Switching models

How to switch

All text models share the /v1/chat/completions endpoint and the same request structure. To switch models, change only the model parameter; the rest of the code stays the same.

cURL example

GPT-5.6-sol

curl https://api.yomiapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5.6-sol", "messages": [{"role": "user", "content": "Hello"}]}'

Claude Sonnet 5

curl https://api.yomiapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "claude-sonnet-5", "messages": [{"role": "user", "content": "Hello"}]}'

DeepSeek V4 Pro

curl https://api.yomiapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4-pro", "messages": [{"role": "user", "content": "Hello"}]}'

Python example

Iterate over several models with the same code to compare their output:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.yomiapi.com/v1"
)

for model in ["gpt-5.6-sol", "claude-sonnet-5", "deepseek-v4-pro"]:
    response = client.chat.completions.create(
        model=model,
        messages=[{"role": "user", "content": "Introduce yourself in one sentence"}]
    )
    print(f"[{model}] {response.choices[0].message.content}")

Things to check when switching

• Model ID: Use the ID shown in the Model Catalog (such as gpt-5.6-sol), not the display name.
• Context length: Limits differ by model (for example, gpt-5.6-sol has 1.05M and claude-opus-4-8 has 200K). Check before switching long-context applications.
• Key group: A key's group determines its available models. If a model is unavailable after switching, check the key's group in API Keys.
• Call charges: Models have different prices. Check unit prices in the Model Catalog before calling and review charges under Usage after switching.