Qwen3.6 35B A3B
Qwen · Open weights · Released Apr 27, 2026 · qwen/qwen3.6-35b-a3b
Best $0.045 in / $0.30 out via Engy · 208K ctx at this price (headline 262K)
262K contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 12 providersUSD / MTOK · PRICES 15 MINUTES AGO · SPEED 8 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | SMOKE | UPTIME |
|---|---|---|---|---|---|---|---|---|---|
| $0.045 | $0.30 | $0.015 | 208K | — | ✕ | ✕ | — | — | |
| $0.05 | $0.70 | $0.025 | 262K | fp4 | 2.8s | 118 tok/s | 1/5 | 99.9% | |
| $0.08 | $0.76 | $0.08 | 262K | fp8 | — | — | 2/5 | 100.0% | |
| $0.10 | $0.90 | $0.05 | 262K | fp8 | 1s | 53 tok/s | 2/5 | 100.0% | |
| $0.10 | $0.89 | $0.035 | 262K | fp8 | 0.53s | 101 tok/s | — | 99.4% | |
| $0.10 | $0.95 | $0.10 | 262K | fp8 | 0.47s | 219 tok/s | — | 100.0% | |
| $0.10 | $0.90 | $0.025 | 262K | fp8 | 0.69s | 57 tok/s | 2/5 | 99.2% | |
| $0.10 | $1.00 | — | 256K | fp8 | 0.88s | 170 tok/s | 1/5 | 100.0% | |
| $0.15 | $1.43 | $0.15 | 262K | fp8 | — | — | — | 99.9% | |
| $0.19 | $1.70 | $0.17 | 262K | fp8 | 0.73s | 45 tok/s | — | 100.0% | |
| $0.24 | $1.80 | $0.15 | 262K | fp8 | 1.1s | 61 tok/s | — | 90.1% | |
| $0.338 | $2.02 | $0.15 | — | — | ✕ | ✕ | — | — |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = 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 8 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Input price history · best listed price, observed
↑ 350% SINCE NOV 5, 2026
$0.01 · NOV 5, 2026$0.045 · TODAY
Pricing variants · USD / MTok in / out
STANDARD
$0.045 / $0.30
per MTok in / out
CACHE READ $0.015
Recent changesRSS ↗
Nov 21, 2026endpoint removed · atlascloud13 → 12
Nov 17, 2026endpoint removed · dekallm14 → 13
Nov 16, 2026price decreased · input0.026 → 0.018
Nov 16, 2026price decreased · output0.239 → 0.167
Nov 14, 2026price increased · input0.014 → 0.02
Nov 14, 2026price increased · output0.131 → 0.188
Nov 13, 2026price increased · input0.011 → 0.014
Nov 13, 2026price increased · output0.101 → 0.131
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 API15 minutes ago
AGGREGATORHugging Face15 minutes ago
COMMUNITYModelIndex benchmarks8 minutes ago
MEASUREDVerified 15 minutes ago · list prices, not negotiated rates.