The industry standard AI Gateway for models, mcps and agents https://xitter.cf/t.co/UV2Ppapiyz
try it today ➜
Joined December 2022
- Tweets1.1K
- Following195
- Followers5.9K
- Likes1.1K
LiteLLM (YC W23) retweeted
Signups are now open for @LiteLLM Handoff, our two-week workshop for developers building cloud agents.
You’ll work with the LiteLLM team to build an agent and deploy an internal beta in your own cloud.
The workshop is remote and limited to 50 developers, October 26 – November 9, 2026
Claude Code + your favorite model?
Just use LiteLLM.
Using our harnesses with other models is supported: just use a proxy like litellm (see our docs page, or ask Claude to set it up for you).
One challenge is there’s a lot of model-specific tool design and prompting that goes into building a good harness. The team and I spend a lot of time dialing these in for each model.
LiteLLM (YC W23) retweeted
Which model names (-m) can you use in Harbor? Now there's one answer: LiteLLM's.
harbortoolkit.com/model
LiteLLM (YC W23) retweeted
Small Grok Bot, but useful for me: Switchboard 🔀
If you run a @LiteLLM proxy with different local models, you know the pain of setting everything up again every time you swap.
Switchboard fixes that. It keeps the same alias for the same model family, so when you swap recipes (vLLM, llama.cpp, Ollama…) you configure your harnesses once and never touch them again.
What it does:
• finds the model that's running and reads its id
• points the family alias at it, or adds a new one
• backs up the config before every change
• reloads LiteLLM and tests a real chat completion
• rolls back automatically if anything breaks
It only edits the LiteLLM config. It never starts or stops your model servers.
Built for my DGX Spark. Still early and I'm still testing it.
Try it: x.ai/bot/ppO9XYR2CUS7-Hyaklf…
#LocalAI #LiteLLM
The October LiteLLM Townhall is next Thursday
Thu, Oct 22 · 7:30 to 8:30 AM PT · Zoom
What we'll cover:
- Security
- Stability & Performance
- Recent product releases & what we're planning to ship - Q&A
Register here: forms.gle/F8tTYR8rfjKBA4D67
LiteLLM AI Gateway serves decision models on /v1/decisions, in OpenAI’s format, and on /v1/systemone, with named questions.
Any decision model works on either route, with up to 128 questions per call and a probability on every answer.
Get started here: docs.litellm.ai/docs/decisio…
LiteLLM (YC W23) retweeted
The @LiteLLM team is hosting a 2-week workshop to help teams build cloud agents within their own infrastructure.
You can sign up here: docs.litellm.ai/blog/cloud-a…
We’ll work with your team to build an end-to-end cloud agent that users can trigger from Slack, Teams, or email to complete a task and open a PR.
The workshop starts October 19th and is remote-friendly (if you are based in SF, we will come and work with you in person).
By the end of the workshop, you’ll have a working cloud agent running on your infrastructure from a message in Slack to a PR, end to end.
Gemini 4 Argon, @Google’s flagship reasoning model, is now supported on LiteLLM!
Launch pricing until Nov 30:
Input: $2.00 / MTok
Output: $10.00 / MTok
Cache read: $0.10 / MTok
Pricing and limits: models.litellm.ai/models/gem…
LiteLLM (YC W23) retweeted
We're open sourcing agentchat, it's a unified SDK that allows you to connect your agent to Slack, Teams, iMessage, email, and WhatsApp in 2 lines of code and works with any agent SDK
We noticed we kept on rebuilding the stack to connect our agents to different channels and ended up building the same shared layer. That's where agentchat came in.
This allows you as a developer to focus on your core agent's brain and let the SDK manage your connections with different channels.
Day 0 support for Meta Muse Wonder on LiteLLM!
- $4 in, $20 out per 1M
- 1M-token context window
- Text, image, video, PDF input
Details here: models.litellm.ai/models/mus…
Call Jev, Clef, Microsoft-Decision-1 and other decision models through one LiteLLM endpoint.
And test them in the Decisions tab of the playground:
docs.litellm.ai/docs/decisio…
LiteLLM (YC W23) retweeted
Microsoft 365 Copilot is now available through LiteLLM AI Gateway.
With LiteLLM and Copilot, it's now possible for your apps to answer questions like "summarize my emails and my last call”
docs.litellm.ai/docs/provide…
Our Usage dashboard just got a major refresh!
New charts and visuals for:
- Spend & token tracking: Break down cost, tokens, and requests across models, virtual keys, teams, and users.
- Agent attribution: See usage by agent (Claude Code, Codex, OpenCode, and more)
- Targeted insights: Filter by date range or user, then drill down into model, key, and MCP server activity.
LiteLLM (YC W23) retweeted
@LiteLLM open-sourced Moyai: isolated cloud workspaces, tests and PRs for review. Its 79% cost saving is an internal comparison, not a universal result. Compare task quality and total operating cost before switching. docs.litellm.ai/blog/moyai-o…
We're offering 3 months of LiteLLM Enterprise for free to @ycombinator founders and alumni (incl. ex-YC founders).
LiteLLM gateway helps you manage access, spend, and virtual keys. Enterprise adds org-wide controls:
- Org hierarchy: Team-level budgets, limits, and allowlists
- Delegated admin: Self-serve keys and member management
- SSO & SCIM: Okta, Azure AD, and Google Workspace
- Audit logs: Full activity and key tracking
- Spend controls: Real-time alerts and usage breakdown
- Guardrails: Per-team logging destinations
- Self-hosted: Private deployment + dedicated Slack support
Send a DM to Ishaan (@ishaan_jaff) or Krrish (@krrish_dh) to get 3 months of LiteLLM Enterprise free.
LiteLLM (YC W23) retweeted
If you're a developer building agents in production, @LiteLLM Lens now uses @typesafeai JEV to judge every agent run and tag the ones that went wrong, right in your logs.
JEV decides in ~130 ms, so it keeps up with 200K+ traces
Find your failing runs without reading traces one by one.
Day 0 support for Claude Haiku 5.5 (@AnthropicAI) on LiteLLM
Claude Haiku 5.5 costs a tenth of Haiku 4.5 per token.
Claude Haiku 5.5 pricing
- Input: $0.10 / MTok for prompts up to 100K tokens, $0.50 / MTok above
- Output: $0.50 / MTok, or $2.50 / MTok above 100K
- Cache read: $0.01 / MTok, or $0.05 / MTok above 100K
Get started with @claudeai Haiku 5.5: docs.litellm.ai/blog/claude-…