DeepSeek R1 Distill Qwen 32B
DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. 128,000 token context window. Includes independent benchmarks from Artificial Analysis.
- Input / output price
- $0.497 / $4.881 per 1M
- Context
- 80K tokens
- Released
- Jan 20, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
ConcentrateRetiring concentrate/deepseek-r1-distill-32b | $0.497/M | $4.881/M |
Pricing
USD per 1M tokens on Concentrate, after gateway discounts.
- Input
- $0.497 per 1M
- Output
- $4.881 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
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 better2.0tokens/sacross providers
Response latency
Lower is better0.5sacross providers
Benchmarks
7 published scores from 3 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBenchhuggingface.co | 57.2% | huggingface.co | Jan 20, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 64.1% | Epoch AI | Nov 17, 2026 |
| GPQA Diamondhuggingface.co | 62.1% | huggingface.co | Jan 20, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH-500huggingface.co | 94.3% | huggingface.co | Jan 20, 2025 |
| AIME 2024huggingface.co | 72.6% | huggingface.co | Jan 20, 2025 |
| OTIS Mock AIME 2024-2025Epoch AI | 55.6% | Epoch AI | Nov 17, 2026 |
Apps
Use DeepSeek R1 Distill Qwen 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.
DeepSeek R1 Distill Qwen 32B FAQ
Short answers, built from the data on this page.
DeepSeek R1 Distill Qwen 32B is a model from Deepseek, released on Jan 20, 2025. DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. 128,000 token context window. Includes independent benchmarks from Artificial Analysis.
On the Respan gateway, DeepSeek R1 Distill Qwen 32B costs $0.497 per 1M input tokens and $4.881 per 1M output tokens on Concentrate, after gateway discounts.
DeepSeek R1 Distill Qwen 32B is served by Concentrate.
DeepSeek R1 Distill Qwen 32B accepts up to 80K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "deepseek-r1-distill-qwen-32b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
DeepSeek R1 Distill Qwen 32B has 7 published benchmark scores, including LiveCodeBench 57.2%, BALROG 19.5%, and GPQA Diamond 64.1%. 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.