Skip to main content

QwQ 32B

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

Input / output price
$0.66 / $1.00 per 1M
Context
24K tokens
Released
Mar 5, 2025
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "qwq-32b".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
ConcentrateRetiringconcentrate/qwq-32b
$0.66/M$1.00/M

Pricing

USD per 1M tokens on Concentrate, after gateway discounts.

Input
$0.66 per 1M
Output
$1.00 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$0.66/MConcentrate

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

1.9tokens/sacross providers

Faster than 1% of the other 599 models on the gateway

Response latency

Lower is better

0.5sacross providers

Faster than 83% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 5 published scores from 4 sources, each linked to where it was published.

15.0/ 100

Respan Index#160 of 176

176 ranked models. The shaded band is this model's 95% interval, 10.6 to 25.9. GPT-4.1 mini and Granite 4.2 8B fall inside it, so the gap is within the margin of error.
QwQ 32B by category: Coding 3.1 (estimated), Agents 12.0 (estimated), Reasoning 20.6, Knowledge & language 5.0, Human preference 36.9
  1. 160QwQ-32B15.0
  2. 159GPT-4.1 mini15.3
  3. 161Granite 4.2 8B14.9

Published scores

BenchmarkScore
GPQA DiamondEpoch AI65.3%

Compare QwQ 32B: QwQ-32B vs Qwen3.8-Max, QwQ-32B vs Qwen3.8-Flash-Next, QwQ-32B vs Qwen3.7-Max, QwQ-32B vs Qwen3.8 27B, QwQ-32B vs Qwen3.6-Max-Preview, QwQ-32B vs Qwen3.7-Plus

Apps

Use QwQ 32B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

QwQ 32B FAQ

Short answers, built from the data on this page.

QwQ 32B is a model from Qwen, released on Mar 5, 2025. QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

On the Respan gateway, QwQ 32B costs $0.66 per 1M input tokens and $1.00 per 1M output tokens on Concentrate, after gateway discounts.

QwQ 32B is served by Concentrate.

QwQ 32B accepts up to 24K tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwq-32b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

QwQ 32B scores 15.0 out of 100 on the Respan Index v1.1, ranking #160 of 176 models. By category: Coding 3.1 (estimated), Agents 12.0 (estimated), Reasoning 20.6, Knowledge & language 5.0, and Human preference 36.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

QwQ 32B has 5 published benchmark scores, including GPQA Diamond 65.3%, AIME 2025 65.8%, and MMLU-Pro 69.1%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.