DeepSeekReleased on Jan 20, 2025

DeepSeek R1 Distill Qwen 32B: Benchmarks, Pricing & Size

DeepSeek R1 Distill Qwen 32B is a language model from DeepSeek, released in January 2025.

DeepSeek-R1 is the first-generation reasoning model built atop DeepSeek-V3 (671B total parameters, 37B activated per token). It incorporates large-scale reinforcement learning (RL) to enhance its chain-of-thought and reasoning

Input
Text
Output
Text
Speed
Latency p95650ms
Throughput P9537.0char/s
Cost
$0.13/ 1M · 8:1 in:out
$0.12 in · $0.18 out

DeepSeek R1 Distill Qwen 32B pricing

Providers

DeepSeek R1 Distill Qwen 32B starts at $0.120 per million input tokens and $0.180 per million output tokens via DeepInfra.

ProviderInput $/MOutput $/MMax InputMax OutputLatency p95 sThroughput P95QuantInputOutput
DeepInfra logoDeepInfra
$0.120$0.180128.0K128.0K
0.65
37 c/s
—

DeepSeek R1 Distill Qwen 32B model size

DeepSeek R1 Distill Qwen 32B has 32.8 billion parameters and was trained on 14.8 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens
32.8B
14.8Ttokens
451× tokens-to-params ratio
Large (30–80B)
32.8B
1B7B70B405B

DeepSeek R1 Distill Qwen 32B API

API access coming soon

DeepSeek R1 Distill Qwen 32B will be available through our gateway shortly.

DeepSeek R1 Distill Qwen 32B examples

Recent arena outputs from DeepSeek R1 Distill Qwen 32B, picked from the highest-ranked matchups.

DeepSeek R1 Distill Qwen 32B license

DeepSeek R1 Distill Qwen 32B is released under the MIT license, which permits commercial use, has 32.8B parameters.

License
MIT
Commercial use allowed
Parameters
32.8B

MIT License - allows commercial use

FAQ

Common questions about DeepSeek R1 Distill Qwen 32B.

When was DeepSeek R1 Distill Qwen 32B released?

DeepSeek R1 Distill Qwen 32B was released on January 20, 2025 by DeepSeek. This is the official DeepSeek R1 Distill Qwen 32B release date tracked on LLM Stats.

Is DeepSeek R1 Distill Qwen 32B available via API?

Yes, DeepSeek R1 Distill Qwen 32B is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

How big is DeepSeek R1 Distill Qwen 32B?

DeepSeek R1 Distill Qwen 32B has 32.8 billion parameters. It was trained on 14.8 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created DeepSeek R1 Distill Qwen 32B?

DeepSeek R1 Distill Qwen 32B was created by DeepSeek.

What is the license for DeepSeek R1 Distill Qwen 32B?

DeepSeek R1 Distill Qwen 32B is released under the MIT license. This is an open-source / open-weight license that permits self-hosting.

Where can I use DeepSeek R1 Distill Qwen 32B?

DeepSeek R1 Distill Qwen 32B is available through 1 provider including DeepInfra.

Where is the DeepSeek R1 Distill Qwen 32B paper or technical report?

DeepSeek R1 Distill Qwen 32B has a paper or technical report available at https://arxiv.org/pdf/2501.12948. Use that source for architecture, training, release and evaluation details.