Interfaze (YC P26)

The AI model built for deterministic developer tasks

[Interfaze (YC P26) @interfaze_ai]

The audience was amazing, super technical and we went into great depth about the architecture

[Postman @getpostman]

[Recording Available!] Recorded live on May 27, 2026, San Francisco - Agents & APIs SF Developer Meetup. Demos by @public, @Firebase, @interfaze_ai & @getpostman. Check it out! https://t.co/sv1XRMhQNX

[Yoeven @yoeven]

Every one in the team gets this and any one who crosses one year, signs the one in the office

Quotes reminding us to stay on track anytime we're lost

[Yoeven @yoeven]

Presenting at Postman

[patricia_dugan @patricia_dugan]

Super grateful to @yoeven of @interfaze_ai, @BuildwithPublic & @TarricSookdeo of @public, and my colleague @tristandenyer of @getpostman for their solid demos at tonight’s meetup!!

[Interfaze (YC P26) @interfaze_ai]

Does the ability to refuse make a model more intelligent?

https://t.co/Y9SxEH7aHK

[Yoeven @yoeven]

We ran Extend's Parse 2.0 on OlmOCR to get a better perspective on where it stand across LLMs and other specialized OCR providers

[Interfaze (YC P26) @interfaze_ai]

@khurdula Interfaze Mascot?

[Interfaze (YC P26) @interfaze_ai]

Full breakdown: https://t.co/EiEsFlKEIq

[Interfaze (YC P26) @interfaze_ai]

We've added the latest flash model to the suite of 9 benchmarks for tasks like OCR, Object detection, ASR

Interfaze outperforms Gemini 3.5 flash while being 2.6x cheaper

[Interfaze (YC P26) @interfaze_ai]

Interfaze provides the most value per dollar with the previous Gemini 3 flash preview coming close

[Harsha @khurdula]

Presenting at AI Engineer in Singapore

Broke down how Interfaze works and the evolution of AI

The audience was great and Singapore was amazing

[Yoeven @yoeven]

We don't really think Gemini 3.5 flash is truly a flash series model based on pricing but we still ran benchmarks

Interfaze outperforms on OCR & Object detection while being 3x less the cost

3.5 flash does better than 3 flash, so would any Pro model at that price range

[Yoeven @yoeven]

Not sure why is Gemini flash 3.5 even considered a flash model based on its pricing

Seems pretty far away from what users would pay for production workflow use cases

And if the focus is coding, it seems far behind compared to gpt 5.5/opus 4.7 even with all that benchmaxing

[Interfaze (YC P26) @interfaze_ai]

Awesome breakdown on Interfaze!

[Better Stack @BetterStackHQ]

Can a new AI architecture completely stop hallucinations? Here is a breakdown of how Interfaze works and how it performed against generalist models when parsing messy, real-world data.

[Interfaze (YC P26) @interfaze_ai]

Legend

[Nehal @NehallAgrawal]

🛑[LIVE] on day 3 of @aiDotEngineer 🇸🇬

@khurdula, co-founder and CTO of @interfaze_ai on building alternative architecture designed for deterministic developer tasks.

“The solution is: Task specific DNNs + CNNs + Transformers”

[Interfaze (YC P26) @interfaze_ai]

@Raghavendra_K_M Check out the fully methodology and breakdown here https://t.co/EnvpSam8yn

[Interfaze (YC P26) @interfaze_ai]

Interfaze is a new model architecture that outperforms in tasks like OCR, Object detection, Translation and more

It beats models like Claude Sonnet 4.6, Gemini 3 flash and GPT 5.4 mini on 9 benchmarks

[Interfaze (YC P26) @interfaze_ai]

Orchestrator implies a one way delegation or tool call but how it actually works is specialized DNN encoder layers which are Small models (SM) not SLM since they aren't language/transformer based layers.

The CNN/DNNs are encoded within the same vector space as the base transformer which act as the orchestrator kinda similar to MoE models but done with DNNs.

[Interfaze (YC P26) @interfaze_ai]

@avivsinai Supported languages: https://t.co/lUI7jyjGeI

Language benchmark: https://t.co/lUI7jyjGeI

[Interfaze (YC P26) @interfaze_ai]

@bygregorr @aaron_epstein Both, benchmarks are industry standard way to have broad tasks but we work with customers with much worse data quality for extraction. We'll be dropping way me explains on different use cases! Stay tuned.

[Interfaze (YC P26) @interfaze_ai]

@Dadojvk Yup depending on the use case. We outperform on deterministic tasks like OCR, objection detection, etc