impulse

Qwen3 30B A3B

Open weights

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks.

API id qwen3-30b-a3bReleased 28 Apr 2025 (Apr 2025)
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
129K
tokens
Max output
16K
tokens per reply
Hosts
11
11 listings
Released
Apr 2025
28 Apr 2025

Where to run it

11 hosts serve Qwen3 30B A3B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
qwen3-30b-a3b
-
qwen3-30b-a3b
-
Qwen CloudLab API
qwen3-30b-a3b
-
qwen3-30b-a3b
$0.09 / $0.20
qwen3-30b-a3b-fp8
$0.0509 / $0.335
GMI CloudInference
Qwen3-30B-A3B
$0.08 / $0.25
Qwen3-30B-A3B
$0.10 / $0.30
Novita AIInference
qwen3-30b-a3b-fp8
$0.09 / $0.45
ZeroGPUCloud
qwen3-30b-a3b-fp8
$0.10 / $0.45
DeepInfraInference
Qwen3-30B-A3B
$0.12 / $0.50
Fireworks AIInference
qwen3-30b-a3b
$0.15 / $0.60

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Apache-2.0
Runs in about 73.3 GB of GPU memory
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller Alibaba Qwen models

No similar Alibaba Qwen model keeps its key capabilities.

Other frontier labs

  • GPT-5.5 Pro
    OpenAI · on OpenAI
    $30.00 / $180.00
    Has every key capability
  • Claude Fable 5.2
    Anthropic · on Anthropic
    $8.00 / $40.00
    Has every key capability
  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability

Open-weight picks

  • Command A Plus
    Cohere · on AIHubMix
    $2.50 / $10.00
    Has every key capability
  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
  • Qwen3.8.2 4T A95B
    Alibaba Qwen · on DeepInfra
    $2.00 / $6.00
    Has every key capability
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability

Call it

Using Alibaba DashScope's API.

Python
from litellm import completion

response = completion(
    model="dashscope/qwen3-30b-a3b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3 30B A3B cost?

Its lowest listed price is at Pinstripes: $0.09 per million input tokens and $0.20 per million output tokens.

Which APIs offer Qwen3 30B A3B?

Qwen3 30B A3B runs on 11 APIs: Alibaba DashScope, Qianwen AI Platform, Qwen Cloud, Pinstripes, Cloudflare Workers AI, GMI Cloud, Nebius AI Studio, Novita AI, ZeroGPU and 2 more.

What is Qwen3 30B A3B's context window?

129K tokens, with up to 16K tokens in one reply.

Is Qwen3 30B A3B being retired?

No retirement date is scheduled for it on any API we track.

When was Qwen3 30B A3B released?

Alibaba Qwen released it on 28 Apr 2025.

What is Qwen3 30B A3B's API model id?

Use qwen3-30b-a3b with Alibaba DashScope. Other hosts use their own ids: qwen3-30b-a3b-fp8 on Cloudflare Workers AI, Qwen3-30B-A3B on GMI Cloud, Qwen3-30B-A3B on Nebius AI Studio, qwen3-30b-a3b-fp8 on Novita AI.

Sources

Raw catalog entry for qwen3-30b-a3b on Alibaba DashScope
{
  "litellm_provider": "dashscope",
  "max_input_tokens": 129024,
  "max_output_tokens": 16384,
  "mode": "chat",
  "source": "https://www.alibabacloud.com/help/en/model-studio/models",
  "supports_function_calling": true,
  "supports_reasoning": true,
  "supports_tool_choice": true
}