Dylan

#GDTBATH
Respan -

[Dylan @dylanc_5]

@RespanAI 👀

[Dylan @dylanc_5]

@RespanAI 🔥

[Respan @RespanAI]

Introducing Respan Router, powered by Span-01.

Automatically routes every request using task context, model capabilities, and cache-aware cost estimates behind 1 model id: 𝐬𝐩𝐚𝐧-𝐫𝐨𝐮𝐭𝐞𝐫

- 13% lower latency than jev-router on τ-bench airline
- 37% cheaper than the most accurate single model, at matching accuracy
- 0% processing fee on Respan Gateway

[Respan @RespanAI]

GPT-6.1 Sol is now live on the Respan Gateway, with 20% off every request.

Near-Astra performance at 1/5 of Astra’s list token price, with a 1.05M context window.

[Respan @RespanAI]

Octolane is building superintelligence for revenue - managing $700M in pipeline across 1,200 companies.

Every day, @octolane uses Respan to trace tool calls, inspect agents, and improve from production data.

See how @coffeewithone and his team scaled to 4.4M agent requests.

[OpenRouter @OpenRouter]

Span-01 and Span-01 Lite from @RespanAI are live on OpenRouter.

They're decision models for agent traces. Send a span and the behaviors you care about, and get back the probability each one is present, like "is the user frustrated?" or "is this tool call safe to run?"

[Dylan @dylanc_5]

@RespanAI 🔥

[Respan @RespanAI]

Introducing Respan Guardrails.

Built on Span-01, it catches prompt injections, jailbreaks, and unsafe content before they reach your models and tools.

It has the highest average F1 of any guardrail we tested across 8 categories, and it's free and native with Respan gateway.

[Andy Li @Andydy42]

Generalist models can be best overall without winning on every task. GPT-6 might even outperform some human labelers on certain evals. That’s an empirical question.

You clearly haven’t tested Span-01. If you’re making a claim about what works best for “evals,” which evals do you mean? Test it and share the dataset. We’ve published ours.

[Dylan @dylanc_5]

@deanwperkins 🔥

[Dylan @dylanc_5]

@marcusyul 🔥

[Dylan @dylanc_5]

@igus_ai 🔥

[Dylan @dylanc_5]

@astridtgtz 🔥

[Hendrix Liu @HendrixLiu29208]

ok i wasn't expecting this many of you on the Span-01 waitlist 🥹

can't wait to get it into your hands.

while you wait… we wrote it a song. yes, our model has a song now.

sound on!

[Dylan @dylanc_5]

@HendrixLiu29208 🔥

[Dylan @dylanc_5]

@hasantoxr 🔥

[Dylan @dylanc_5]

@RespanAI Game-changing 🔥🔥

[Respan @RespanAI]

Introducing Span-01, the first hyper-parallel reasoning classifier built for unseen challenges (RLAIF).

2x cheaper, 18% better than Jev.
700x cheaper, 4% better than GPT-6 Luna.
Frontier reasoning for every behavior, at classifier speed.

• Span-01: #1 on Behavior Benchmark
• Span-01 Lite: Better than Jev and completely free!

[Dylan @dylanc_5]

@Alokkumarzz 🔥

[Dylan @dylanc_5]

@HeyAmit_ 🔥