All Models

Qwen 3.5 9B

qwenReasoningTool CallingAttachmentsOpen WeightsStructured Output

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...

Providers24
ReleasedFeb 1, 2026
Input Modalitiestext, image, video, audio
Output Modalitiestext
Tarsk Usecoding

Benchmarks

13.7
Intelligence Index
28.7
Coding Index

Available Providers (24)

ProviderModel IDInput CostOutput CostContextMax OutputDocs
QVACqwen3.5-9b$0/MTok$0/MTok32.8K8.2K
Atomic ChatQwen3_5-9B-Q4_K_M$0/MTok$0/MTok32.8K8.2K
Atomic ChatQwen3_5-9B-MLX-4bit$0/MTok$0/MTok32.8K8.2K
CrofAIqwen3.5-9b$0.04/MTok$0.15/MTok262.1K262.1K
NanoGPTqwen/qwen3.5-9b$0.05/MTok$0.15/MTok256K65.5K
EmpirioLabs AIqwen3-5-9b$0.09/MTok$0.13/MTok262.1K32.8K
Merge Gatewayqwen/qwen3.5-9b$0.09/MTok$0.13/MTok262.1K32.8K
LLM Gatewaydeepinfra/qwen3.5-9b$0.10/MTok$0.15/MTok262.1K32.8K
Venice AIqwen3-5-9b$0.10/MTok$0.15/MTok256K32.8K
DevPass (LLM Gateway)qwen3.5-9b$0.10/MTok$0.15/MTok262.1K65.5K
Deep InfraQwen/Qwen3.5-9B$0.10/MTok$0.15/MTok262.1K65.5K
Kilo Gatewayqwen/qwen3.5-9b$0.10/MTok$0.15/MTok256K32.8K
OpenRouterqwen/qwen3.5-9b$0.10/MTok$0.15/MTok262.1K32.8K
SiliconFlowQwen/Qwen3.5-9B$0.10/MTok$0.15/MTok262.1K262.1K
Mixlayerqwen/qwen3.5-9b$0.10/MTok$0.40/MTok262.1K262.1K
Cortecsqwen3.5-9b$0.11/MTok$0.17/MTok262.1K262.1K
OVHcloud AI Endpointsqwen3.5-9b$0.12/MTok$0.18/MTok262.1K262.1K
Regolo AIqwen3.5-9b$0.15/MTok$0.60/MTok262.1K8.2K
TensorXqwen/qwen3.5-9b$0.15/MTok$0.20/MTok262.1K65.5K
routing.runqwen3.5-9b$0.16/MTok$0.48/MTok262.1K32K
Hugging FaceQwen/Qwen3.5-9B$0.17/MTok$0.25/MTok262.1K65.5K
Together AIQwen/Qwen3.5-9B$0.17/MTok$0.25/MTok262.1K65.5K
SiliconFlow (China)Qwen/Qwen3.5-9B$0.22/MTok$1.74/MTok262.1K65.5K
PioneerQwen/Qwen3.5-9B$0.30/MTok$0.30/MTok32.8K32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output