How do I call deepseek-v4-pro from my code?
Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘deepseek/deepseek-v4-pro’ and supply your Synapse Garden API key. No code changes beyond the base URL.
deepseek/deepseek-v4-pro idDeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) ManifoldConstrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability
# Drop-in OpenAI-compatible client$ import { generateText } from 'ai'$$ const { text } = await generateText({$ model: 'deepseek/deepseek-v4-pro',$ baseURL: 'https://synapse.garden/api/v1',$ apiKey: process.env.MG_KEY,$ prompt: 'Why is the sky blue?',$ })
| Rate | Per million tokens · USD |
|---|---|
| Input | $0.479/M |
| Output | $0.957/M |
| Cache read | $0.0040/M |
Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘deepseek/deepseek-v4-pro’ and supply your Synapse Garden API key. No code changes beyond the base URL.
Input: $0.479/M per million tokens. Output: $0.957/M per million tokens. The free tier includes a million tokens every month at no cost.
deepseek-v4-pro supports a context window of 1M tokens, with a maximum output of 384K tokens.
No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.
Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.