This model was retired on 2025-06-25. The pricing below is the last-known rate, kept for migration reference.

QwQ 32BDeprecated

AlibabaKnowledgeApr 2024
Tool useReasoning
Context
131K
Max output
131K
Serving providers
7
Cheapest input
$0.15 /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
31 t/s
tokens / second
Time to first token
2.13s
latency
Headline indices
Intelligence Index
13.4
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
EvalComputeProxy69.5default
GPQA Diamond59%default
Humanity's Last Exam8%default
IFBench39%default
LiveCodeBench63%default
Long-Context Reasoning25%default
MMLU-Pro76%default
SciCode36%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
DeepInfra$0.15$0.401
Nebius$0.15$0.451
Nscale$0.18$0.201
Hyperbolic$0.20$0.201
SambaNova$0.50$1.001
Cloudflare$0.66$1.001
Fireworks AI$0.90$0.901

Price history

input + output $/1M since we started tracking
Input Output
Input down 58% since first tracked
$0.000$0.050$0.100$0.150$0.200May 8Aug 22Sep 10Jun 24$0.150$0.075

Cost calculator

estimate your monthly spend on this model
$62
estimated / month

Model IDs

copy the exact identifier for your platform
deepinfra/Qwen/QwQ-32Bnebius/Qwen/QwQ-32Bnscale/Qwen/QwQ-32Bhyperbolic/Qwen/QwQ-32Bsambanova/QwQ-32Bcloudflare/@cf/qwen/qwq-32bfireworks_ai/accounts/fireworks/models/qwq-32b

Frequently asked questions

QwQ 32B pricing, context and availability

Is QwQ 32B still available?

QwQ 32B was retired on 2025-06-25. The pricing on this page is the last-known rate, kept for migration reference.

How much did QwQ 32B cost?

QwQ 32B's last-known pricing, before it was retired on 2025-06-25, was $0.15 per 1M input tokens and $0.20 per 1M output tokens.

What was the context window of QwQ 32B?

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

What could QwQ 32B do?

QwQ 32B supported tool use and reasoning.

Other Alibaba models

compare pricing across the Alibaba lineup
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