Qwen

Qwen3 32B

qwen/qwen3-32b
Model weightsReleased Apr 28, 2025Open Weights
ThinkingToolsopen weights

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Cost / 1M tokens

Very low usage

$0.08

input

—

cached input

$0.28

output

Context Window

131K

Up to 16K max output

Modalities

text → text

Qwen3 tokenizer

Quickstart & API

qwen/qwen3-32b
Open the model picker in ChatOSS Desktop (Code, Kanban, or Chat) and select or paste this model ID.

Best for & Strengths

Key Strengths

Open weightsExtended reasoningTool & agent calling

Recommended Workloads in ChatOSS

  • Coding agents
  • Complex reasoning & debugging
  • Open-source AI workflows
Available in ChatOSS Code, Kanban Orchestrate, and Chat modes via Plus, Max, or BYOK.

Active Provider Endpoints (5)

Upstream inference providers serving Qwen3 32B, with per-provider pricing, context limits, quantization, and 24-hour uptime.

ProviderInput / 1MOutput / 1MCache Read / 1MContextMax OutputQuantizationUptime (24h)
DeepInfra
deepinfra/fp8/flex
$0.064$0.224—41K37Kfp890.9%
DeepInfra
deepinfra/fp8
$0.08$0.28—41K16Kfp898.7%
DeepInfra
deepinfra/fp8/priority
$0.12$0.42—41K37Kfp8100.0%
Tenstorrentcache
tenstorrent/fp8
$0.14$0.40$0.0920K16Kfp899.5%
SiliconFlow
siliconflow/fp8
$0.14$0.57—131K118Kfp899.6%

Supported API Parameters

Parameters accepted by this model when called through ChatOSS or OpenRouter.

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

Compare Similar Models

Browse all models →