Skip to content

Qwen3.6 35B A3B

text + image + video → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.213

at Darkbloom

Input / output
$0.05 / $0.70
Providers
9
Spread
2.5×
7 days
+474%
30 days
0%
Context
256K
Prices per 1M tokens, blended: Darkbloom $0.213, DeepInfra (fp8/flex) $0.25, CoreWeave $0.298, AkashML $0.30, Parasail $0.30, DeepInfra $0.313, Venice $0.325, PrimeIntellect $0.335, DeepInfra (fp8/priority) $0.469, AtlasCloud $0.50, SiliconFlow $0.63.

Providers

  • DarkbloomCheapest
    $0.213
    $0.05 in · $0.70 out
    −15% vs ref
    256K ctx100% uptimefp4
  • fp8/flex
    $0.25
    $0.08 in · $0.76 out
    ref vs ref
    256K ctx90.0% uptimefp8
  • $0.298
    $0.10 in · $0.89 out
    +19% vs ref
    256K ctx100% uptimefp8
  • $0.30
    $0.10 in · $0.90 out
    +20% vs ref
    256K ctx100% uptimefp8
  • $0.30
    $0.10 in · $0.90 out
    +20% vs ref
    256K ctx98.0% uptimefp8
  • $0.313
    $0.10 in · $0.95 out
    +25% vs ref
    256K ctx99.7% uptimefp8
  • $0.325
    $0.10 in · $1.00 out
    +30% vs ref
    250K ctx99.8% uptimefp8
  • $0.335
    $0.11 in · $1.01 out
    +34% vs ref
    256K ctx99.9% uptimefp8
  • fp8/priority
    $0.469
    $0.15 in · $1.425 out
    +88% vs ref
    256K ctx99.7% uptimefp8
  • $0.50
    $0.25 in · $1.25 out
    +100% vs ref
    256K ctx46.0% uptimefp8
  • $0.63
    $0.24 in · $1.80 out
    +152% vs ref
    256K ctx94.6% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.25 = median of cheapest 20%.

Price history

USD per 1M tokens · each step is a price change

Prices in USD / 1M tokens.

Other pricing

Offered byCache read
Darkbloom, Parasail$0.025
DeepInfra (fp8/flex)$0.08
CoreWeave$0.035
AkashML$0.05
DeepInfra$0.10
PrimeIntellect$0.099
DeepInfra (fp8/priority), SiliconFlow$0.15
AtlasCloud$0.25

Changes

About

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 2.5× the typical price. Context window: 256K tokens. Prices tracked since Oct 3, 2026.

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