This model was retired on 2026-04-06. The pricing below is the last-known rate, kept for migration reference.

Qwen3 32BDeprecated

AlibabaKnowledgeApr 2025

Tool useReasoningStructured output

Compare Qwen3 32B

Context

131K

Max output

131K

Serving providers

Cheapest input

$0.08 /1M

Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis

Speed & latency

Output speed

68 t/s

tokens / second

Time to first token

31.66s

latency

Headline indices

Intelligence Index

11.5

of 100

Coding Index

15.3

of 100

Agentic Index

1.8

of 100

Individual benchmarks · click a row for effort variants

Benchmark

Best score

Effort

Cost / task

CritPt

reasoning: true

—

EvalComputeProxy

281.5

reasoning: true

—

GDPval

275.0

reasoning: true

—

GPQA Diamond

67%

reasoning: true

—

Humanity's Last Exam

reasoning: true

—

IFBench

36%

reasoning: true

—

LiveCodeBench

55%

reasoning: true

—

Long-Context Reasoning

default

—

MMLU-Pro

80%

reasoning: true

—

Omniscience

-50.5

reasoning: true

—

SciCode

35%

reasoning: true

—

TerminalBench Hard

reasoning: true

—

TerminalBench v2.1

reasoning: true

—

τ-bench Banking

reasoning: true

—

τ²-bench

30%

reasoning: true

—

Pricing detail

cost beyond the standard rate · source: models.dev

Reasoning tokens

$8.40

per 1M · thinking output

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand

Serving provider

Input /1M

Output /1M

Endpoints

Ovhcloud

$0.08

$0.23

DeepInfra

$0.10

$0.28

Nebius

$0.10

$0.30

Amazon Bedrock

$0.15

$0.60

Groq

$0.29

$0.59

SambaNova

$0.40

$0.80

Fireworks AI

$0.90

Price history

input + output $/1M since we started tracking

Input Output

Input down 93% since first tracked

Cost calculator

estimate your monthly spend on this model

Input tokens / call

Output tokens / call

Calls / month

Serving provider

$34

estimated / month

Model IDs

copy the exact identifier for your platform

ovhcloud/Qwen3-32Bdeepinfra/Qwen/Qwen3-32Bnebius/Qwen/Qwen3-32Bqwen.qwen3-32b-v1:0groq/qwen/qwen3-32bsambanova/Qwen3-32Bfireworks_ai/accounts/fireworks/models/qwen3-32b

Frequently asked questions

Qwen3 32B pricing, context and availability

Is Qwen3 32B still available?

Qwen3 32B was retired on 2026-04-06. The pricing on this page is the last-known rate, kept for migration reference.

How much did Qwen3 32B cost?

Qwen3 32B's last-known pricing, before it was retired on 2026-04-06, was $0.08 per 1M input tokens and $0.23 per 1M output tokens.

What was the context window of Qwen3 32B?

Qwen3 32B had a 131K token context window and could return up to 131K output tokens.

What could Qwen3 32B do?

Qwen3 32B supported tool use, reasoning and structured output.

Other Alibaba models

compare pricing across the Alibaba lineup

QwQ 32B$0.15/1M · 7 providers Qwen3 235B A22b Instruct 2507$0.09/1M · 6 providers Qwen3 235B A22B Thinking 2507$0.11/1M · 5 providers Qwen3 Next 80B A3B Instruct$0.14/1M · 5 providers Qwen3 Next 80B A3B Thinking$0.14/1M · 5 providers Qwen2 5 Coder 32B Instruct$0.06/1M · 4 providers Qwen3 30B A3B$0.08/1M · 4 providers Qwen3 235B A22B$0.18/1M · 4 providers

Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI