Qwen

Qwen3 VL 235B A22B Thinking API Pricing 2026

Compare pricing, benchmarks, and providers for Qwen3 VL 235B A22B Thinking. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Qwen3 VL 235B A22B Thinking was released on September 23, 2025. Pricing starts at $0.900 per million input tokens and $0.900 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through Qwen.

Context Window
131K
tokens
Pricing
Input$0.900
Output$0.900
Cached$0.450
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
VisionReasoningTools

Qwen3 VL 235B A22B Thinking is priced at $0.900 per million input tokens and $0.900 per million output tokens. It has a context window of 131,072 tokens. It is available from 1 provider, with Fireworks the cheapest at $0.900 per million input tokens. Over the past ~90 days its cheapest input price has risen 125%, from $0.400 to $0.900 per million tokens.

Pricing Comparison

Compare Qwen3 VL 235B A22B Thinking with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.900
$0.900
—
—
—
131,072
Try
$0.900
$0.900
—
—
—
8,192
Try
$0.900
$0.900
—
—
—
120,000
Try
$0.900
$0.900
—
—
—
16,384
Try
$0.900
$0.900
—
—
—
4,096
Try
$0.900
$0.900
—
—
—
131,072
Try
$0.900
$0.900
—
—
—
131,072
Try
$0.900
$0.900
—
—
—
128,000
Try
$0.900
$0.900
—
2.2
1.3
32,768
Try
$0.900
$0.900
—
—
—
128,000
Try
$0.900
$0.900
—
—
—
131,072
Try

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

Compare Providers

Qwen3 VL 235B A22B Thinking is available from multiple providers with different pricing and availability.

1
Providers
$0.900
Cheapest Input/M
$0.900
Cheapest Output/M
Fireworks
Best Price

Provider Pricing

1 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
Fireworks
Fireworks
Best Price
$0.900
$0.900
$0.450
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Qwen3 VL 235B A22B Thinking perform? Vote based on your experience.

Cost vs. Quality

Compare Qwen3 VL 235B A22B Thinking's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try Qwen3 VL 235B A22B Thinking

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Qwen3 VL 235B A22B Thinking directly in your browser.

Open Playground

Frequently Asked Questions

Qwen3 VL 235B A22B Thinking costs $0.000900 per 1,000 input tokens and $0.000900 per 1,000 output tokens.
Qwen3 VL 235B A22B Thinking is available from 1 provider. Fireworks offers the best price.
Fireworks offers Qwen3 VL 235B A22B Thinking at $0.900 per million input tokens.
Yes. Over the past ~90 days, the cheapest input price for Qwen3 VL 235B A22B Thinking has increased 125%, from $0.400 to $0.900 per million tokens.
We compare Qwen3 VL 235B A22B Thinking with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Qwen Models

See pricing for all Qwen models.

View all Qwen models →