Agentic workloads

Agent systems often make several short model calls before they can continue: routing, scoring, extraction, and query rewriting. The latency of those calls accumulates across a workflow.

celeris-1 is optimized for these short, structured tasks. Use it for latency-sensitive intermediate steps and retain a long-form model where the workflow requires extended generation.

Patterns

Classification and routing

Assign an input to a fixed set of labels, such as intent categories, moderation states, or tools. Specify the allowed output values:

{
  "model": "celeris-1",
  "messages": [
    {"role": "system", "content": "Route the user message to exactly one tool: search, calculator, email, none. Reply with the tool name only."},
    {"role": "user", "content": "what is 14% of 2,300,000?"}
  ],
  "max_tokens": 8,
  "temperature": 0
}

Structured extraction

Extract typed fields from unstructured text. Request JSON, define the fields, and set a token limit that fits the expected object:

{
  "model": "celeris-1",
  "messages": [
    {"role": "system", "content": "Extract the fields as JSON only: {name, company, intent}."},
    {"role": "user", "content": "Hi, Priya Nair here from Meridian Logistics — keen to trial the enterprise plan."}
  ],
  "max_tokens": 48,
  "temperature": 0
}

Judging and scoring

Relevance grading, answer verification, and reranking generally use small inputs and outputs, which makes them suitable for celeris-1.

{
  "model": "celeris-1",
  "messages": [
    {"role": "system", "content": "Score how well the passage answers the question, 0-10. Reply with the number only."},
    {"role": "user", "content": "Question: When did the Golden Gate Bridge open?\nPassage: The Golden Gate Bridge opened to pedestrians on May 27, 1937."}
  ],
  "max_tokens": 3,
  "temperature": 0
}

Query rewriting

Turn conversational input into retrieval queries, SQL, or filter expressions:

{
  "model": "celeris-1",
  "messages": [
    {"role": "system", "content": "Rewrite the message as a concise search query. Query only."},
    {"role": "user", "content": "hey do you have anything like the blue runners I bought last month but waterproof"}
  ],
  "max_tokens": 24,
  "temperature": 0
}

Implementation guidance

• Use temperature: 0 and an explicit max_tokens limit for structured calls. This reduces output variation and bounds latency and cost.
• Ask for machine-readable output ("Reply with the tool name only", "JSON only") and validate it before use.
• Parallelize independent calls within a concurrency limit. This provides per-item failure handling without overwhelming the workspace rate limit. See Rate limits.
• Monitor 429 responses in your application. They are not included on the usage page. If the rate increases, reduce concurrency or contact support about a higher sustained limit.