OpenRouter

Respan: Span-01

respan/span-01
Context

4K

Input

text

Output

decisions

Tool calling

Not listed

OverviewProvidersPricingBenchmarksAPI and quickstartReviews

About this model

Span-01 is Respan's reasoning classifier designed for evaluating LLM and AI-agent traces against arbitrary behavior definitions written in natural language. Instead of generating text token by token, Span-01 processes a conversation trace and multiple behavior definitions in a single forward pass and returns calibrated probabilities indicating whether each behavior is present, absent, or not observable from the available evidence. It is trained for general classification reasoning and specialized for behavior detection, supporting use cases such as agent evaluation, guardrails, prompt-injection detection, hallucination monitoring, tool-misuse detection, user-frustration detection, escalation routing, safety monitoring, and large-scale production observability. Its architecture uses hyper-parallel definition branches and hybrid attention to efficiently evaluate multiple behaviors across long and complex traces.

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

OpenRouter
Available

Input tokens

$0.020 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.020 / 1M tokens

Performance & Benchmarks

Independent evaluations and live cluster operational metrics

We haven’t measured this model yet.

API Guide

API docs
  1. 1

    Generate your access token

    Use your API key to generate the JWT access token required by the Models API.

  2. 2

    Add the JWT token

    Copy the generated JWT token and replace JWT_TOKEN in the example below.

  3. 3

    Check your credits

    If your balance is too low, before calling the model.

  4. 4

    Run the API example

    Choose your preferred language, copy the example, and send your first model request.

    curl https://api.oneinfer.ai/v1/ula/decisions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "respan/span-01",
  "state": {
    "task": "Delete inactive customer accounts"
  },
  "questions": {
    "approve": {
      "type": "noul",
      "instructions": "Is this action safe to run automatically?",
      "criteria": {
        "true": "Reversible or low impact",
        "false": "Destructive or requires approval"
      }
    }
  }
}'

Community Model Reviews & Ratings

Verified visitor & developer evaluations on Respan: Span-01's real-world intelligence, code accuracy, and speed

4.8
Community consensus rating
Top Community Consensus Tags:
Be the first to rate and tag this model's coding and reasoning strengths!

No community reviews yet

Be the first to share developer feedback on Respan: Span-01's latency, code accuracy, and reliability in production.