Choose your deployment model

Need

Recommended product

Quick experimentation or low-volume production

Serverless—pay per token, no setup

Production with latency/cost control

Dedicated instances—private GPUs, auto-scaling

Large-scale offline processing (evals, data)

Batch—50% off, up to millions of prompts

Quickstart

Make your first chat completion call in under two minutes:

Copy

from openai import OpenAI

client = OpenAI(
    base_url="https://api.parasail.io/v1",
    api_key="<PARASAIL_API_KEY>"
)

response = client.chat.completions.create(
    model="parasail-deepseek-r1",
    messages=[{"role": "user", "content": "Explain quantum computing in one paragraph."}]
)

print(response.choices[0].message.content)

See the serverless quickstart for the full guide.

Relevant guides

• Chat completions guide—messages, roles, system prompts, and chat templates
• Model selection—find the best model for your use case
• Structured output—force JSON-formatted responses
• Tool/function calling—give the model tools to call

API reference

• Chat completions API
• Parameters—temperature, top_p, top_k, and more
• Responses API—multi-turn agentic workflows with tool calling

Available models

Browse all available serverless models:

Copy

curl https://api.parasail.io/v1/models \
  -H "Authorization: Bearer $PARASAIL_API_KEY"

See also: Model selection and model-specific Serverless notes.