Skip to main content
See the full model recommendation guide for detailed comparisons.

​
Quick picks

Use caseModelWhy
Default / generalllama-3.3-70bBest quality + speed balance
Codingqwen-3-32bTop coding benchmarks
Long documentsllama-4-scout512K context window
Fastest responsellama-3.1-8bLowest latency
Highest qualityqwen-3-235b-cerebras235B parameters

​
Switching models

Just change the model parameter — everything else stays the same: 
# Switch from Llama to Qwen — only 1 line changes
response = client.chat.completions.create(
    model="qwen-3-32b",  # was: "llama-3.3-70b"
    messages=[{"role": "user", "content": "Write a Python function"}]
)

​
List available models

curl https://kymaapi.com/v1/models