Updated

Respan

Hosted LLM gateway, tracing and evals platform (formerly Keywords AI) that routes calls to 1,000+ models through one OpenAI-compatible endpoint and logs every request, with an open-source Rust gateway.

2 makers' products we track use Respan.

Free tierPaid from $199/mo

Renamed: Keywords AI now operates as Respan; keywordsai.co redirects to respan.ai, whose footer reads "Keywords AI, Inc. · Respan® is a registered trademark". Source ↗

Profile checked

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

How makers use Respan

Makers' products we track use Respan for LLM observability & evals (2).

What Respan is used for

LLM Gateway & Routing · Managed gateway + controls →One OpenAI-compatible endpoint to 1,000+ models with fallbacks, caching, spend limits and every request logged in the same place you run evals.Trade-off: Requests pass through its cloud; the free plan caps proxy throughput at 412 requests a minute, and the self-hostable part is only the new open-source gateway.
Kong Gateway2Helicone1Unify1OpenRouter0LiteLLM0Respan0Makers' products on each, for LLM gateway & routing
LLM Observability & Evals · Hosted eval platform →Tracing, monitoring, prompt management and LLM-judge evals for agents, with a built-in gateway that logs every call it routes.Trade-off: Cloud-only below Enterprise; the free plan keeps logs 7 days, and Team starts at $199/mo billed yearly.
Datadog50Langfuse35Helicone13LangSmith11Braintrust6Respan2Makers' products on each, for LLM observability & evals

Respan vs the alternatives makers chose

For LLM observability & evals, 2 of the 117 makers' products we know the choice of picked Respan (2%), behind Datadog (43%).

OptionMakers' productsFree forAt 10,000 usersOpen source
Datadog50 43%——No
Langfuse35 30%~5,000 users$29/mo · CoreYes
Helicone13 11%~1,000 users$116/mo · ProYes
LangSmith11 9%~520 users$475/mo · DeveloperNo
Braintrust6 5%——No
Weights & Biases3 3%——No
Respan2 2%——No

For LLM observability & evals: how many of the 117 makers' products we know the LLM observability & evals of chose each option, and what each costs at 10,000 users.

Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.

When to use Respan, and when not

Something else fits better if

  • You want tracing, prompts and evals in one tool you can self-host for free: Langfuse.
  • You already use OpenTelemetry or want vendor-neutral instrumentation: Arize Phoenix.
  • You want request logs and costs today by changing one base URL: Helicone.
  • Your app is built on LangChain or LangGraph: LangSmith.
  • Your main question is whether a prompt or model change made outputs better or worse: Braintrust.
From each decision's guide, written from what makers' products chose and why.

How Respan itself is built

2 tools, from its own code, website and Product Hunt page.

Who uses it

2 makers' products, each linked to the source that shows it. The best known on Product Hunt: Nia (325 followers), Octolane (297 followers).

Octolane
OctolaneSelf-driving AI CRM that you can talk to

“We run a lot of agents at octolane. slash-command skills, deal detection, follow-up generation. respan is how we see what they're actually doing in production. evals + observability in one place, built for agent workflows.”

LLM Observability & EvalsMaker says so · source ↗

Alternatives to Respan

All alternatives by situation →

Questions makers ask about Respan

What is Respan used for?

Hosted LLM gateway, tracing and evals platform (formerly Keywords AI) that routes calls to 1,000+ models through one OpenAI-compatible endpoint and logs every request, with an open-source Rust gateway. Makers' products we track use it for LLM observability & evals (2).

What are the alternatives to Respan?

For LLM observability & evals, the other options makers' products we track chose most are Datadog (50), Langfuse (35), Helicone (13), LangSmith (11), Braintrust (6), Weights & Biases (3). Open source or self-hostable among them: Langfuse, Helicone, Weights & Biases. Each alternative, with the situation it fits, is on the Respan alternatives page.

Is Respan free?

Yes — there is a free tier a small product can run on; paid use starts at $199/mo. source ↗

Is Respan open source or self-hostable?

Not open source, and hosted only. source ↗

Can AI coding agents work with Respan?

No llms.txt, official MCP server or CLI found yet.

Who uses Respan?

2 makers' products we track, each with a source. The best known of them on Product Hunt: Nia (325 followers), Octolane (297 followers). source ↗