Update README.md

README.md

@@ -1,113 +1,35 @@
----
-title: README
-emoji: 📊
-colorFrom: blue
-colorTo: purple
-sdk: static
-pinned: false
----
 
-# The AI model built for deterministic developer tasks - 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.
 
-*   OCR, web scraping, web search, classification and more
-*   OpenAI chat completion API compatible
-*   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
-
-Fullsite: https://interfaze.ai
-
-## Model Comparison
-
-* Benchmark: MMLU-Pro
-  * interfaze-beta: 83.6
-  * GPT-4.1: 80.6
-  * Claude Sonnet 4: 83.7
-  * Gemini 2.5 Flash: 80.9
-  * Claude Sonnet 4 (Thinking): 83.7
-  * Claude Opus 4 (Thinking): 86
-  * GPT-5-Minimal: 80.6
-  * Gemini-2.5-Pro: 86.2
-* Benchmark: MMLU
-  * interfaze-beta: 91.38
-  * GPT-4.1: 90.2
-  * Claude Sonnet 4: -
-  * Gemini 2.5 Flash: -
-  * Claude Sonnet 4 (Thinking): 88.8
-  * Claude Opus 4 (Thinking): 89
-  * GPT-5-Minimal: -
-  * Gemini-2.5-Pro: 89.2
-* Benchmark: MMMU
-  * interfaze-beta: 77.33
-  * GPT-4.1: 74.8
-  * Claude Sonnet 4: -
-  * Gemini 2.5 Flash: 79.7
-  * Claude Sonnet 4 (Thinking): 74.4
-  * Claude Opus 4 (Thinking): 76.5
-  * GPT-5-Minimal: -
-  * Gemini-2.5-Pro: 82
-* Benchmark: AIME-2025
-  * interfaze-beta: 90
-  * GPT-4.1: 34.7
-  * Claude Sonnet 4: 38
-  * Gemini 2.5 Flash: 60.3
-  * Claude Sonnet 4 (Thinking): 74.3
-  * Claude Opus 4 (Thinking): 73.3
-  * GPT-5-Minimal: 31.7
-  * Gemini-2.5-Pro: 87.7
-* Benchmark: GPQA-Diamond
-  * interfaze-beta: 81.31
-  * GPT-4.1: 66.3
-  * Claude Sonnet 4: 68.3
-  * Gemini 2.5 Flash: 68.3
-  * Claude Sonnet 4 (Thinking): 77.7
-  * Claude Opus 4 (Thinking): 79.6
-  * GPT-5-Minimal: 67.3
-  * Gemini-2.5-Pro: 84.4
-* Benchmark: LiveCodeBench
-  * interfaze-beta: 57.77
-  * GPT-4.1: 45.7
-  * Claude Sonnet 4: 44.9
-  * Gemini 2.5 Flash: 49.5
-  * Claude Sonnet 4 (Thinking): 65.5
-  * Claude Opus 4 (Thinking): 63.6
-  * GPT-5-Minimal: 55.8
-  * Gemini-2.5-Pro: 75.9
-* Benchmark: ChartQA
-  * interfaze-beta: 90.88
-  * 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: -
-* Benchmark: AI2D
-  * interfaze-beta: 91.51
-  * GPT-4.1: 85.9
-  * Claude Sonnet 4: -
-  * Gemini 2.5 Flash: -
-  * Claude Sonnet 4 (Thinking): -
-  * Claude Opus 4 (Thinking): -
-  * GPT-5-Minimal: -
-  * Gemini-2.5-Pro: 89.5
-* Benchmark: Common-Voice-v16
-  * interfaze-beta: 90.8
-  * 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: -
 
+[Try now](https://interfaze.ai/dashboard) or [Read paper](https://www.arxiv.org/abs/2602.04101)
+
+- OCR, web scraping, web search, classification and more
+- OpenAI chat completion API compatible
+- 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
+
+### 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.
 
@@ -115,70 +37,219 @@ Fullsite: https://interfaze.ai
 
 OpenAI API compatible, works with every AI SDK out of the box
 
-OpenAI SDK
+```
+import OpenAI from "openai";
 
-Vercel AI SDK
+const interfaze = new OpenAI({
+    baseURL: "https://api.interfaze.ai/v1",
+    apiKey: "<your-api-key>"
+});
 
-Langchain SDK
+const completion = await interfaze.chat.completions.create({
+    model: "interfaze-beta",
+    messages: [\
+        {\
+            role: "user",\
+            content: "Get the company description of JigsawStack from their linkedin page",\
+        },\
+    ],
+});
 
-![Extraction](https://interfaze.ai/examples/extraction_example.png)
-
-![scraping](https://interfaze.ai/examples/scraper_example.png)
-
-Fully configurable guardrails for text and images
-
-![Extraction](https://interfaze.ai/examples/nsfw_example.jpg)
-
-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.
+console.log(completion.choices[0].message.content);
+```
 
-[![How it works](https://interfaze.ai/examples/howitworks.png)
+### OCR & Document Extraction
 
+[vision docs ->](https://interfaze.ai/docs/vision)
 
+```
+prompt = "Get the person information from the following ID."
 
-](/examples/howitworks.png)
+schema = z.object({
+  first_name: z.string(),
+  last_name: z.string(),
+  dob: z.string(),
+  expiry: z.string(),
+});
+```
 
-### Specs
+![Extraction](https://interfaze.ai/examples/extraction_example.png)
 
-Max output tokens
+### Smart Web Scraping
 
-32k tokens
+[web docs ->](https://interfaze.ai/docs/web)
 
-Input modalities
+```
+prompt = "Extract the information from Yoeven D Khemlani's linkedin page based on the schema."
 
-Text, Images, Audio, File, Video
+schema = z.object({
+  first_name: z.string(),
+  last_name: z.string(),
+  about: z.string(),
+  current_company: z.string(),
+  current_position: z.string(),
+});
+```
 
-Output tokens
+![scraping](https://interfaze.ai/examples/scraper_example.png)
 
-$3.50 / MTok
+### Translation
+
+[translation docs ->](https://interfaze.ai/docs/translation)
+
+```
+prompt = "The UK drinks about 100–160 million cups of tea every day, and 98% of tea drinkers add milk to their tea."
+
+schema = z.object({
+  zh: z.string(),
+  hi: z.string(),
+  es: z.string(),
+  fr: z.string(),
+  de: z.string(),
+  it: z.string(),
+  ja: z.string(),
+  ko: z.string(),
+});
+```
+
+```
+zh: 英国每天饮用约100–160百万杯茶，有98%的茶饮者在茶中加入牛奶。
+hi: यूके हर दिन लगभग 100–160 मिलियन कप चाय पीता है, और 98% चाय पीने वाले अपनी चाय में दूध मिलाते हैं।
+es: El Reino Unido bebe alrededor de 100–160 millones de tazas de té cada día, y el 98 % de los consumidores de té añade leche a su té.
+fr: Le Royaume-Uni boit environ 100–160 millions de tasses de thé chaque jour, et 98 % des buveurs de thé ajoutent du lait à leur thé.
+de: Das Vereinigte Königreich trinkt etwa 100–160 Millionen Tassen Tee pro Tag, und 98 % der Teetrinker fügen ihrem Tee Milch hinzu.
+it: Il Regno Unito beve circa 100–160 milioni di tazze di tè ogni giorno e il 98% degli amanti del tè aggiunge latte al proprio tè.
+ja: イギリスでは毎日約100～160百万杯の紅茶が飲まれており、紅茶を飲む人の98%が紅茶に牛乳を加えます。
+ko: 영국에서는 매일 약 1억 ~ 1억 6천만 잔의 차를 마시며, 차를 마시는 사람의 98%가 차에 우유를 넣습니다.
+```
+
+### Speech-to-text (STT) and diarization
+
+[stt docs ->](https://interfaze.ai/docs/speech-to-text)
+
+```
+prompt = "Transcribe https://jigsawstack.com/preview/stt-example.wav"
+
+schema = z.object({
+  text: z.string(),
+  speakers: z.object({
+    id: z.string(),
+    start: z.number(),
+    end: z.number()
+  })
+});
+```
+
+```
+{
+  "text": " The little tales they tell are false The door was barred, locked and bolted as well Ripe pears are fit for a queen's table A big wet stain was on the round carpet The kite dipped and swayed but stayed aloft The pleasant hours fly by much too soon The room was crowded with a mild wob The room was crowded with a wild mob This strong arm shall shield your honour She blushed when he gave her a white orchid The beetle droned in the hot June sun",
+  "speakers": [\
+    {\
+      "start":0,\
+      "end":4.78,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":4.78,\
+      "end":9.48,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":9.48,\
+      "end":13.06,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":13.06,\
+      "end":17.24,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":17.24,\
+      "end":21.78,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":21.78,\
+      "end":26.3,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":26.3,\
+      "end":30.76,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":30.76,\
+      "end":35.08,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":35.08,\
+      "end":39.24,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":39.24,\
+      "end":43.94,\
+      "id": "SPEAKER_00"\
+    },\
+    {\
+      "start":43.94,\
+      "end":48.5,\
+      "id": "SPEAKER_00"\
+    }\
+  ]
+}
+```
+
+### Configurable guardrails and NSFW checks
+
+[guardrails docs ->](https://interfaze.ai/docs/guard-rails)
 
-Observability & Logging
+Fully configurable guardrails for text and images
 
-Coming soon
+```
+S1: Violent Crimes
+S2: Non-Violent Crimes
+S3: Sex-Related Crimes
+S4: Child Sexual Exploitation
+S5: Defamation
+S6: Specialized Advice
+S7: Privacy
+S8: Intellectual Property
+S9: Indiscriminate Weapons
+S10: Hate
+S11: Suicide & Self-Harm
+S12: Sexual Content
+S12_IMAGE: Sexual Content (Image)
+S13: Elections
+S14: Code Interpreter Abuse
+```
+
+### Architecture
+
+[read paper ->](https://www.arxiv.org/abs/2602.04101)
 
-### FAQ
+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.
 
-### Todo (Prioritized)
+![How it works](https://interfaze.ai/examples/howitworks.png)
 
-*   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
-*   v1.1 Interfaze
-*   Reduce latency and improve throughput
-*   Custom SDKs for interfaze with AI SDK, Langchain, etc.
-*   Leaderboard for projects
+### Specs
 
-If you have feature requests or recommendations, please reach out!
+- Context window: 1m tokens
+- Max output tokens: 32k tokens
+- Input modalities: Text, Images, Audio, File, Video
+- Reasoning: Available
 
 ### Research references
 
-*   [Interfaze: The Future of AI is built on Task-Specific Small Models](https://www.arxiv.org/abs/2602.04101)
-*   [Agentic Context Engineering](https://www.arxiv.org/pdf/2510.04618)
-*   [Small Language Models are the Future of Agentic AI](https://arxiv.org/pdf/2506.02153)
-*   [The Sparsely-Gated Mixture-of-Experts Layer](https://arxiv.org/pdf/1701.06538)
-*   [DeepSeekMoE](https://arxiv.org/pdf/2401.06066)
-*   [Confronting LLMs with Traditional ML](https://arxiv.org/pdf/2310.14607)
+- [Interfaze: The Future of AI is built on Task-Specific Small Models](https://www.arxiv.org/abs/2602.04101)
+- [Agentic Context Engineering](https://www.arxiv.org/pdf/2510.04618)
+- [Small Language Models are the Future of Agentic AI](https://arxiv.org/pdf/2506.02153)
+- [The Sparsely-Gated Mixture-of-Experts Layer](https://arxiv.org/pdf/1701.06538)
+- [DeepSeekMoE](https://arxiv.org/pdf/2401.06066)
+- [Confronting LLMs with Traditional ML](https://arxiv.org/pdf/2310.14607)
 
 ### Who are we?