Qwen

Qwen3 32B API Pricing 2026

Compare pricing, benchmarks, and providers for Qwen3 32B. 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 32B was released on April 28, 2025. Pricing starts at $0.064 per million input tokens and $0.224 per million output tokens. The model supports a context window of up to 41K tokens. API access is available through Qwen.

Context Window
41K
tokens
Pricing
Input$0.064
Output$0.224
Cached$0.450
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
ReasoningToolsCaching

Qwen3 32B is priced at $0.064 per million input tokens and $0.224 per million output tokens. It has a context window of 40,960 tokens. It is available from 6 providers, with DeepInfra the cheapest at $0.064 per million input tokens (input prices range from $0.064 to $0.900). On benchmarks, Qwen3 32B scores Aider 40.0 (20th percentile). Over the past ~90 days its cheapest input price has fallen 20%, from $0.080 to $0.064 per million tokens.

Pricing Comparison

Compare Qwen3 32B 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
$0.064
$0.224
—
—
—
40,960
Try
$0.060
$0.120
—
—
—
262,144
Try
$0.060
$0.240
—
—
—
262,144
Try
$0.060
$0.300
—
—
—
-
Try
$0.060
$0.200
—
—
—
131,072
Try
$0.060
$0.060
—
—
—
131,072
Try
$0.060
$0.060
—
—
—
8,192
Try
IB
IBM
$0.060
$0.150
—
—
63.1
131,072
Try
$0.060
$0.180
—
—
—
131,072
Try
$0.060
$0.180
—
—
—
-
Try
$0.060
$0.400
—
—
—
202,752
Try

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

Compare Providers

Qwen3 32B is available from multiple providers with different pricing and availability.

6
Providers
$0.064
Cheapest Input/M
$0.224
Cheapest Output/M
DeepInfra
Best Price

Provider Pricing

6 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
DeepInfra
DeepInfra
Best Price
$0.064
$0.224
-
-
-
$0.080
$0.280
-
-
-
$0.140
$0.570
-
-
-
$0.200
$0.780
-
-
-
$0.290
$0.590
-
-
-
$0.900
$0.900
$0.450
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Qwen3 32B perform? Vote based on your experience.

Cost vs. Quality

Compare Qwen3 32B's benchmark performance against all models.

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

Try Qwen3 32B

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Qwen3 32B directly in your browser.

Open Playground

Frequently Asked Questions

Qwen3 32B costs $0.000064 per 1,000 input tokens and $0.000224 per 1,000 output tokens.
Qwen3 32B is available from 6 providers. DeepInfra offers the best price.
DeepInfra offers Qwen3 32B at $0.064 per million input tokens, the lowest of 6 providers (input prices range from $0.064 to $0.900 per million tokens).
Qwen3 32B scores Aider 40.0 (20th percentile). Only benchmarks with published data for this model are shown.
Yes. Over the past ~90 days, the cheapest input price for Qwen3 32B has dropped 20%, from $0.080 to $0.064 per million tokens.
We compare Qwen3 32B 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 →