Back to models
DeepSeek·DeepSeek V family
DeepSeek V4
Open weightsMoEmitReleased Feb 1, 2026
DeepSeek's fourth-generation model with improved mixture-of-experts architecture, enhanced reasoning and coding capabilities, and stronger multilingual performance. Competitive with frontier proprietary models.
ChatText completionFunction callingCode generationReasoningtext · code
Available from 6 providers
Cheapest
SiliconFlow
$0.14 / $0.28
+1
Anyscale, DeepSeek, Fireworks, Hugging Face Inference, SiliconFlow, Together AI
Providers (6)
Sorted by total cost (input + output per 1M tokens). Select a row to view provider details.
| Provider | Pricing (per 1M) | Rate limits | Regions | Health | Latency |
|---|---|---|---|---|---|
| In: $0.14Out: $0.28 | 600 RPM / 1.0M TPM | ap-east-1global | Healthy | 0ms |
| In: $0.18Out: $0.36 | 300 RPM / 500K TPM | us-east-1eu-west-1 | Healthy | 0ms |
| In: $0.20Out: $0.40 | 300 RPM / 500K TPM | us-east-1us-west-2 | Healthy | 0ms |
| In: $0.20Out: $0.80 | 600 RPM / 1.0M TPM | us-east-1us-west-2 | Healthy | 0ms |
| In: $0.27Out: $1.10 | 500 RPM / 1.0M TPM | us-east-1global | Healthy | 0ms |
 | In: $0.90Out: $0.90 | 600 RPM / 1.0M TPM | us-east-1us-west-2 | Healthy | 0ms |
Quick start
Use this model via SiliconFlow with an OpenAI-compatible SDK.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.siliconflow.com/v1",
apiKey: process.env.SILICONFLOW_API_KEY,
});
const response = await client.chat.completions.create({
model: "deepseek-ai/DeepSeek-V4",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);Using SiliconFlow API · OpenAI-compatible SDK