Isoquant (YC F26)

Self-optimizing inference cloud for faster, cheaper AI

[Aniket @anideshp]

Really excited to release ultra-fast DeepSeek v4.1 Flash 1017 on @isoquant_labs. Let us know what you think!

[Videh Seksaria @videhps]

This is so cool! 600 tokens/second is a game changer

[Isoquant (YC F26) @isoquant_labs]

DeepSeek V4.1 Flash 1017 runs at 600+ tok/s on Isoquant

Ships Tetris in 10 seconds, 8.7x faster than Claude Opus 5.5.

This is our AI optimizing AI, and we are passing performance wins and cost savings on to our customers:
→ 0.24s P50 / 1.16s P95 time to first token
→ $0.035 input / $0.005 cached / $0.37 output per 1M tokens

Keep your code and harness, just change the base URL. Works with your existing OpenAI and Anthropic SDK integrations.

No waitlist, live now: isoquant [dot] ai

[Isoquant (YC F26) @isoquant_labs]

0 to 1.2 TRILLION tokens in one month! 🚀

1000+ customers joined Isoquant for frontier quality, better tokenomics, lower latency, and more control over inference.

[Isoquant (YC F26) @isoquant_labs]

Today we’re publishing the Inference Engineering Benchmark: 6 frontier models on 15 tasks, from tokenizers and GPU kernels to complete serving stacks.

[Aniket @anideshp]

Gemini 4 Argon leads GPU optimization on Isoquant's new Inference Engineering Benchmark: a 4.38× mean speedup across 9 tasks, ahead of GPT-6 Astra (3.71×) and Muse Wonder 1.0 (3.66×).

We evaluate how well AI models improve inference performance across 15 tasks. 🧵

[Isoquant (YC F26) @isoquant_labs]

🙌

[Aniket @anideshp]

wgmi

[Aniket @anideshp]

wgmi

[Aniket @anideshp]

What a first week at Isoquant! More and more customers are trusting us with their production workloads. Looking for faster inference? Bring us your workload.

[Aniket @anideshp]

From 0 to 18 billion tokens served within 24 hours of launch! 🚀

Teams are moving real workloads to open models because they want frontier quality, better tokenomics, low latency and more control over inference.

@isoquantai gives them the infrastructure to make that shift.

[Isoquant (YC F26) @isoquant_labs]

We’re making AI cheaper and faster. We’re launching
Isoquant with GLM-5.3-Flash at just $0.07/M input, $0.20/M output and $0.014/M cached input. Median time to first token: 452 ms ⚡️

We’ve made breakthroughs across the inference stack, from GPU kernels to model serving, to drive down latency and cost, and we’re now bringing those gains to everyone through Isoquant.

Keep your code and harness. Change the endpoint. Works with coding harnesses like Codex, OpenCode and Cline, plus your existing OpenAI and Anthropic SDK integrations.

Supports streaming, tool calling, structured outputs, image inputs, automatic prompt caching, and zero data retention 🔒

We own performance engineering and serving end to end, so you can focus on your product.

Our ask: run one of your real workloads on Isoquant. Get an API key at https://t.co/Nr3FFjT8ae to get started.

We also support dedicated endpoints and specialist models for specific workloads. Want lower latency and cost for your company's workload? Book a time: https://t.co/TtALIkmeUr