Appndo
All models

Qwen3 Coder 480B A35B Instruct

QwenOpen weights262K contextTool callingReasoning

LMArena score 1357 · #199 overall · #159 in coding (2026-10-13)

Lowest price, from Google Vertex AI

Pricing page

Per million tokens

Input
$0.22
Output
$1.80
Cached input
$0.022
Batch input / output
$0.11 / $0.90
  • Up to 33K 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 Google Vertex AI: $5.80 a month.

Where to buy it (6)

Sorted by your monthly estimate. Prices per million tokens.

  • Google Vertex AICheapest

    Input / output
    $0.22 / $1.80
    Context
    262K
    Per month
    $5.80

    vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas

  • Novita AI

    Input / output
    $0.38 / $1.55
    Context
    262K
    Per month
    $6.90

    novita/qwen/qwen3-coder-480b-a35b-instruct

  • DeepInfra

    Input / output
    $0.40 / $1.60
    Context
    262K
    Per month
    $7.20

    deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct

  • Amazon Bedrock Converse

    Input / output
    $0.45 / $1.80
    Context
    131K
    Per month
    $8.10

    qwen.qwen3-coder-480b-a35b-v1:0

  • Amazon Bedrock Mantle

    Input / output
    $0.45 / $1.80
    Context
    128K
    Per month
    $8.10

    bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct

  • Fireworks AI

    Input / output
    $0.45 / $1.80
    Context
    262K
    Per month
    $8.10

    fireworks_ai/accounts/fireworks/models/qwen3-coder-480b-a35b-instruct

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

Similar models