Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Respan Router, powered by Span-01. Automatically routes every request using task context, model capabilities, and cache-aware cost estimates behind 1 model id: 𝐬𝐩𝐚𝐧-𝐫𝐨𝐮𝐭𝐞𝐫 - 13% lower latency than jev-router on τ-bench airline - 37% cheaper than the most accurate single model, at matching accuracy - 0% processing fee... show more

Respan

3,280 subscribers

18,112 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Built a model router with Jev by TypeSafe AI. Jev decides what model fits your request best and the request is sent to that model.

Built a model router with Jev by TypeSafe AI. Jev decides what model fits your request best and the request is sent to that model.

Duncan

120,065 views • 1 month ago

Meet Auto, our upgraded model router 🔀 Frontier quality at 90% lower cost. It matches each task to the right model, balancing quality, speed, and cost. And if it gets stuck, it changes course.

Meet Auto, our upgraded model router 🔀 Frontier quality at 90% lower cost. It matches each task to the right model, balancing quality, speed, and cost. And if it gets stuck, it changes course.

Notion

41,352 views • 13 days ago

Doc-OCR router using Jev TypeSafe AI A Jev-powered router that looks at a PDF page by page, decides which pages actually need OCR, extracts the rest locally. Result: save cost on # OCR pages + speed

Doc-OCR router using Jev TypeSafe AI A Jev-powered router that looks at a PDF page by page, decides which pages actually need OCR, extracts the rest locally. Result: save cost on # OCR pages + speed

Misbah Syed

27,028 views • 1 month ago

You can now use Jev right inside Claude Code 🤯 It's called jev-model-router, an early access mod built on Claude Code's new function hooks. Before every turn, it checks in with Jev and asks: > how mechanical the task is > how much reasoning it needs > whether it's risky Then it routes: → it'll move up to a stronger model on weak evidence, and only drops to a cheaper one when it's confident the task is simple → every decision gets logged in your transcript → if the call fails, your request runs untouched Setup: 1. copy the install command: npx claude-code-templates@latest --mod productivity/jev-model-router 2. paste it inside Claude Code 3. run claude with CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1 set 4. accept the trust prompt on first launch Link: Also works with no api key, it just falls back to a built-in classifier with no confidence score. For real jev routing, add your typesafeApiKey or gatewayApiKey to ~/.claude/settings.json. Follow me for more AI workflows and tutorials.

You can now use Jev right inside Claude Code 🤯 It's called jev-model-router, an early access mod built on Claude Code's new function hooks. Before every turn, it checks in with Jev and asks: > how mechanical the task is > how much reasoning it needs > whether it's risky Then it routes: → it'll move up to a stronger model on weak evidence, and only drops to a cheaper one when it's confident the task is simple → every decision gets logged in your transcript → if the call fails, your request runs untouched Setup: 1. copy the install command: npx claude-code-templates@latest --mod productivity/jev-model-router 2. paste it inside Claude Code 3. run claude with CLAUDE_CODE_ENABLE_FUNCTION_HOOKS=1 set 4. accept the trust prompt on first launch Link: Also works with no api key, it just falls back to a built-in classifier with no confidence score. For real jev routing, add your typesafeApiKey or gatewayApiKey to ~/.claude/settings.json. Follow me for more AI workflows and tutorials.

Alvaro Cintas

44,149 views • 1 month ago

The opposite of token-maxxing isn’t giving up on AI. It’s using the right model for the right task. The new Auto router in Notion handles that for you.

The opposite of token-maxxing isn’t giving up on AI. It’s using the right model for the right task. The new Auto router in Notion handles that for you.

Akshay Kothari

13,588 views • 14 days ago

Monitor and control your AI spend on every provider on Our early users save 40% on average. Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue. Tradeoffs between latency, reasoning, cost, service tier, open source and closed source models are shifting constantly. Router sends every request to the model that's actually best for the task and helps you control what tokens you buy. We benchmark it against real work: ~40% lower cost for the same outputs. Today we're opening it to everyone. Two lines of code or just change your base URL. No Ramp account needed. Free through 2026, first $26 on us. Get an API key today at

Monitor and control your AI spend on every provider on Our early users save 40% on average. Every week, the price-intelligence-latency frontier shifts, and we expect this trend to continue. Tradeoffs between latency, reasoning, cost, service tier, open source and closed source models are shifting constantly. Router sends every request to the model that's actually best for the task and helps you control what tokens you buy. We benchmark it against real work: ~40% lower cost for the same outputs. Today we're opening it to everyone. Two lines of code or just change your base URL. No Ramp account needed. Free through 2026, first $26 on us. Get an API key today at

Veeral Patel

1,431,425 views • 2 months ago

Opus 5 is the best Claude model on ReactBench Better at frontend code than Claude Fable 5 and >2x cheaper (!!)

Opus 5 is the best Claude model on ReactBench Better at frontend code than Claude Fable 5 and >2x cheaper (!!)

Aiden Bai

48,060 views • 3 months ago

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.

50% cheaper Claude inference with just one line of code change! - Remove → model="claude-opus-4-8" - Add → model="ship-like/claude-opus-4-8" I verified the cost saving in my own terminal by invoking the same Anthropic model with the same prompt. The underlying engineering by Ship is actually interesting, and the patterns can be used in any production LLM stack. Essentially, a trained model is a frozen artifact. Every request performs the same forward-pass, whether it extracts a date or refactors a module, because the compute decision was made at training time, before the request existed. Ship makes that decision at inference time instead. After seeing a request, it searches over executions, involving single models, cascades, ensembles, or harnesses with tools, and serves the cheapest one that will match the reference model's quality. This is not a basic router, because picking a cheaper model per query doesn't ensure the cheaper model preserves the original's behavior, like output shape, tool-call patterns, and refusals. Ship measures this equivalence directly. Outputs stay distributionally indistinguishable from the reference model, not token-identical, since two calls to the same model already differ, but they are indistinguishable in capability and behavior. Of course, some requests execute cheaply and some cost Ship more than the customer pays, but the price per request is still a flat 50% off either way, so the execution-cost variance moves off the application's bill entirely. The video below depicts the cost savings and output in my real invocation, and I partnered with the team to put this together.

Akshay 🚀

64,482 views • 3 months ago

$TSLA 🇰🇷 The Model 3 RWD and Model Y L sold in Korea are cheaper than any other country. • Model 3 RWD ($28,000~) • Model Y L ($43,000~)

$TSLA 🇰🇷 The Model 3 RWD and Model Y L sold in Korea are cheaper than any other country. • Model 3 RWD ($28,000~) • Model Y L ($43,000~)

Tsla Chan

17,263 views • 7 months ago

Introducing the AI Registry Discover all models in the AI SDK AI Gateway: 🔍 Filter by: - Name - Input/output modalities - Context length - Output size - Providers 📄 View model details ⚖️ Compare model vs. model Open-source, link below!

Introducing the AI Registry Discover all models in the AI SDK AI Gateway: 🔍 Filter by: - Name - Input/output modalities - Context length - Output size - Providers 📄 View model details ⚖️ Compare model vs. model Open-source, link below!

Francisco Moretti

10,449 views • 1 year ago

Introducing $JTVO Staking Stake JTVO to fund GPUs that run open-source models for you: automatically, and fully private. Every other model is still one key away on the Jatevo gateway. live on this end of the week

Introducing $JTVO Staking Stake JTVO to fund GPUs that run open-source models for you: automatically, and fully private. Every other model is still one key away on the Jatevo gateway. live on this end of the week

Jatevo

12,327 views • 1 month ago

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

Superman

105,212 views • 3 months ago

AMAZON SENIOR DEVELOPER BUILT A CONTEXT PIPELINE THAT DECIDES WHAT THE MODEL EVEN GETS TO SEE Most teams still dump the entire codebase into every prompt and hope it sorts itself out. He ranked every file by relevance to the task instead of how recently it was touched. A router decides how much context each task earns, a typo fix pulls three files, a full rewrite pulls the whole module. Whatever survives gets compressed to the exact lines that actually matter, so nothing bloats the window with dead weight. Token cost per finished task dropped the moment the model stopped reading dead weight just to fix one function. See how the four stages work together below👇

AMAZON SENIOR DEVELOPER BUILT A CONTEXT PIPELINE THAT DECIDES WHAT THE MODEL EVEN GETS TO SEE Most teams still dump the entire codebase into every prompt and hope it sorts itself out. He ranked every file by relevance to the task instead of how recently it was touched. A router decides how much context each task earns, a typo fix pulls three files, a full rewrite pulls the whole module. Whatever survives gets compressed to the exact lines that actually matter, so nothing bloats the window with dead weight. Token cost per finished task dropped the moment the model stopped reading dead weight just to fix one function. See how the four stages work together below👇

wast3

24,029 views • 2 months ago

Routing for long-horizon coding agents is a big deal. Not Diamond just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before each turn in a session, runs through a privacy-preserving local proxy, and your requests still execute through your own gateway. In their benchmarks, it approximates Opus 4.8 Xhigh quality at 39 to 61 percent lower cost.

Routing for long-horizon coding agents is a big deal. Not Diamond just announced a model router that works natively with Claude Code. This is huge. It picks the model and reasoning effort before each turn in a session, runs through a privacy-preserving local proxy, and your requests still execute through your own gateway. In their benchmarks, it approximates Opus 4.8 Xhigh quality at 39 to 61 percent lower cost.

elvis

13,699 views • 3 months ago

HOLY MOLY: Aikido got GPT-6 Astra in advance to run it on our Cybersecurity benchmark, it crushed EVERY other model! - At pass@3 it rediscovered 29/32 CVEs, the highest recall we've ever recorded and 4 more than GPT-5.6-Sol - Even at pass@1, it has 75% recall. The model is VERY consistent - The performance however come at a high price (literally). The three runs cost us almost $4,000 Astra is now the #1 model on the benchmark Debarshi and I built, and by a LOT 1/3 🧵

HOLY MOLY: Aikido got GPT-6 Astra in advance to run it on our Cybersecurity benchmark, it crushed EVERY other model! - At pass@3 it rediscovered 29/32 CVEs, the highest recall we've ever recorded and 4 more than GPT-5.6-Sol - Even at pass@1, it has 75% recall. The model is VERY consistent - The performance however come at a high price (literally). The three runs cost us almost $4,000 Astra is now the #1 model on the benchmark Debarshi and I built, and by a LOT 1/3 🧵

pilvar (Philippe Dourassov)

49,470 views • 1 month ago

This is absolutely f*cking insane. you can put a $0.042-per-million-token model in front of Claude and let it decide what Claude ever has to see. that's Jev signal routing, and the trick is stupidly simple: Jev takes the first look at everything. Claude only gets the hard cases. instead of: data -> Claude -> tokens burnt $ it's: data -> Jev -> only the unsure ones -> Claude and here's the part people miss. every Jev answer comes with a probability. that's your router: -> Jev is sure? its answer is final -> Jev hesitates? the case goes up to Claude set the cutoff once, by testing on your own data, not by guessing. 3 repos that already do the routing for you: -> duckdb-jev: route your data. Jev labels every row straight from SQL, up to 1,000 calls in one request -> quicksilver: route your files. Jev checks all 187 files in parallel and Claude gets the 4 that matter. ~2.4k tokens instead of ~26k -> jev-router: route your models. before every message Jev decides simple or hard and sends it to the fast model or the strong one. works with your normal Claude login where this pays off right away: -> support tickets -> your inbox -> lead lists -> messy spreadsheets -> comment moderation on a public benchmark Jev labeled 1,000 rows for $0.015. Claude charged $0.80 for the same job. faster. cheaper. way fewer tokens burned. Jev sorts the mail so the genius only opens what matters. Claude thinks. Jev routes. code does the job.

This is absolutely f*cking insane. you can put a $0.042-per-million-token model in front of Claude and let it decide what Claude ever has to see. that's Jev signal routing, and the trick is stupidly simple: Jev takes the first look at everything. Claude only gets the hard cases. instead of: data -> Claude -> tokens burnt $ it's: data -> Jev -> only the unsure ones -> Claude and here's the part people miss. every Jev answer comes with a probability. that's your router: -> Jev is sure? its answer is final -> Jev hesitates? the case goes up to Claude set the cutoff once, by testing on your own data, not by guessing. 3 repos that already do the routing for you: -> duckdb-jev: route your data. Jev labels every row straight from SQL, up to 1,000 calls in one request -> quicksilver: route your files. Jev checks all 187 files in parallel and Claude gets the 4 that matter. ~2.4k tokens instead of ~26k -> jev-router: route your models. before every message Jev decides simple or hard and sends it to the fast model or the strong one. works with your normal Claude login where this pays off right away: -> support tickets -> your inbox -> lead lists -> messy spreadsheets -> comment moderation on a public benchmark Jev labeled 1,000 rows for $0.015. Claude charged $0.80 for the same job. faster. cheaper. way fewer tokens burned. Jev sorts the mail so the genius only opens what matters. Claude thinks. Jev routes. code does the job.

kiosa

11,388 views • 9 days ago

everyone on x: "astra is cooked. opus 5.5 is agi" me: i can't switch tools every other week when a new model drops Ramp router: you shouldn't have to

everyone on x: "astra is cooked. opus 5.5 is agi" me: i can't switch tools every other week when a new model drops Ramp router: you shouldn't have to

jpa

10,798 views • 1 month ago

With iOS 27 Apple introduced its most powerful on-device model: AFM 3 Core Advanced It’s a 20 billion parameters model activating only between 1 to 4 billion parameters depending on the request Here’s the model running on iPhone 17 Pro

With iOS 27 Apple introduced its most powerful on-device model: AFM 3 Core Advanced It’s a 20 billion parameters model activating only between 1 to 4 billion parameters depending on the request Here’s the model running on iPhone 17 Pro

Adrien Grondin

472,311 views • 1 month ago

Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.

Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.

Claude

6,793,336 views • 26 days ago