Respan by Keywords AI, Inc.
AI gateway that routes LLM calls across providers with built-in logging, tracing, evals and prompt management.
LLM gateways and routers Official MCP server
Price
Free plan
then from $199/mo
Free tier
Yes
Free plan: 100k logs, 1k scores, 5 datasets, 2...
SDK downloads
—
npm @respan/respan · PyPI respan-ai
Status
—
no public status page
Pricing
| Free tier | Free plan: 100k logs, 1k scores, 5 datasets, 2 evaluators, 5 prompts, 7-day retention |
|---|---|
| Cheapest paid plan | $199 a month |
| Usage price | Additional logs $8 / 100k logs; additional scores $1 / 1k scores; extra seats $15/member (Team) |
| Good to know | Formerly Keywords AI (keywordsai.co redirects to respan.ai). Team plan $199 per month is shown as billed yearly. |
From the official pricing page, checked Oct 10, 2026. Prices change: confirm before you buy.
Use it from an agent
| MCP server | Official: https://respan.ai/docs/documentation/mcp |
|---|---|
| npm | npm install @respan/respan |
| PyPI | pip install respan-ai |
Alternatives to Respan
| API | Free | Price | SDK downloads / wk | GitHub stars | MCP |
|---|---|---|---|---|---|
| Vercel AI Gateway Unified API to hundreds of models with provider fallbacks, billed at provider list prices. |
$5/month of AI Gateway credits (free-tier... | Free plan then Provider list price per token, zero markup and no... |
27.7M | 27.2K | |
| LiteLLM Open-source proxy and SDK that calls 100+ LLMs in OpenAI format with keys, budgets and logging. |
Open-source gateway free to self-host | Free plan | 22.9M | 60.5K | |
| OpenRouter One OpenAI-compatible API for 500+ models across 80+ providers with routing and fallbacks. |
25+ free models, 50 requests/day | Free plan then Provider list price per token (no markup); fee on credit... |
1.3M | 262 | MCP |
| Portkey AI gateway with routing, fallbacks, caching, guardrails, prompt management and observability. |
Developer: 10k recorded logs/month, 3-day... | Free plan · paid from $49/mo | 925K | 13.2K | |
| Cloudflare AI Gateway Proxy for LLM providers adding analytics, caching, rate limiting, logging and unified billing. |
Core features (analytics, caching, rate... | Free plan then Unified Billing: 5% fee on credits purchased; provider... |
251K | 1,189 | MCP |
| Helicone Open-source LLM observability platform and AI gateway with caching, rate limits and fallbacks. |
Hobby: 10,000 requests/month, 1 GB storage, 1 seat | Free plan · paid from $79/mo | 2,989 | 6,210 | MCP |