Qwen3-30B-A3B-Thinking-2507 on FlexAI

Qwen3 · Alibaba

Serverless
Open Source

Last refreshed 2026-11-18. Next refresh: weekly.

Why use Qwen3-30B-A3B-Thinking-2507 on FlexAI?

FlexAI offers Qwen3-30B-A3B-Thinking-2507 with pay-as-you-go pricing at $0.20/1M input tokens. FlexAI operates Token Factory, an OpenAI-compatible inference API for open models, plus dedicated GPU endpoints, fine-tuning, training, and private-cloud AI Factory deployments.

Input / 1M
$0.20
Output / 1M
$2.40
Cache
read $0.030
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: Qwen3-30B-A3B-Thinking-2507-FP8
Model ID
Qwen3-30B-A3B-Thinking-2507-FP8

Request example

Curated snippets for this provider are not sourced yet. Use FlexAI documentation with model ID Qwen3-30B-A3B-Thinking-2507-FP8.

Gotchas

  • Use provider model ID "Qwen3-30B-A3B-Thinking-2507-FP8", not the LLMReference slug "qwen3-30b-a3b-thinking-2507".

Pricing

TypePrice (per 1M)
Input tokens$0.20
Output tokens$2.40

Capabilities

ReasoningJSON / Tool use

About Qwen3-30B-A3B-Thinking-2507

Qwen3-30B-A3B-Thinking-2507 is Alibaba Qwen’s thinking-mode mixture-of-experts model with 30.5 billion total parameters and 3.3 billion activated. It runs only in thinking mode, has a native context of 262,144 tokens, and publishes Apache-2.0 open weights on Hugging Face.

Get Started

Model Specs

Released2025-07-29
Parameters30.5B (3.3B active)
Context256K
ArchitectureMixture of Experts

Provider

FlexAI

FlexAI Systems Inc

All models on FlexAI →