impulse

Qwen3 32B

Open weights

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue.

API id qwen3-32b-fp8Released 28 Apr 2025 (Apr 2025)
Input / 1M
$0.05
at Lambda AI
Output / 1M
$0.10
at Lambda AI
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
8
9 listings
Released
Apr 2025
28 Apr 2025

Pricing

List prices at Lambda AI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.05$0.10

What it costs a month

At Lambda AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$22.50
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$27.60
  • Coding agent1,000 requests a day, 40K in / 2K out$66.00
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$144
Use your own numbers

Where to run it

8 hosts serve Qwen3 32B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Lambda AIInference
qwen3-32b-fp8
$0.05 / $0.10
Qwen3-32B
$0.08 / $0.23
+88% vs headline
DeepInfraInference
Qwen3-32B
$0.08 / $0.28
+108% vs headline
Qwen3-32B
$0.10 / $0.30
+140% vs headline
Novita AIInference
qwen3-32b-fp8
$0.10 / $0.45
+200% vs headline
GMI CloudInference
Qwen3-32B-FP8
$0.10 / $0.60
+260% vs headline
qwen.qwen3-32b-v1:0
$0.15 / $0.60
+320% vs headline
Fireworks AIInference
qwen3-32b
$0.90 / $0.90
+1340% vs headline
Show 1 more listings: regions, snapshots and variants
Amazon Bedrock
Mantle
qwen.qwen3-32b
$0.15 / $0.60
+320% 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
Features
Parallel tool calls
Open weights
License: Apache-2.0
Runs in about 78.6 GB of GPU memory
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 Lambda AI.

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

  • Gemma 4 E2B
    Google · on Amazon Bedrock
    $0.04 / $0.08
    Has every key capability
    20% less
  • Qwen3.7 Flash Variant1
    Alibaba Qwen · on EmpirioLabs AI
    $0.028 / $0.11
    Has every key capability
    22% less
  • gpt-oss-20b
    OpenAI · on Darkbloom
    $0.0145 / $0.07
    Has every key capability
    55% less
  • Llama 3.2 3B
    Meta · on LlamaGate
    $0.04 / $0.08
    Lacks reasoning
    20% less

Model line

Newer and older versions, at each lab's own price.

  1. Apr 2025Qwen3 32BLatest$0.05 / $0.10
  2. Apr 2025Qwen 3 32B$0.10 / $0.30
  3. UndatedQwen2.5 32B$0.90 / $0.90

Call it

Using Lambda AI's API.

Python
from litellm import completion

response = completion(
    model="lambda_ai/qwen3-32b-fp8",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3 32B cost?

On Lambda AI, Qwen3 32B costs $0.05 per million input tokens and $0.10 per million output tokens.

Which APIs offer Qwen3 32B?

Qwen3 32B runs on 8 APIs: Lambda AI, OVHcloud AI Endpoints, DeepInfra, Nebius AI Studio, Novita AI, GMI Cloud, Amazon Bedrock and Fireworks AI.

What is Qwen3 32B's context window?

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

Is Qwen3 32B being retired?

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

Is there a newer version of Qwen3 32B?

No. Qwen3 32B is the newest model in its line.

What are cheaper alternatives to Qwen3 32B?

Models that cost less and keep most of what it can do: Gemma 4 E2B on Amazon Bedrock (20% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Qwen3 32B released?

Alibaba Qwen released it on 28 Apr 2025.

What is Qwen3 32B's API model id?

Use qwen3-32b-fp8 with Lambda AI. Other hosts use their own ids: Qwen3-32B on OVHcloud AI Endpoints, Qwen3-32B on DeepInfra, Qwen3-32B on Nebius AI Studio, Qwen3-32B-FP8 on GMI Cloud.

Sources

Raw catalog entry for qwen3-32b-fp8 on Lambda AI
{
  "input_cost_per_token": 5e-8,
  "litellm_provider": "lambda_ai",
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 1e-7,
  "supports_function_calling": true,
  "supports_parallel_function_calling": true,
  "supports_reasoning": true,
  "supports_system_messages": true,
  "supports_tool_choice": true
}