Powered by JigsawStack
Interfaze - The AI model built for deterministic developer tasks
Interfaze is an AI model built on a new architecture that merges specialized DNN/CNN models with LLMs for developer tasks that require deterministic output and high consistency like OCR, scraping, classification, web search and more.
+===-----------------=++**++=---::::::::::::::::::::::::::::::--=+++++=-
%##*=--------------:---==+***++=---::::::::::::::::::::::::::::::-=+****=:.:
%%@%#===+++++++++++++++***#####*********++++++++++++++++++++++++++*######*=:::
%@@@#+=+*#****##############################****************###%%%%%%%%@@#=::-
%%@@#+-::=+******############%%%%%%%%%%%%%%######***********#%%%%%%%%%@@@%=::-
%%@@*-:...-+#%%@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@%+--=
%%@%+-....:%@@@@@@@@@@@@@%%%%%%%%#################******##%@@@@@@@@@@@@@@%**++
%%@%+:....-%%%@@@@@@%%%%%%%%%%%################***********#%%@@@@@@@@@@@@@#*++
%%@%+:....=%#%@@@@@@%%%%%%%%%################**************#%%@%@@@@@@@@@@#+==
%%@%+:....+#%@@@@@@@%%%%%%%%%################****************#%%@@@@@@@%@@*+--
%%@%+:...:*#%@@@@@@@%%%%%%%%%################************#****##%@@@@@@@@@*+-=
%%@%+:...:*#%@@@@@@@%%%%%%%%%################******#######*===+##@@@@@@%@@*+-=
%%@%=:...:##%@@@@@@%%%%%%%%%%######################%%%%%#*+:.:-*#@@@@@@%@@*+-=
%%@%=:...:##@@@@@@@%%%%%%%%%%#################%%%%%%%%%#*+=. .:+#@@@@@@%@@*+-=
%%%%=:...:%%@@@@@@@%%%%%%%%%%############%%%%%%%%%%%%##*+=-. .=#%@@@@@%@@#+==
%%@%=:...-%%@@@@@@@%%%%%%%%%%########%%%%%%%%%%%%%###**++=-. .-#%@@@@@%@@#+==
%%%%=:...-%%#%%%%######%%%%%%%%%%%%%%%%@@@@%%%%####*****++=:..:=#@@@@@@%@@#+==
%%%%=:...-%%#%###%%%###%%%%%%%%%%%%@@@@%%%%%%####********++=--=+%@@@@@@%%@#+==
%%%%=:...-%%%%%%%%%%%%%%#%%%%%%@@@@@%%%%%########**********+==+#%@@@@@@%%@#*==
%%%%=:...-%%#%%###########*##%%%@%%%%%############**********++*#@@@@@@@%%@#*==
%%%%=:...-%%%#%#%%%%%%%%%%#%%%%%%%%################***********#%@@@@@@@%%%#*==
%%%%=:...-@%@@@@@@@@@@@@@@%%%%%%%######################******##%@@@@@@%%%%#*==
%%%%=:...-@%@@@@@@@@@@@@@%%%%%%%%##############################@@@@@@@%%%%#*==
%%%#=::::=@%@@@@@@@@@@@%%%%%%%%%%%############################%@@@@@@@%%%%#*==
%%%%+=--=+%@@@@@@@@@@@%%%%%%%%%%%%%%##########################%@@@@@@@%%%%#*==
%%%%*+=--=%@%@@@@@@@@@%%%%%%%%%%%%%%%%#######################%@@@@@@@@%%%%#*==
%%%%*+-:.:*%%%@@@@@@@@@%%%%%%%%%%%%%%%%%%###################%@@@@@@@@%%%%%#*+=
##%#+-....+%%%@@@@@@@@@@%%%%%%%%%%%%%%%%%%%%%%%%%#########%%%@@@@@@@@%%%%%#*+=
%#%#=:....-%%%@@@@@@@@@@@@@@@@%%%%%%%%%%%%%%%%%%%%%%%%%%%%%@@@@@@@@@@%%%%%#*+=
%#%#=:.....-=+*#######%%%%%%@@@@@@@@@@@@@@@@@@@%%%%%%#####%%%%%%%@@@@@%%%%#*+=
##%#=:.....:::--==++++===---::::::::::::::::::::::::::::::::-=++***##%@@@%#*+=
####=:::-----------==+****++=-------------------:::::::::::::----=+**####%#*+=
####=::::::::::::::--==+++=--::::::::::::::::::::::::...........::-+********+=
####=::::::::::::::--=++++=--:::::::::::::::::::................::-+********++
###*=::::::::::::::-==++++=--::::::::::::::::..:--:::------------=+*##*####*++
###*=:::::::::::::--==++++=--::::::::::::-++:..+%%*:-+****+++++=+*##%%*%%%@#++
##**=:::::::::::::--==++++=--::::::::::-*##*-::-==-:..:........:::-+***####*++
#***+===============++++++==--------------:::::::::----------==+**##########
#**************************++++++++++++++++++++++++++****##%%%%%%%%%%%%%
###########################*******##########%%%%%%%%%%%%%%%###
#*++**#%@@@@@@@@@@@@@@@@@@%%%%%%%%%%%%%%%%@@@@@@@@@@@%#######
*+===+*#%%%%%####************+++++++++++++*##%%%%%%@@%######
***#####%###*****++++++++++++++++++++++**#%%%%%%%%@@@@@@ - OpenAI chat completion API compatible
- OCR, web scraping, STT, classification, internet access and more
- High accuracy structured output consistency
- Built-in code execution and sandboxing
- Custom web engine for scraping and web research capabilities
- Auto reasoning when needed
- Controllable guardrails
- Fully managed and scalable
- Globally distributed fallback system with high uptime
Beta launch video
Model Comparison
| Benchmark | interfaze-beta | GPT-4.1 | Claude Sonnet 4 | Gemini 2.5 Flash | Claude Sonnet 4 (Thinking) | Claude Opus 4 (Thinking) | GPT-5-Minimal | Gemini-2.5-Pro |
|---|---|---|---|---|---|---|---|---|
| MMLU-Pro | 83.6 | 80.6 | 83.7 | 80.9 | 83.7 | 86 | 80.6 | 86.2 |
| MMLU | 91.38 | 90.2 | - | - | 88.8 | 89 | - | 89.2 |
| MMMU | 77.33 | 74.8 | - | 79.7 | 74.4 | 76.5 | - | 82 |
| AIME-2025 | 90 | 34.7 | 38 | 60.3 | 74.3 | 73.3 | 31.7 | 87.7 |
| GPQA-Diamond | 81.31 | 66.3 | 68.3 | 68.3 | 77.7 | 79.6 | 67.3 | 84.4 |
| LiveCodeBench | 57.77 | 45.7 | 44.9 | 49.5 | 65.5 | 63.6 | 55.8 | 75.9 |
| ChartQA | 90.88 | - | - | - | - | - | - | - |
| AI2D | 91.51 | 85.9 | - | - | - | - | - | 89.5 |
| Common-Voice-v16 | 90.8 | - | - | - | - | - | - | - |
*Results for Non-Interfaze models are sourced from model providers, leaderboards, and evaluation providers such as Artificial Analysis.
Works like any other LLM
OpenAI API compatible, works with every AI SDK out of the box
OpenAI SDK
Vercel AI SDK
Langchain SDK
typescript
python
...
OCR & Document Extraction
...
Smart Web Scraping
...
Translation
...
...
Configurable guardrails and NSFW checks
Fully configurable guardrails for text and images
...
Speech-to-text (STT) and diarization
...
...
Architecture
read paper ->
This architecture combines a suite of small specialized models supported with custom tools and infrastructure while automatically routing to the best model for the task that prioritizes accuracy and speed.
Specs
Context window
1m tokens
Max output tokens
32k tokens
Input modalities
Text, Images, Audio, File, Video
Reasoning
Available
Pricing
Input tokens
$3 / MTok
Output tokens
$10 / MTok
Caching
Included
Observability & Logging
Included
FAQ
You can make 1000 requests per hour during the beta. We'll be increasing the rate limit significantly for the public release.
You can track your usage on the dashboard. We'll be adding more detailed metrics and analytics in the future.
We don't store or log any messages or prompts by default. When we do offer observability and logging in the future, you will have the option to allow or disallow storage.
We do expect many bugs and issues. Please report them to us at interfaze@jigsawstack.com
Please email us at interfaze@jigsawstack.com or reach out to Yoeven on X: https://x.com/yoeven
Todo (Prioritized)
- Reduce transactional token count
- Pre-built prompts/schemas optimized for specific tasks
- Embedding model
- Built-in observability and logging on the dashboard
- Complete metrics and analytics
- v0.2 Interfaze
- Reduce latency and improve throughput
- Custom SDKs for interfaze with AI SDK, Langchain, etc.
- Leaderboard for projects
If you have feature requests or recommendations, please reach out!
Research references
- Interfaze: The Future of AI is built on Task-Specific Small Models
- Agentic Context Engineering
- Small Language Models are the Future of Agentic AI
- The Sparsely-Gated Mixture-of-Experts Layer
- DeepSeekMoE
- Confronting LLMs with Traditional ML
Who are we?
We are a small team of ML, Software and Infrastructure engineers engrosed in the fact that a small model can do a lot more when specialized. Allowing us to make AI available in every dev workflow.