Skip to content

Qwen3.6 35B A3B

Qwentext + image + video → textHugging Face OpenRouter

The cheapest provider for Qwen3.6 35B A3B is Darkbloom at $0.213 per 1M tokens (blended), charging $0.05 per 1M input and $0.70 per 1M output tokens. 9 providers serve it; the most expensive charges 3.0× as much. Context window: 256K tokens. Prices tracked since Oct 3, 2026.

Best price
$0.213
at Darkbloom
Input / output
$0.05 / $0.70
per 1M tokens
Providers
9
3.0× spread
7 days
—
best price
30 days
—
best price
Context
256K
tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

  • DarkbloomCheapest
    $0.213
    $0.05 in · $0.70 out
    best
    256K ctx100% uptimefp4
  • $0.30
    $0.10 in · $0.90 out
    +41%
    256K ctx100% uptimefp8
  • $0.313
    $0.10 in · $0.95 out
    +47%
    256K ctx99.7% uptimefp8
  • $0.325
    $0.10 in · $1.00 out
    +53%
    250K ctx100% uptimefp8
  • $0.363
    $0.15 in · $1.00 out
    +71%
    256K ctx100% uptimefp8
  • $0.418
    $0.186 in · $1.11 out
    +97%
    256K ctx99.3% uptimefp8
  • $0.468
    $0.20 in · $1.27 out
    +120%
    256K ctx99.8% uptime
  • $0.50
    $0.25 in · $1.25 out
    +135%
    256K ctx100% uptimefp8
  • $0.63
    $0.24 in · $1.80 out
    +196%
    256K ctx99.7% uptimefp8
Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered byCache read
Darkbloom$0.025
AkashML, Parasail$0.05
DeepInfra$0.10
AtlasCloud$0.186
Phala$0.056
CoreWeave$0.25
SiliconFlow$0.15

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

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...
Released
Apr 27, 2026
First tracked
Oct 3, 2026
Canonical slug
qwen/qwen3.6-35b-a3b-20260415
Weights
Qwen/Qwen3.6-35B-A3B