Skip to content

Qwen 3.8 27B - Cerebras Free Trial Multimodal Model, 64K Context

Model ID qwen-3.8-27b
New Cerebras accounts that add a verified payment method receive a $5 trial credit (30 days), and calls within the free trial tier cost $0. After the credit is used up or expires, usage is billed at Developer rates ($0.99/$1.49 per million tokens).

Model Information

AttributeValue
Context length65,536 tokens (free tier)
Max output32,768 tokens (free tier)
Free tier price$0 (within the $5 trial credit)
Paid price$0.99 input / $1.49 output (per million tokens)
ProviderAlibaba Qwen / Cerebras
StatusFree trial
Input modalitiesText + image

Rate Limits (Free Trial Tier)

TypeLimit
Requests5/min
Uncached tokens30,000/min
Total tokens90,000/min
Tokens1,000,000/hour, 1,000,000/day
ImagesUp to 2 per request, request body max 10 MiB

Description

Qwen 3.8 27B is Alibaba’s 27B dense multimodal model, built for agentic coding, tool calling, research and long-horizon workflows. The model accepts text and base64-encoded PNG/JPEG image input, and supports configurable reasoning effort (default high; set reasoning_effort to none to disable), tool calling, parallel tool calling, structured output and prompt caching.

Usage Example

curl https://api.cerebras.ai/v1/chat/completions \
  -H "Authorization: Bearer $CEREBRAS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-3.8-27b",
    "messages": [{"role": "user", "content": "Implement an LRU cache in Python"}]
  }'

Image input uses OpenAI-compatible image_url content blocks, and the URL can be a base64 data URL.

Related Links

📚 Related Free Models

These models are also available for $0 on Cerebras. Choose by context length and modality.

ModelContextDescription
GPT-OSS 120B65KGPT-OSS 120B is OpenAI’s open-weight reasoning model for

📋 View all Cerebras free models →

🔗 Site Navigation

Last updated on · Source: Cerebras official documentation and pricing pages. Quotas and prices may change at any time.