KosComputeAPI
Models

Qwen: Qwen3.8 27B

Capabilities, limits, pricing, and endpoints for qwen/qwen3.8-27b.

View Markdown

Canonical model ID: qwen/qwen3.8-27b

Qwen 3.8 27B for writing, reasoning, coding, and image understanding.

Runtime metadata

This table is generated from public model metadata. Readiness and capacity are refreshed from GET /v1/models on page load.

Property Value
Kind chat
Input text, image
Output text
Context 262,144 tokens
Maximum output 32,768 tokens
Supported endpoints /v1/chat/completions, /v1/responses, /v1/messages
Capabilities tool_calling, json_mode, structured_outputs, reasoning
Pricing Input $0.35 / 1M · Output $2.2 / 1M tokens

Vision limits

Vision limits are model-specific.

Property Value
Processor pixel budget 1,048,576

Reasoning

Reasoning support and controls are model-dependent.

Supported efforts: none, low, medium, xhigh. Maximum configured reasoning sub-budget: 8,192 tokens.

See the reasoning guide for budget semantics.

Use this model

Copy the canonical ID into the model field. Check the endpoint guide before using optional capabilities.

Type to search guides, models, and API reference.