Skip to content

Qwen3 32B

Best price · blended / 1M

$0.104

at DeepInfra

Input / output
$0.064 / $0.224
Providers
3
Spread
2.4×
7 days
−20.0%
30 days
−20.0%
Context
128K
Prices per 1M tokens, blended: DeepInfra (fp8/flex) $0.104, DeepInfra $0.13, DeepInfra (fp8/priority) $0.195, Tenstorrent $0.205, SiliconFlow $0.248.

Providers

  • DeepInfraCheapest
    fp8/flex
    $0.104
    $0.064 in · $0.224 out
    ref vs ref
    40K ctx97.5% uptimefp8
  • $0.13
    $0.08 in · $0.28 out
    +25% vs ref
    40K ctx99.7% uptimefp8
  • fp8/priority
    $0.195
    $0.12 in · $0.42 out
    +88% vs ref
    40K ctx99.9% uptimefp8
  • $0.205
    $0.14 in · $0.40 out
    +97% vs ref
    20K ctx91.8% uptimefp8
  • $0.248
    $0.14 in · $0.57 out
    +138% vs ref
    128K ctx81.4% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.104 = 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
Tenstorrent$0.09

Changes

About

The cheapest provider for Qwen3 32B is DeepInfra at $0.104 per 1M tokens (blended), charging $0.064 per 1M input and $0.224 per 1M output tokens. 3 providers serve it; the most expensive charges 2.4× the typical price. Its best price fell 20.0% over the last 30 days. Context window: 128K tokens. Prices tracked since Oct 3, 2026.

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...
Released
Apr 28, 2025
First tracked
Oct 3, 2026
Canonical slug
qwen/qwen3-32b-04-28
Weights
Qwen/Qwen3-32B