Head of Developer Experience @RespanAI (Formerly Keywords AI, YC W24)
Joined February 2023
- Tweets 286
- Following 103
- Followers 107
- Likes 363
72 Photos and videos
Jun 11
10 engineers × 4 CLI agents = 40 accounts, 40 invoices, 40 price tags.
We made it 1.
Claude Code, Codex, Gemini CLI, OpenCode, and more can now run through Respan Gateway with unified billing and discounted usage.
3
10
1,700
Jun 11
sth fable 5 actually can do with samples. not sure how people making those videos.
1
36
Frank Chen retweeted
MiniMax is live on @RespanAI Gateway
Developers now have another easy way to access our models.
as more teams ship AI products across text, speech, image, video, and music, we want our models right there when you need them.
link in comments 👇
#MiniMax #Respan #AIGateway #MultimodalAI #AIModels #Developers #BuildWithAI
11
5
100
7,373
Frank Chen retweeted
Tera is live on the Respan Gateway.
Users can now call Tera models while keeping unified observability (logs, cost, latency, reliability) in Respan.
Congrats to the @RespanAI team for the launch!
Introducing Respan AI Gateway.
The world’s first AI gateway with built-in observability, evals, and prompt optimization.
Access 1,000 models through one endpoint, with the production layer teams need beyond routing.
2
3
5
418
Frank Chen retweeted
Jun 9
Novita AI is now available on Respan Gateway.
Teams can now discover and build with our AI and agent cloud through @RespanAI.
We give developers access to model APIs, GPU infrastructure, and agent runtimes for building production AI applications.
3
4
19
477
Frank Chen retweeted
Jun 9
AI bill is out of control, and the fix lives in the gateway layer!
wrote about why the gateway is becoming the control plane for spend, observability evals:
3
3
18
1,637
May 13
Doing a smog check today and realized California really said:
“Your car seems fine, but prove it.”
Honestly, AI apps need the same energy.
Your agent might look fine in demo, but in production you still need to prove:
latency isn’t creeping up
cost isn’t randomly spiking
tool calls aren’t silently failing
answers aren’t getting worse after a prompt change
The vibe is not “trust me bro, it works", and that’s what we’re building at respan.ai
6
61
Apr 25
Interesting. This is also what we support at @RespanAI.
Most gateways like OpenRouter use router-style APIs that normalize requests into an OpenAI format. That can change behavior or drop provider-specific features.
Respan is different. We provide a true pass-through gateway, so requests, headers, and streaming are forwarded as-is. Agent CLIs behave exactly the same as calling the provider directly.
In addition, we also log all calls for observability and debugging.
(PS. we also support Codex, Gemini CLI , and OpenCode)
Apr 22
Anthropic has quietly shipped third-party inference for Cowork and Code in Claude Desktop.
This should work with local models or OpenRouter via LiteLLM proxy.
Is it just me?
1
5
145
Respan Launch Week, Day 5 🚀
Introducing AI Gateway Limits and Alerts.
LLM costs can get out of control fast in production, especially as traffic grows across models, API keys, and apps.
Now you can set limits directly in Respan AI Gateway:
- Alerts via email or Slack
- Recurring budgets for LLM usage
- Limits by API key or model
- Controls for cost, requests, or tokens
When a limit is exceeded, you can block the request or send a warning.
Built for teams that want to move fast with clear cost controls.
Try it today!
4
5
28
611,899
Respan Launch Week, Day 4: Introducing Respan Integrations
Most teams still spend days setting up observability.
That’s why we invested heavily in Respan Integrations.
We support major LLM and agent frameworks like OpenAI, Anthropic, Gemini, LangChain, Vercel AI, and Pydantic AI, with more being added.
Run 'npx [at]respan/cli setup' and start tracing in minutes, not days.
1
7
18
1,080
Apr 23
The cake is 🐐
Apr 22
@RespanAI team pulling all nighters for their launch week to keep up with demands. Absolutely cracked team everyone lives and works under the same roof. Bullish on these guys
2
42
Respan Launch Week, Day 3: introducing @RespanAI Agent, CLI, and MCP.
Three ways to stop doing AI engineering by hand:
→ Agent: ask it to build an evaluator, fix a prompt, or find the root cause of a bad trace on the platform.
→ CLI: npx respan@cli setup - auth, framework detection, and tracing in one command.
→ MCP: plug Respan into Claude Code, Cursor, or anything that speaks MCP.
Same data, same access, wherever you work.
3
7
22
4,413