Skip to content
System One

Span-01

Span-01 is Respan's behavior classifier for agent traces. It reads a conversation span and behaviors you define in plain language, and returns the probability that each is present, absent or not observable. Respan says Span-02 replaced it. OpenRouter still lists it at $0.02 per million input tokens, with a free Lite tier.

Updated

What Span-01 is

Span-01 is Respan’s classification model for agent traces. Like a System One model, it returns probabilities in one forward pass and writes no text. You send a conversation span and a list of behaviors written in plain language, such as “the user expresses frustration.” Respan says the behaviors are not a fixed list. It trained the model for general classification reasoning with RLAIF, reinforcement learning from AI feedback, then specialised it for behavior detection.

Respan’s launch post now says Span-02 replaced Span-01, and Respan’s Span-01 docs redirect to the Span-02 docs. This page marks it deprecated for that reason. OpenRouter still lists Span-01 and Span-01 Lite, served by Respan, as of 14 November 2026.

What it returns

For each behavior you get three probabilities: present, absent and not observable. Not observable means the trace cannot answer the question, for example when it ends before the customer replies.

Every behavior in a request is scored in one forward pass, and output tokens are free. The three-way output does not match Choice, Score or Noul exactly, and Noul is the closest. A third-party benchmark repo calls it through OpenRouter’s System One endpoint.

What it is good at

Respan aims it at the behaviors production teams monitor in LLM and agent output, such as user frustration, escalation and jailbreak attempts. That fits LLM guardrails and confidence-gated actions.

On Respan’s own production behavior benchmark, Span-01 scores 0.806 overall F1, against 0.716 for Jev, 0.719 for Sonnet 5 and 0.885 for GPT-6 Sol. Its best domains are privacy and secrets at 1.000 and agent and tool reliability at 0.845. These are Respan’s numbers on its own dataset.

The one outside test found is not about behaviors. On a 48-question sentiment and topic pool, the zero-shot-ie-bench author measured 85.4% for Span-01 and 79.2% for Lite, against 93.8% for Jev.

Span-01 Lite

Lite is the free, lighter tier of Span-01. On Respan’s overall behavior chart it scores 0.761 F1 against 0.843 for Span-01 and 0.715 for Jev. OpenRouter lists it at no cost.

Span-02 replaced it

On 15 October 2026 Respan released Span-02, a general decision model rather than a behavior classifier. It answers Choice, Score, Noul and number questions on its own endpoint, /api/v1/decisions, at $0.01 per million input tokens, and has open weights on Hugging Face. Respan now points Span-01 users to Span-02. Span-02 does not return the three-way present, absent and not observable output.

What it is not for

It does not write text or explain a score, and OpenRouter lists text input only. It is not a general classifier over a fixed option list. No context length or latency figure is published, so test long traces yourself. For new work, start with Span-02.

Access

Respan’s launch post, dated 24 September 2026, says Span-01 is public, and its price table still lists Span-01 Lite as free and Span-01 at $0.02 per million input tokens. Respan’s Span-01 docs are gone. OpenRouter has listed both since 26 September, from Respan as the only provider, and still did on 14 November 2026.

Specifications

InputsTextOpenRouter lists text input only, checked 2026-11-14. Respan's Span-01 docs now redirect to Span-02.
Question typesNoul
Max Choice optionsNot documented
Score levelsNot documented
Questions per callNot documented
Total contextNot documented
State budgetNot documented
Rate limitNot documented
EndpointPOST https://api.respan.ai/api/v1/scores
LicenceNot published as of 14 Nov 2026
SDKs

No context length is published. OpenRouter lists 0, checked 2026-11-14.

Versions

  • span-01-pro, 24 Sep 2026, OpenRouter lists it as respan/span-01, snapshot span-01-20260925, at $0.02 per million input tokens, served by Respan (checked 2026-11-14). Release notes
  • span-01-free, 24 Sep 2026, Span-01 Lite, the free lighter tier. OpenRouter lists it as respan/span-01-lite and respan/span-01-lite:free, snapshot span-01-lite-20260925, served by Respan (checked 2026-11-14). On Respan's overall behavior benchmark it scores 0.761 F1 against 0.843 for Span-01. Release notes

Use cases

What people use Span-01 for, one page per pattern.

Safety and qualityIntermediate

LLM guardrails with System One models

Put one Jev request in front of an LLM and one behind it. Yes/no questions return the probability that each hazard holds, a Score rates how much harm complying would do, and your thresholds turn those numbers into pass, review, block, or a crisis path.

NoulScore
Workflow controlIntermediate

Confidence-gated actions with System One models

Jev returns a confidence value from 0 to 1 alongside every Choice and Score answer. Your code treats it as a separate axis: act automatically when it's high, confirm or flag when it's middling, hand the decision to a person when it's low. Riskier actions get higher bars.

ChoiceScore

Benchmarks

Published scores, each linked to its source. A row marked vendor-run was measured by the vendor itself, so read it as one side's result. The compare hub sets these beside the other models.

BenchmarkMetricScoreRun byDate
Respan behavior benchmarkOverall F10.806vendor-run24 Sep 2026
  • Respan behavior benchmark, Overall F1: Respan's own production dataset; Jev scored 0.716.