WIDEAREAINTELLIGENCE
← model directory

cloudflare

deepseek-ai/deepseek-r1-distill-qwen-32b

cloudflare/deepseek-ai/deepseek-r1-distill-qwen-32b

↓ runs free on your own hardware⚙ tool calling

DeepSeek-R1-Distill-Qwen-32B is a model distilled from DeepSeek-R1 based on Qwen2.5. It outperforms OpenAI-o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.

specs & pricing
Type
text
Provider
cloudflare
Model ID
cloudflare/deepseek-ai/deepseek-r1-distill-qwen-32b
Capabilities
tools
Context window
80K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.55 / 1M tokens
Output price
$5.37 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

What it costs to run

cloud · 1M in + 1M out

$5.92

$0.55 for a million input tokens plus $5.37 for a million output tokens, billed from credits only when a request fails over to the cloud.

your hardware

$0 / token

Served from a workstation or on-prem server you own, there is no per-token fee — the marginal cost is power.

AI cost calculator →GPU power cost →

Run it on your own hardware

Estimated GPU memory for deepseek-ai/deepseek-r1-distill-qwen-32b (33B parameters), including the KV cache for a 8,192-token context.

Q4_K_M
~21.4 GBfits a 24 GB card
Q8_0
~35.1 GBfits a 48 GB card
FP16 / BF16
~63.8 GBfits a 80 GB card

Install the agent on the machine and it dials out to the gateway over a single WebSocket — no port forwarding or inbound firewall rules. Requests for this model go to your node first and fail over to the cloud only when it can't serve.

VRAM calculator →Which GPU do I need? →

/// initialize

Call deepseek-ai/deepseek-r1-distill-qwen-32b through one OpenAI-compatible endpoint.

Serve it from hardware you own, with cloud failover when your nodes are busy or offline.

Run it on your own hardwareTry it in chat

no credit card · 2 nodes free · openai-compatible

Frequently asked questions

What is the context window of deepseek-ai/deepseek-r1-distill-qwen-32b?
deepseek-ai/deepseek-r1-distill-qwen-32b accepts up to 80,000 tokens (80K) of context per request.
How much does deepseek-ai/deepseek-r1-distill-qwen-32b cost per million tokens?
Through Wide Area Intelligence, deepseek-ai/deepseek-r1-distill-qwen-32b costs $0.55 per 1M input tokens and $5.37 per 1M output tokens when served from the cloud, billed from prepaid credits. A workload of 1M input plus 1M output tokens costs $5.92.
Can I run deepseek-ai/deepseek-r1-distill-qwen-32b on my own hardware?
Yes — deepseek-ai/deepseek-r1-distill-qwen-32b is an open-weight model you can run on a workstation or on-prem server you own. At Q4_K_M it needs roughly 21.4 GB of GPU memory with an 8,192-token context — it fits a single 24 GB card. Wide Area Intelligence routes requests to your own nodes first and fails over to the cloud only when they can't serve.

More from cloudflare

← browse all models