Price Per TokenPrice Per Token
Qwen

Qwen3 30B A3B Thinking 2507 API Pricing 2026

Compare pricing, benchmarks, and providers for Qwen3 30B A3B Thinking 2507. Find the best value for your use case.

Get our weekly newsletter on pricing changes, new releases, and tools.

No bots, no big tech influence — join the new community for AI devs
8 Ways to Use Fewer Tokens
Last updated: May 1, 2026 at 08:30 AM

Overview

Qwen3 30B A3B Thinking 2507 was released on August 28, 2025. Pricing starts at $0.080 per million input tokens and $0.300 per million output tokens. The model supports a context window of up to 33K tokens. API access is available through Qwen.

Context Window
33K
tokens
Pricing
Input$0.080
Output$0.300
Cached$0.080
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
ReasoningToolsCaching

Pricing Comparison

Compare Qwen3 30B A3B Thinking 2507 with 0 similar models by price.

Current Pricing (per 1M tokens)

1 models

Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.080
$0.300
32,768
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Qwen3 30B A3B Thinking 2507 is available from multiple providers with different pricing and availability.

No multi-provider data available for this model

This model may only be available from a single provider

Community Rankings

How does Qwen3 30B A3B Thinking 2507 perform? Vote based on your experience.

Cost vs. Quality

Compare Qwen3 30B A3B Thinking 2507's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Qwen3 30B A3B Thinking 2507 (Thinking)
Other models

Try Qwen3 30B A3B Thinking 2507

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Qwen3 30B A3B Thinking 2507 directly in your browser.

Open Playground

Frequently Asked Questions

Qwen3 30B A3B Thinking 2507 costs $0.000080 per 1,000 input tokens and $0.000300 per 1,000 output tokens.

All Qwen Models

See pricing for all Qwen models.

View all Qwen models →