impulse

QwQ 32B

Open weights
API id QwQ-32B
Input / 1M
$0.18
at Nscale
Output / 1M
$0.20
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$0.18$0.20

What it costs a month

At Nscale list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$69.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$93.60
  • Coding agent1,000 requests a day, 40K in / 2K out$228
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$480
Use your own numbers

Where to run it

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

HostIn / out per 1M
NscaleInference
QwQ-32B
$0.18 / $0.20
HyperbolicInference
QwQ-32B
$0.20 / $0.20
+8% vs headline
DeepInfraInference
QwQ-32B
$0.15 / $0.40
+15% vs headline
QwQ-32B
$0.15 / $0.45
+22% vs headline
$0.66 / $1.00
+303% vs headline
Fireworks AIInference
qwq-32b
$0.90 / $0.90
+386% 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 Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Qwen3.8 Flash
    Alibaba Qwen · on AIHubMix
    $0.113 / $0.38
    Has every key capability
    3% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    3% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    14% less
  • Ministral 8B 2512
    Mistral AI · on Mistral AI
    $0.15 / $0.15
    Has every key capability
    19% less

Benchmarks

Scores published on the model card.

  • Aider Polyglot20.9%

Call it

Using Nscale's API.

Python
from litellm import completion

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

Quick answers

How much does QwQ 32B cost?

On Nscale, QwQ 32B costs $0.18 per million input tokens and $0.20 per million output tokens.

Which APIs offer QwQ 32B?

QwQ 32B runs on 6 APIs: Nscale, Hyperbolic, DeepInfra, Nebius AI Studio, Cloudflare Workers AI and Fireworks AI.

What is QwQ 32B's context window?

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

Is QwQ 32B being retired?

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

What are cheaper alternatives to QwQ 32B?

Models that cost less and keep most of what it can do: Qwen3.8 Flash on AIHubMix (3% less). Savings are on a mix of 3 input tokens to 1 output token.

What is QwQ 32B's API model id?

Use QwQ-32B with Nscale. Other hosts use their own ids: qwq-32b on Cloudflare Workers AI, qwq-32b on Fireworks AI.

Sources

Raw catalog entry for QwQ-32B on Nscale
{
  "input_cost_per_token": 1.8e-7,
  "litellm_provider": "nscale",
  "mode": "chat",
  "output_cost_per_token": 2e-7,
  "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models"
}