Appndo
All models

Qwen 3 32B

QwenOpen weights131K contextReasoningTool calling

LMArena score 1340 · #212 overall · #221 in coding (2026-10-13)

Lowest price, from Ovhcloud

Pricing page

Per million tokens

Input
$0.08
Output
$0.23
Cached input
—
Batch input / output
—
  • Up to 32K output tokens per request.

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From Ovhcloud: $1.26 a month.

Where to buy it (8)

Sorted by your monthly estimate. Prices per million tokens.

  • OvhcloudCheapest

    Input / output
    $0.08 / $0.23
    Context
    32K
    Per month
    $1.26

    ovhcloud/Qwen3-32B

  • DeepInfra

    Input / output
    $0.08 / $0.28
    Context
    41K
    Per month
    $1.36

    deepinfra/Qwen/Qwen3-32B

  • Nebius

    Input / output
    $0.10 / $0.30
    Context
    41K
    Per month
    $1.60

    nebius/Qwen/Qwen3-32B

  • Vercel AI Gateway

    Input / output
    $0.10 / $0.30
    Context
    41K
    Per month
    $1.60

    vercel_ai_gateway/alibaba/qwen-3-32b

  • Amazon Bedrock Converse

    Input / output
    $0.15 / $0.60
    Context
    33K
    Per month
    $2.70

    qwen.qwen3-32b-v1:0

  • Amazon Bedrock Mantle

    Input / output
    $0.15 / $0.60
    Context
    32K
    Per month
    $2.70

    bedrock_mantle/qwen.qwen3-32b

  • Cerebras

    Input / output
    $0.40 / $0.80
    Context
    128K
    Per month
    $5.60

    cerebras/qwen-3-32b

  • Fireworks AI

    Input / output
    $0.90 / $0.90
    Context
    131K
    Per month
    $10.80

    fireworks_ai/accounts/fireworks/models/qwen3-32b

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Reasoning, Tool calling.

Similar models