QwQ-32B-Preview: API Pricing, Context Window & Benchmarks
QwQ-32B-Preview is a language model from Qwen, released in November 2024.
An experimental research model focused on advancing AI reasoning capabilities, particularly excelling in mathematics and programming. Features deep introspection and self-questioning abilities while having some limitations in language
QwQ-32B-Preview benchmarks
Rankings
Quality Tracker
QwQ-32B-Preview Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sun Jul 26 2026QwQ-32B-Preview pricing
Providers
QwQ-32B-Preview starts at $0.150 per million input tokens and $0.600 per million output tokens via DeepInfra. See all 4 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Output $/M | Context in / out | TTFT p50 / p95 s | Output avg / p5 c/s | Success 7d | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.150 | $0.600 | 32.8K/32.8K | —/0.44 | 76/— | — | / |
 Hyperbolic | $0.200 | $0.200 | 32.8K/32.8K | —/1.05 | 32/— | — | / |
 Fireworks | $0.890 | $0.890 | 32.8K/32.8K | —/0.53 | 99/— | — | / |
 Together | $1.20 | $1.20 | 32.8K/32.8K | —/0.74 | 62/— | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.
QwQ-32B-Preview model size
QwQ-32B-Preview has 32.5 billion parameters. See how it compares to other models in the same parameter range.
QwQ-32B-Preview context window
Input and output token limits for QwQ-32B-Preview, plus how it ranks on long-context understanding.
QwQ-32B-Preview API
Available from the model provider
QwQ-32B-Preview has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationQwQ-32B-Preview latency
QwQ-32B-Preview time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
QwQ-32B-Preview examples
Recent arena outputs from QwQ-32B-Preview, picked from the highest-ranked matchups.
QwQ-32B-Preview license
QwQ-32B-Preview is released under the Apache 2.0 license, which permits commercial use, has 32.5B parameters, has a knowledge cutoff of November 2024.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 32.5B
- Knowledge cutoff
- November 2024
Apache License 2.0 - allows commercial use
QwQ-32B-Preview resources
Official sources for QwQ-32B-Preview: api documentation, official playground, paper or system card, official launch post, source repository.
QwQ-32B-Preview vs other models
The most-compared alternatives to QwQ-32B-Preview are DeepSeek R1 Zero, DeepSeek R1 Distill Llama 70B, QwQ-32B. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like QwQ-32B-Preview
Models ranked just above and below QwQ-32B-Preview by LLM Stats score.
FAQ
Common questions about QwQ-32B-Preview.