- Home
- AI LLM Observability Tools
- Respan (formerly Keywords AI)
Respan (formerly Keywords AI)
What it is
Respan, formerly Keywords AI, is an AI gateway with observability, evaluations, and security testing. Its OpenAI-compatible endpoint routes requests to more than 1,000 models. Fallbacks, load balancing, automatic retries, and response caching support reliability, although the gateway may add 50 to 150 ms of latency. Respan traces LLM calls, tool runs, retrievals, and agent turns, recording inputs, outputs, latency, and cost. Evaluations can combine LLM judges, deterministic code checks, and human review, including scoring sampled production traffic. Monitoring tracks requests, errors, cost, latency, and tokens, with threshold alerts through Slack, email, or webhook. The integrations directory lists 171 connections, including OpenTelemetry, LangChain, OpenAI, Anthropic, AWS Bedrock, Slack, and PostHog. API, self-hosted, and web deployment are available. Free costs nothing; Team costs $199 a year billed yearly; Enterprise pricing is custom. Respan states support for SOC 2, GDPR, and HIPAA, with a BAA for healthcare teams.
For and against
For
- Routes requests to more than 1,000 models
- Traces calls, tools, retrievals, and agent turns
- Combines automated and human evaluations
- Alerts through Slack, email, or webhook
- Offers API and self-hosted deployment
Against
- Gateway may add 50 to 150 ms
- Free plan has usage limits
- Enterprise pricing is custom
- Team plan is billed yearly
The verdict
Respan combines model routing with tracing, evaluation, monitoring, and security support. Its latency note and plan limits matter for teams with strict response-time or usage requirements.
Who it suits
Respan suits startup and enterprise teams tracing workflows, evaluating agent behavior, and monitoring production AI systems. It also fits teams needing API or self-hosted deployment options.
Plans and prices
Free
100k logs · 1k scores · 5 datasets · 2 evaluators
Read 4 Oct 2026 · respan.ai
Team
10k scores · 100k logs · unlimited datasets, evaluators, and prompts · 5 members
Read 4 Oct 2026 · respan.ai
Enterprise
Custom packages · volume discount · custom SLAs · dedicated support engineer
Read 4 Oct 2026 · respan.ai
On the record
- Company background
- The About page says Respan, formerly Keywords AI, began at the University of Illinois and joined Y Combinator's Winter 2024 batch.respan.ai · read 4 Oct 2026
- Enterprise security
- The Enterprise plan lists self-hosted deployment, Google and SAML SSO, HIPAA compliance, and a HIPAA BAA.respan.ai · read 4 Oct 2026
- Evaluations
- Evaluators can combine LLM judges, deterministic code checks, and human review, and can score sampled production traffic.respan.ai · read 4 Oct 2026
- Gateway
- Its OpenAI-compatible gateway routes requests to 1,000+ models through one endpoint.respan.ai · read 4 Oct 2026
- Gateway latency
- The gateway quickstart says the gateway may add 50 to 150 ms and may not suit products with strict latency requirements.respan.ai · read 4 Oct 2026
- Integrations
- The integrations directory lists 171 integrations, including OpenTelemetry, LangChain, OpenAI, Anthropic, AWS Bedrock, Slack, and PostHog.respan.ai · read 4 Oct 2026
- Intended users
- The About page says Respan helps teams trace workflows, evaluate agent behavior, and improve quality in production, and that startups and enterprise teams use it.respan.ai · read 4 Oct 2026
- Monitoring
- The product tracks requests, errors, cost, latency, and tokens, with threshold alerts sent through Slack, email, or webhook.respan.ai · read 4 Oct 2026
- Privacy and compliance
- The homepage states Respan supports SOC 2, GDPR, and HIPAA, and says a BAA is available for healthcare teams.respan.ai · read 4 Oct 2026
- Product
- Respan describes itself as an AI gateway with built-in observability, evaluations, and security testing.respan.ai · read 4 Oct 2026
- Reliability
- The gateway provides model fallbacks, load balancing, automatic retries, and response caching.respan.ai · read 4 Oct 2026
- Support
- The pricing page lists Community Discord for Free, email support for Team, and a dedicated support engineer for Enterprise.respan.ai · read 4 Oct 2026
- Tracing
- Respan captures LLM calls, tool runs, retrievals, and agent turns as spans in a trace with input, output, latency, and cost.respan.ai · read 4 Oct 2026
