Qwen

Qwen3 30B A3B Instruct 2507

qwen/qwen3-30b-a3b-instruct-2507

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Qwen3 30B A3B Instruct 2507

open weights tools

Qwen qwen/qwen3-30b-a3b-instruct-2507

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

Input $/1M: $0.05
Output $/1M: $0.19
Context: 262K
Max output: 32K
Released: Jul 29, 2025
Modalities: text

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Qwen3 30B A3B Instruct 2507
targets:
  - id: qwen3-30b-a3b-instruct-2507
    kind: llm
    name: Qwen3 30B A3B Instruct 2507
    metadata:
      model: qwen/qwen3-30b-a3b-instruct-2507          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 262144
    cost:
      usd_per_1k_tokens: 0.000121

Price among Qwen models

Input list price per million tokens; Qwen3 30B A3B Instruct 2507 is the 2nd cheapest of 13 listed.

1
Qwen3.7 Flash
$0.03
2
Qwen3 30B A3B Instruct 2507
$0.05
3
Qwen3.6 35B A3B
$0.10
4
Qwen3.8 Flash
$0.15
5
Qwen3.6 Flash
$0.19
6
Qwen3.5 Plus 2026-04-20
$0.30
7
Qwen3.7 Plus
$0.32
8
Qwen3.8 27B
$0.42
9
Qwen3.6 Max Preview
$1.03
10
Qwen3.7 Max
$1.48
11
Qwen3.8 Max (0902)
$2.00
12
Qwen3.8 2.4T A95B
$2.00

More from Qwen

Other models by the same vendor in the catalogue.