Build with the world's underserved languages
Simple REST APIs, Python & Node SDKs. Drop-in replacement for Voyage, Cohere, or OpenAI embeddings — no NLP expertise required.
Quick Start
1. Get your API key
Sign up for a free account and generate your API key from the dashboard. Every account starts with free credits.
Get API Key2. Install the SDK (optional)
pip install bhala
# or
npm install @bhala/sdk3. Make your first API call
from bhala import Bhala
client = Bhala(api_key="bh_sk_...")
# Generate embeddings for any supported language
response = client.embed(
input="Sawubona, ngingakusiza kanjani?",
model="bantu-embed-v1",
dimensions=1024
)
print(response.data[0].embedding[:5])
# [0.0234, -0.0891, 0.1456, 0.0312, -0.0678]curl -X POST https://api.bhala.ai/v1/embed \
-H "Authorization: Bearer bh_sk_..." \
-H "Content-Type: application/json" \
-d '{
"input": "Sawubona, ngingakusiza kanjani?",
"model": "bantu-embed-v1",
"dimensions": 1024
}'{
"object": "embedding",
"data": [{
"embedding": [0.0234, -0.0891, 0.1456, ...],
"dimensions": 1024
}],
"usage": { "total_tokens": 8 }
}from bhala import Bhala
client = Bhala(api_key="bh_sk_...")
# Generate embeddings for any supported language
embeddings = client.embed(
input="Sawubona, ngingakusiza kanjani?",
model="bantu-embed-v1"
)
print(len(embeddings.data[0].embedding))
# → 1024
# Translate English → IsiZulu
result = client.translate(
text="Your payment was successful.",
source="en",
target="zu"
)
print(result.translation)
# → "Inkokhelo yakho iphumelele."Why developers choose Bhala
Drop-in replacement
Same REST interface you already know from OpenAI, Cohere, or Voyage. Switch your base URL and you're done.
No NLP expertise needed
Our models handle noun classes, agglutination, and tonal patterns — you just send text and get results.
Start free, scale to millions
2M embedding tokens and 200K translation characters included free. Pay-as-you-go from $0.08/1M tokens.
APIs
Universal Embedding Layer
Stop relying on translation layers that lose nuance. Integrate a native semantic understanding of under-digitized languages directly into your AI stack. Power your RAG pipelines, classifiers, and agents with structural intelligence that transcends language families.
$0.08 per 1M tokens
Native Translation Bridge
Enable your AI products to communicate fluently in the world's most complex languages. Our structural approach eliminates the need for massive parallel datasets, allowing you to scale your product into new markets in days, not years.
$5.00 per 1M characters
Cross-Lingual Reranker
Solve the 'no results found' problem in local languages. Our reranker provides the final mile of precision for your AI search, ensuring high-relevance retrieval across diverse scripts and dialects.
$0.06 per 1M tokens
Native Intelligence Suite
Equip your AI with the fundamental tools it needs for native-level performance: grammar correction, sentiment analysis, and NER that actually work for the world's most complex languages.
Custom Enterprise Pricing
API Reference
POST /v1/embedEmbeddings
Generate vector embeddings for low-resource language text.
POST /v1/translateTranslation
Translate between supported languages.
POST /v1/rerankReranker
Rerank search results by relevance.
POST /v1/identifyLanguage ID
Identify which language a text is written in.
POST /v1/correctGrammar Correction
Grammatical error correction for low-resource languages.
POST /v1/analyzeSentiment
Sentiment analysis for low-resource languages.
Start building with Bhala
Get free API access and start integrating low-resource language understanding into your applications today.