Appndo
All models

Qwen3 235B A22B Instruct 2507

QwenOpen weights262K contextTool calling

LMArena score 1419 · #121 overall · #110 in coding (2026-10-13)

Lowest price, from DeepInfra

Pricing page

Per million tokens

Input
$0.09
Output
$0.55
Cached input
—
Batch input / output
—
  • Up to 262K 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 DeepInfra: $2.00 a month.

Where to buy it (8)

Sorted by your monthly estimate. Prices per million tokens.

  • DeepInfraCheapest

    Input / output
    $0.09 / $0.55
    Context
    262K
    Per month
    $2.00

    deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507

  • Novita AI

    Input / output
    $0.09 / $0.58
    Context
    131K
    Per month
    $2.06

    novita/qwen/qwen3-235b-a22b-instruct-2507

  • Nebius

    Input / output
    $0.20 / $0.60
    Context
    262K
    Per month
    $3.20

    nebius/Qwen/Qwen3-235B-A22B-Instruct-2507

  • Fireworks AI

    Input / output
    $0.22 / $0.88
    Context
    262K
    Per month
    $3.96

    fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507

  • Google Vertex AI

    Input / output
    $0.22 / $0.88
    Context
    262K
    Per month
    $3.96

    vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas

  • Replicate

    Input / output
    $0.264 / $1.06
    Context
    —
    Per month
    $4.76

    replicate/qwen/qwen3-235b-a22b-instruct-2507

  • Scaleway

    Input / output
    $0.75 / $2.25
    Context
    256K
    Per month
    $12.00

    scaleway/qwen/qwen3-235b-a22b-instruct-2507

  • Crusoe

    Input / output
    $3.00 / $3.00
    Context
    262K
    Per month
    $36.00

    crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507

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

Similar models