deepseek-v3.2
Use deepseek-v3.2 through KeepBal. POST /v1/chat/completions. Input: $0.336 / Output: $0.504 / Cache read: $0.26 / Cache write: $0 per 1M tokens.
curl
curl https://keepbal.com/v1/chat/completions -H 'Authorization: Bearer YOUR_KEEPBAL_KEY' -H 'Content-Type: application/json' -d '{"model":"deepseek-v3.2","messages":[{"role":"user","content":"Summarize this research."}],"max_tokens":256}'OpenAI SDK
import os
from openai import OpenAI
client = OpenAI(api_key=os.environ["KEEPBAL_API_KEY"], base_url="https://keepbal.com/v1")
response = client.chat.completions.create(model="deepseek-v3.2", messages=[{"role": "user", "content": "Summarize this research."}], max_tokens=256)
print(response)Pair with tools
Search for source material, inspect and run a tool, then pass the results to a model for summarization or analysis. Browse tools
| Tool | What it returns | Price |
|---|---|---|
| Chatgpt Ask | Get ChatGPT's consumer-app answer to a prompt, with cited sources, in a chosen country. | Variable: provider price plus 35% |
| Copilot Ask | Get Copilot's consumer-app answer to a prompt, with cited sources, in a chosen country. | Variable: provider price plus 35% |
| Gemini Ask | Get Gemini's consumer-app answer to a prompt, with cited sources, in a chosen country. | Variable: provider price plus 35% |
FAQ
Which endpoint should I use?
POST /v1/chat/completions with the exact model ID deepseek-v3.2.
How is usage priced?
Input: $0.336 / Output: $0.504 / Cache read: $0.26 / Cache write: $0 per 1M tokens. Charges add the applicable input, output, cache read, and cache write token amounts at their respective rates. Cached input is charged at its cache rate instead of the regular input rate. Embeddings are billed for input tokens only. Billing uses returned token usage.