API Documentation

Complete reference for all Brainiall APIs

Authentication

All endpoints accept any of these headers (use one):

Ocp-Apim-Subscription-Key: YOUR_KEY Authorization: Bearer YOUR_KEY api-key: YOUR_KEY

Base URL: https://api.brainiall.com

API Endpoint

https://api.brainiall.com/v1

OpenAI-compatible API. Works with any tool that supports custom OpenAI endpoints.

Coding Tools

Cline / Roo Code / Kilo Code

Settings > API Provider > OpenAI Compatible (or Brainiall if available)

Base URL: https://api.brainiall.com/v1

API Key: [your brnl- key]

Model: claude-opus-4-6

Continue.dev

Add to ~/.continue/config.yaml (or config.json):

models:
  - provider: openai
    title: Brainiall (Claude Haiku)
    model: claude-haiku-4-5
    apiBase: https://api.brainiall.com/v1
    apiKey: YOUR_KEY

Works with any model from /v1/models. Continue.dev OpenAI docs →

Cursor

Settings > Models > Add Model > OpenAI Compatible

Base URL: https://api.brainiall.com/v1

API Key: [your brnl- key]

Model: claude-haiku-4-5

Windsurf (Codeium)

Cascade > Settings > Add Custom Model

Provider: OpenAI Compatible

API Base: https://api.brainiall.com/v1

API Key: [your brnl- key]

Model: claude-haiku-4-5

Aider

export OPENAI_API_BASE=https://api.brainiall.com/v1
export OPENAI_API_KEY=YOUR_KEY
aider --model openai/claude-haiku-4-5

REST API

POST /v1/chat/completions

Generate a chat completion. Supports streaming, tools, and all OpenAI-compatible parameters.

curl https://api.brainiall.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.brainiall.com/v1",
    api_key="YOUR_KEY",
)

response = client.chat.completions.create(
    model="claude-haiku-4-5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.brainiall.com/v1",
  apiKey: "YOUR_KEY",
});

const response = await client.chat.completions.create({
  model: "claude-haiku-4-5",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

GET /v1/models

List all available models and their pricing.

curl https://api.brainiall.com/v1/models \
  -H "Authorization: Bearer YOUR_KEY"

Popular Models

Model	Input $/MTok	Output $/MTok	Features
claude-opus-4-6	$5.00	$25.00	Flex, Cache, Tools, Reasoning
claude-sonnet-4-6	$3.00	$15.00	Flex, Cache, Tools, Reasoning
claude-haiku-4-5	$1.00	$5.00	Flex, Cache, Tools
deepseek-r1	$1.35	$5.40	Flex, Cache, Reasoning
deepseek-v3	$0.27	$1.10	Flex, Tools
llama-3.3-70b	$0.72	$0.72	Flex, Tools
nova-pro	$0.80	$3.20	Flex, Cache, Tools
nova-micro	$0.035	$0.14	Flex, Streaming

Full list: GET /v1/models — 113+ models available. Flex pricing saves 50% on supported models.

Pronunciation assessment, speech-to-text, text-to-speech, and Whisper transcription.

POST /v1/pronunciation/assess/base64

Assess pronunciation accuracy from base64-encoded audio.

Request body:

{
  "audio_base64": "<base64-audio>",
  "text": "Hello world",
  "language": "en-US"
}

Response:

{
  "overall_score": 85.2,
  "pronunciation_score": 82.0,
  "fluency_score": 90.1,
  "words": [...]
}

curl -X POST https://api.brainiall.com/v1/pronunciation/assess/base64 \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_base64":"...","text":"Hello world","language":"en-US"}'

import httpx, base64

audio_b64 = base64.b64encode(open("audio.wav", "rb").read()).decode()
resp = httpx.post(
    "https://api.brainiall.com/v1/pronunciation/assess/base64",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"audio_base64": audio_b64, "text": "Hello world", "language": "en-US"},
)
print(resp.json())

const fs = require("fs");
const audio = fs.readFileSync("audio.wav").toString("base64");
const resp = await fetch("https://api.brainiall.com/v1/pronunciation/assess/base64", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ audio_base64: audio, text: "Hello world", language: "en-US" }),
});
console.log(await resp.json());

POST /v1/stt/transcribe/base64

Transcribe speech to text from base64-encoded audio (Azure Speech Services).

Request body:

{
  "audio_base64": "<base64-audio>",
  "language": "en-US"
}

Response:

{
  "text": "Hello world",
  "confidence": 0.95
}

curl -X POST https://api.brainiall.com/v1/stt/transcribe/base64 \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_base64":"...","language":"en-US"}'

import httpx, base64

audio_b64 = base64.b64encode(open("audio.wav", "rb").read()).decode()
resp = httpx.post(
    "https://api.brainiall.com/v1/stt/transcribe/base64",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"audio_base64": audio_b64, "language": "en-US"},
)
print(resp.json()["text"])

const audio = require("fs").readFileSync("audio.wav").toString("base64");
const resp = await fetch("https://api.brainiall.com/v1/stt/transcribe/base64", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ audio_base64: audio, language: "en-US" }),
});
console.log((await resp.json()).text);

POST /v1/tts/synthesize

Convert text to speech. Returns audio binary (WAV format).

Request body:

{
  "text": "Hello, welcome!",
  "voice": "en-US-JennyNeural"
}

Response:

Binary audio data (WAV)
Content-Type: audio/wav

curl -X POST https://api.brainiall.com/v1/tts/synthesize \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hello, welcome!","voice":"en-US-JennyNeural"}' \
  --output speech.wav

POST /v1/tts/synthesize/stream

Streaming text-to-speech. Returns chunked audio for low-latency playback.

Same request body as /v1/tts/synthesize.
Response: chunked audio stream (Transfer-Encoding: chunked).

GET /v1/tts/voices

List all available TTS voices with language and gender info.

curl https://api.brainiall.com/v1/tts/voices \
  -H "Authorization: Bearer YOUR_KEY"

POST /v1/whisper/transcribe/base64

Transcribe audio using OpenAI Whisper (GPU-accelerated). Supports 99+ languages with automatic detection.

Request body:

{
  "audio_base64": "<base64-audio>"
}

Response:

{
  "text": "Hello world",
  "language": "en",
  "segments": [...]
}

curl -X POST https://api.brainiall.com/v1/whisper/transcribe/base64 \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_base64":"..."}'

Text analysis APIs — toxicity detection, sentiment analysis, named entities, PII detection, and language identification. All endpoints accept {"text": "..."} and respond in <200ms.

POST /v1/nlp/toxicity $0.001/request

Detect toxic, offensive, or harmful content in text.

Request body:

{ "text": "This is amazing!" }

Response:

{
  "is_toxic": false,
  "score": 0.0012,
  "label": "not_toxic"
}

curl -X POST https://api.brainiall.com/v1/nlp/toxicity \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"This product is absolutely amazing"}'

import httpx

resp = httpx.post(
    "https://api.brainiall.com/v1/nlp/toxicity",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"text": "This product is absolutely amazing"},
)
print(resp.json())

const resp = await fetch("https://api.brainiall.com/v1/nlp/toxicity", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ text: "This product is absolutely amazing" }),
});
console.log(await resp.json());

POST /v1/nlp/sentiment $0.001/request

Analyze sentiment polarity (positive/negative) with confidence score.

Request body:

{ "text": "I love this product!" }

Response:

{
  "label": "POSITIVE",
  "score": 0.9987
}

curl -X POST https://api.brainiall.com/v1/nlp/sentiment \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"I love this product!"}'

import httpx

resp = httpx.post(
    "https://api.brainiall.com/v1/nlp/sentiment",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"text": "I love this product!"},
)
print(resp.json())

const resp = await fetch("https://api.brainiall.com/v1/nlp/sentiment", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ text: "I love this product!" }),
});
console.log(await resp.json());

POST /v1/nlp/entities $0.002/request

Extract named entities (people, organizations, locations, etc.) from text.

Request body:

{ "text": "John works at Google" }

Response:

{
  "entities": [
    {"text":"John","label":"PER",
     "start":0,"end":4,"score":0.99},
    {"text":"Google","label":"ORG",
     "start":14,"end":20,"score":0.98}
  ]
}

curl -X POST https://api.brainiall.com/v1/nlp/entities \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"John works at Google in Mountain View"}'

import httpx

resp = httpx.post(
    "https://api.brainiall.com/v1/nlp/entities",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"text": "John works at Google in Mountain View"},
)
print(resp.json())

const resp = await fetch("https://api.brainiall.com/v1/nlp/entities", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ text: "John works at Google in Mountain View" }),
});
console.log(await resp.json());

POST /v1/nlp/pii $0.002/request

Detect personally identifiable information (email, phone, SSN, credit card, IP address).

Request body:

{ "text": "Email me at john@ex.com" }

Response:

{
  "pii_detected": true,
  "entities": [
    {"text":"john@ex.com",
     "type":"email",
     "start":12,"end":23}
  ]
}

curl -X POST https://api.brainiall.com/v1/nlp/pii \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Contact me at john@example.com or 555-123-4567"}'

import httpx

resp = httpx.post(
    "https://api.brainiall.com/v1/nlp/pii",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"text": "Contact me at john@example.com or 555-123-4567"},
)
print(resp.json())

const resp = await fetch("https://api.brainiall.com/v1/nlp/pii", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ text: "Contact me at john@example.com or 555-123-4567" }),
});
console.log(await resp.json());

POST /v1/nlp/language $0.0005/request

Detect the language of a given text with confidence score.

Request body:

{ "text": "Bonjour, comment allez-vous?" }

Response:

{
  "language": "fr",
  "confidence": 0.9995
}

curl -X POST https://api.brainiall.com/v1/nlp/language \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Bonjour, comment allez-vous?"}'

GPU-accelerated image processing — background removal (BiRefNet), upscaling (ESRGAN), and face restoration (GFPGAN). All endpoints accept and return base64-encoded images.

POST /v1/image/remove-background/base64 $0.005/image

Remove background from an image using BiRefNet. Returns transparent PNG.

Request body:

{
  "image_base64": "<base64-image>"
}

Response:

{
  "image_base64": "<result-png>"
}

IMG=$(base64 -i photo.jpg)
curl -X POST https://api.brainiall.com/v1/image/remove-background/base64 \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"image_base64\":\"$IMG\"}"

import httpx, base64

img_b64 = base64.b64encode(open("photo.jpg", "rb").read()).decode()
resp = httpx.post(
    "https://api.brainiall.com/v1/image/remove-background/base64",
    headers={"Authorization": "Bearer YOUR_KEY"},
    json={"image_base64": img_b64},
    timeout=30,
)
result = base64.b64decode(resp.json()["image_base64"])
open("result.png", "wb").write(result)

const fs = require("fs");
const img = fs.readFileSync("photo.jpg").toString("base64");
const resp = await fetch("https://api.brainiall.com/v1/image/remove-background/base64", {
  method: "POST",
  headers: { "Authorization": "Bearer YOUR_KEY", "Content-Type": "application/json" },
  body: JSON.stringify({ image_base64: img }),
});
const { image_base64 } = await resp.json();
fs.writeFileSync("result.png", Buffer.from(image_base64, "base64"));

POST /v1/image/upscale/base64 $0.003/image

Upscale an image using Real-ESRGAN. Supports 2x and 4x scale factors.

Request body:

{
  "image_base64": "<base64-image>",
  "scale": 2
}

Response:

{
  "image_base64": "<upscaled-image>"
}

curl -X POST https://api.brainiall.com/v1/image/upscale/base64 \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image_base64":"...","scale":2}'

POST /v1/image/restore-face/base64 $0.005/image

Restore and enhance faces in photos using GFPGAN. Improves clarity, fixes artifacts.

Request body:

{
  "image_base64": "<base64-image>"
}

Response:

{
  "image_base64": "<restored-image>"
}

curl -X POST https://api.brainiall.com/v1/image/restore-face/base64 \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image_base64":"..."}'