Qwen3.6 27B

reasoningapache-2.027B

Qwen3.6 27B is an open-weight general-purpose model with a 262k context window, hosted by Reka. It is served as an OpenAI-compatible passthrough with native tool calling, reasoning and streaming.

Context
262K
Max output
33K
Input price
$0.29/1M tokens
Output price
$1.95/1M tokens

Capabilities

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

Details

Model IDqwen3.6-27b
Provider Reka AI
Creator Qwen
Familyqwen3.6
Licenseapache-2.0
Statusactive
Typereasoning
Input modalitiestext
Output modalitiestext
Open weight—
Parameters27B
Architecture—
Context window262K tokens
Max input—
Max output33K tokens
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.reka.ai/v1/chat/completions

Pricing

Input
$0.29
Output
$1.95
Cache write
—
Cache read
$0.03
Batch in
—
Batch out
—

API

GET/v1/models/reka/qwen3.6-27b