasedApr 27, 2026
TokenizerQwen
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3.6-35b-a3b)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks20 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.