Appndo
All models

Qwen3.5 397B A17B

QwenOpen weights262K contextReasoningTool callingVisionWeb search

LMArena score 1438 · #80 overall · #80 in coding (2026-10-13)

Lowest price, from AIHubMix

Pricing page

Per million tokens

Input
$0.1644
Output
$0.9864
Cached input
—
Batch input / output
—
  • Up to 66K 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 AIHubMix: $3.62 a month.

Where to buy it (5)

Sorted by your monthly estimate. Prices per million tokens.

  • AIHubMixCheapest

    Input / output
    $0.1644 / $0.9864
    Context
    262K
    Per month
    $3.62

    aihubmix/qwen3.5-397b-a17b

  • DeepInfra

    Input / output
    $0.45 / $3.00
    Context
    262K
    Per month
    $10.50

    deepinfra/Qwen/Qwen3.5-397B-A17B

  • Nebius

    Input / output
    $0.60 / $3.60
    Context
    262K
    Per month
    $13.20

    nebius/Qwen/Qwen3.5-397B-A17B

  • Novita AI

    Input / output
    $0.60 / $3.60
    Context
    262K
    Per month
    $13.20

    novita/qwen/qwen3.5-397b-a17b

  • Scaleway

    Input / output
    $0.60 / $3.60
    Context
    256K
    Per month
    $13.20

    scaleway/qwen/qwen3.5-397b-a17b

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

Similar models