Advanced reasoning model rivaling frontier models at a fraction of the cost. Uses chain-of-thought reasoning by default, making it excellent for math, logic, and complex multi-step problems. Transparent reasoning process lets you see the model's thought process.
DeepSeek
64k tokens
8,192 tokens
deepseek/deepseek-r1
Drop-in compatible with any OpenAI client library.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.deployai.dev/v1",
apiKey: process.env.DEPLOYAI_API_KEY,
});
const completion = await client.chat.completions.create({
model: "deepseek/deepseek-r1",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
});
console.log(completion.choices[0].message.content);Latest general-purpose model with strong reasoning and code generation. Excellent value for money.
Efficient reasoning model optimized for speed. High reasoning effort with lower latency and cost.
Most capable multimodal model. Excels at complex reasoning, coding, creative writing, and vision tasks.