---
id: "qwen/qwen3.5-9b"
also: ["qwen/qwen3.5-9b-20260310", "Qwen/Qwen3.5-9B", "hf/Qwen/Qwen3.5-9B", "requesty/qwen/qwen3.5-9b"]
cheapest_list_usd_per_m: "0.071 in, 0.104 out, at primeintellect/bf16 on openrouter"
cheapest_effective_usd_per_m: "0.0617 in, 0.13 out, at runware on requesty"
context: 262144
max_output: 235929
input: ["text", "image", "video"]
output: ["text"]
released: "2026-03-10"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 12
gateways: "openrouter (7), hf (4), requesty (1)"
no_training: 8
trains: 0
retains_prompts: 1
coding: 28.7000
agentic: 1.2000
---
# Qwen: Qwen3.5-9B

Qwen3.5 9B is a compact hybrid-reasoning model from the Qwen3.5 family with strong coding, math, and multilingual performance for its size, a 262K token context window, tool calling, and structured output support. Served via Runware.