Impulse
Models/Qwen2.5-32B-Instruct
Compare

Qwen2.5-32B-InstructActive · Cloud

Nebius AI Studio · Released · Apache-2.0

Nebius chat model.

Context
128K
Max output
128K
Input
$0.06
Output
$0.20
Cached in
-
Latency
-

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

Details

ProviderNebius AI Studio
Released
LicenseApache-2.0
InputText
OutputText
Throughput-
Availability-

Related models

DeepSeek-R1-0528Nebius AI Studio164K$0.80Qwen3-14BNebius AI Studio33K$0.08Qwen3-235B-A22BNebius AI Studio262K$0.20