←
Respan859 posts
Respan avatar✓

Respan ✓

@RespanAI

The only AI router with observability & evals on every call. Creator of Span-02. OSS gateway: github.com/respanai/respan-g… Community: respan.ai/discord

◷ Joined March 2024▧ 281 Photos and videos
Respan avatar
Respan@RespanAI·Nov 16

Weekly drop #5 is live on the Respan AI Gateway. This week is a closed-source special. Every model in the drop comes from OpenAI, Anthropic, Google, or Meta. Top deal: Gemini 4 Argon, 55% off. $1.80 in / $9.00 out per 1M tokens. Also this week: Gemini 4 Carbon: 55% off Gemini 3.8 Flash: 50% off Muse Ember: 20% off GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Astra, GPT-6 Luna: 18% off Claude Opus 5.5: 10% off Claude Fable 5.2: 7% off No transaction fees. No markup. New drop every Monday.

Post attachment
Frank Chen avatar
⟳ Respan retweeted
Frank Chen@francchen·11h

Made by Respan Gateway for Respan Gateway One shot from gemini omni 1.2 flash respan.ai/gateway

0:15
Respan avatar
Respan@RespanAI·19h

day-0 support for GPT-6.2 Sol and Astra, and Sol is free for the next 24 hours!

Post attachment
Respan avatar
Respan@RespanAI·Nov 16

We’ve shipped so much that our old demo doesn’t describe @RespanAI anymore. So we recorded a new one 👇 → Gateway: best model discounts, now fully open source → Observability: auto-grouped sessions, turn by turn, just like your Claude Code chats → Evals: every request analyzed by span-02, our frontier decision model specially trained for model behaviors And Respan 2.0 is coming next. demo.respan.ai

4:08
Respan avatar
Respan@RespanAI·Nov 13

We’re seeing more people build with realtime and live chat. Respan OSS Gateway was built for compatibility from day one, and now we’re putting more into realtime. Through Respan, realtime models are interchangeable: keep your OpenAI Realtime client, switch to Gemini Live or Phonic.

0:11
Bing Wu avatar
⟳ Respan retweeted
Bing Wu@_bingwu·Nov 12

Retell just crossed $100M in revenue run rate. $10M to $100M in 17 months. Profitable. $4.6M raised. From day one, we’ve focused on solving the hardest parts of deploying voice AI in the product itself, so customers can build, manage, and improve their own agents without depending on us. Our bet: the future of the contact center belongs to the teams who run it. Proud of our team. Grateful to every customer who believed in us.

1:47
Coffee with One 🇺🇸 avatar
⟳ Respan retweeted
Coffee with One 🇺🇸@coffeewithone·Nov 11

We trained a custom model to kill the only moat CRMs have, switching cost. @RespanAI asked @octolane to migrate them off Attio to Octolane. Octolane migrated years of their data in under 4 minutes. That’s Exodus 1, our in-house migration model. It reads your old CRM’s schema, maps every custom field and object, carries over full conversation history, and enriches every account and contact in flight. Attio customers now migrate in under 5 minutes. HubSpot customers in under 20. And we’re already training Exodus 2 to migrate Salesforce customers in under 30 minutes.

1:52
Kelly Liu avatar
⟳ Respan retweeted
Kelly Liu@kelly_zhuoer·Nov 10

hi @X i'm Kelly! sf-based, looking for more friends in tech :) a lil about me: > journalism grad > used to make documentaries > now making launch videos at an AI startup > learning to code with claude code, slowly would love to meet anyone building cool things, especially if you still shoot film for fun 📷

Post attachment
Frank Chen avatar
⟳ Respan retweeted
Frank Chen@francchen·Nov 9

Prompt caching: why does Anthropic only offer 5-minute and 1-hour options? It comes down to where your cache is stored. A cache can sit in GPU memory (fast, expensive) or CPU memory (slower, much cheaper). Either way, keeping it costs money every minute. At some point it costs more than just rereading your prompt. I did the math. The break-even point: ~5 minutes on GPU (HBM) ~1.5 hours in CPU memory (DRAM) So when you pick 5 minutes or 1 hour, you’re really telling Anthropic where to store your cache.

Post attachment
Hendrix Liu avatar
⟳ Respan retweeted
Hendrix Liu@HendrixLiu29208·Nov 9

we’re making Muse Ember free! Meta’s newest and most cost-efficient model built for high-volume agent work. no payment or credit card required. 1. create an API key on @RespanAI 2. call meta/muse-ember:free fyi: free usage has a token limit. deposit $5 to raise it (still free).

Post attachmentPost attachmentPost attachment
Respan avatar
Respan@RespanAI·Nov 9

Claude Fable 5.2 is live on the Respan Gateway. Respan-only launch deal: 15% off, this week only $6.80 in / $34 out per 1M tokens (was $8 / $40) 1M context · 128K max output · adaptive thinking Model: anthropic/claude-fable-5.2

Post attachment