impulse

DeepSeek R1 Distill Qwen 32B

Open weights
API id DeepSeek-R1-Distill-Qwen-32B
Input / 1M
$0.15
at Nscale
Output / 1M
$0.15
at Nscale
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
6
6 listings
Released
-
date not published

Pricing

List prices at Nscale, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.15$0.15

What it costs a month

At Nscale list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$56.25
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$77.40
  • Coding agent1,000 requests a day, 40K in / 2K out$189
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$396
Use your own numbers

Where to run it

6 hosts serve DeepSeek R1 Distill Qwen 32B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
NscaleInference
DeepSeek-R1-Distill-Qwen-32B
$0.15 / $0.15
DeepInfraInference
DeepSeek-R1-Distill-Qwen-32B
$0.27 / $0.27
+80% vs headline
Novita AIInference
deepseek-r1-distill-qwen-32b
$0.30 / $0.30
+100% vs headline
GMI CloudInference
DeepSeek-R1-Distill-Qwen-32B
$0.50 / $0.90
+300% vs headline
Fireworks AIInference
deepseek-r1-distill-qwen-32b
$0.90 / $0.90
+500% vs headline
deepseek-r1-distill-qwen-32b
$0.497 / $4.88
+962% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Apache-2.0
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Nscale.

Smaller DeepSeek models

No cheaper DeepSeek model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • MiMo V2.5
    Xiaomi · on GMI Cloud
    $0.119 / $0.238
    Has every key capability
    1% less
  • DeepSeek V4.1 Flash
    DeepSeek · on Sail
    $0.09 / $0.30
    Has every key capability
    5% less
  • Qwen3.6 35B A3B
    Alibaba Qwen · on Sail
    $0.05 / $0.40
    Has every key capability
    8% less
  • Gemma 4 26B A4B IT
    Google · on DeepInfra
    $0.07 / $0.34
    Has every key capability
    8% less

Call it

Using Nscale's API.

Python
from litellm import completion

response = completion(
    model="nscale/DeepSeek-R1-Distill-Qwen-32B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does DeepSeek R1 Distill Qwen 32B cost?

On Nscale, DeepSeek R1 Distill Qwen 32B costs $0.15 per million input tokens and $0.15 per million output tokens.

Which APIs offer DeepSeek R1 Distill Qwen 32B?

DeepSeek R1 Distill Qwen 32B runs on 6 APIs: Nscale, DeepInfra, Novita AI, GMI Cloud, Fireworks AI and Cloudflare Workers AI.

What is DeepSeek R1 Distill Qwen 32B's context window?

131K tokens, with up to 131K tokens in one reply.

Is DeepSeek R1 Distill Qwen 32B being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to DeepSeek R1 Distill Qwen 32B?

Models that cost less and keep most of what it can do: MiMo V2.5 on GMI Cloud (1% less). Savings are on a mix of 3 input tokens to 1 output token.

What is DeepSeek R1 Distill Qwen 32B's API model id?

Use DeepSeek-R1-Distill-Qwen-32B with Nscale. Other hosts use their own ids: deepseek-r1-distill-qwen-32b on Novita AI, deepseek-r1-distill-qwen-32b on Fireworks AI, deepseek-r1-distill-qwen-32b on Cloudflare Workers AI.

Sources

Raw catalog entry for DeepSeek-R1-Distill-Qwen-32B on Nscale
{
  "input_cost_per_token": 1.5e-7,
  "litellm_provider": "nscale",
  "metadata": {
    "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output."
  },
  "mode": "chat",
  "output_cost_per_token": 1.5e-7,
  "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
}