tbuy
text-embedding-v4 API pricing & access
text-embedding-v4 API pricing: $0.07 per 1M tokens. text-embedding-v4 API for multilingual semantic search, RAG and text clustering.
text-embedding-v4 API access
text-embedding-v4 API for multilingual semantic search, RAG and text clustering.
Compare supported API endpoints and capabilities, then access text-embedding-v4 through the unified API gateway.
- Category
- vector
- Supported APIs
- OpenAI Chat Completions API
- API endpoints
- POST /v1/chat/completions
text-embedding-v4 API pricing
- Base input price
- $0.07 per 1M tokens
- Base output price
- $0.07 per 1M tokens
Base prices are shown in USD before group-specific adjustments. Open the live pricing page for current access-group prices.
About text-embedding-v4
text-embedding-v4 converts multilingual text into vectors for retrieval, clustering, and classification. The official API defaults to 1024 dimensions, offers listed sizes from 64 to 2048, and accepts up to 10 texts of 8192 tokens each.
Use it for knowledge bases and semantic search. It returns vectors rather than chat answers; check your selected endpoint's limits.
Model reference · API limits, checked 2026-10-11.
API pricing and model selection
Review the prices and endpoints on this page. Check your account discounts, quota and actual usage after signing in, then evaluate the selected endpoint on a small sample.
Compare models in this category · API integration documentation.
Use cases and prompting
Keep index and query settings consistent
Split documents into meaningful passages and preserve source identifiers. Use the same model and vector dimensions for indexing and queries; build a new index when either changes.
Measure retrieval quality with real questions and known answers. Include empty text, oversized text, and batch failures in tests. Verify the number and dimensions of returned vectors.
A task to evaluate
Build a fixed retrieval evaluation set with an expected document for each query. Record chunking rules, model and vector dimensions. Compare retrieval results rather than request success alone.
Compare the output with your acceptance criteria. Record the model, endpoint, input size, elapsed time and actual usage; change one condition at a time.
How to call text-embedding-v4
text-embedding-v4 is served through tbuy's unified gateway. Existing OpenAI or Anthropic SDK code keeps working: point base_url at https://modelsok.com and use your tbuy API key.
curl (OpenAI-compatible)
curl https://modelsok.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "text-embedding-v4", "messages": [{"role": "user", "content": "Hello"}]}'Python (openai SDK)
from openai import OpenAI
client = OpenAI(base_url="https://modelsok.com/v1", api_key="YOUR_API_KEY")
response = client.chat.completions.create(
model="text-embedding-v4",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Related pages
Frequently asked questions about text-embedding-v4
What is text-embedding-v4?
text-embedding-v4 API for multilingual semantic search, RAG and text clustering.
How do I call text-embedding-v4?
Create an API key with access to text-embedding-v4, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is text-embedding-v4 priced?
Pricing depends on the selected provider group and the model billing unit. Refer to the current input, output, request, or media prices in the pricing section.
How should I evaluate text-embedding-v4 for my project?
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.