Qwen3.5-9B

apache-2.0

Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.

Context
262K
Input price
$0.1/1M tokens
Output price
$0.15/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Fine-tuning

Details

Model IDQwen/Qwen3.5-9B
Provider DeepInfra
Family—
Licenseapache-2.0
Statusactive
Typechat
Input modalitiestext, image
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window262K tokens
Max input—
Max output—
Reasoning tokensYes
Knowledge cutoff—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input
$0.1
Output
$0.15
Cache write
—
Cache read
—
Batch in
—
Batch out
—

API

GET/v1/models/deepinfra/Qwen/Qwen3.5-9B

Qwen3.5-9B

Qwen/Qwen3.5-9B

Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.

Changes · 4 entries
Qwen/Qwen3.5-9Bcreateca7a400Nov 2, 2026, 03:02 AM
Qwen/Qwen3.5-9Bupdate0d5a9a1Oct 14, 2026, 06:38 AM
reasoning_tokensyes
Qwen/Qwen3.5-9Bupdated68a4f1Jun 10, 2026, 02:10 AM
pricinginput$0.04→$0.1
Qwen/Qwen3.5-9Bcreate80c574aJun 3, 2026, 07:05 AM