modelhub.help

DeepSeek-Coder-V2

DeepSeekOpen-weight

128K context · 236B (21B active) params · MIT (code) / DeepSeek License

deepseek/deepseek-coder-v2

DeepSeek-Coder-V2 is a 236B-parameter MoE code model (21B active) with 128K context across 300+ programming languages. Strong at code completion, repository-level understanding and code reasoning; weights are open for self-hosting.

Cheapest blended: $0.182 / 1M tokens on DeepSeekGet custom quote

Reachability & verification

Live reachability

Probing…

Target (DeepSeek): https://api.deepseek.com

Live reachability probe

Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.

Pricing across providers

1

Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.

ProviderInput /1MOutput /1MBlendedCtxp50 latencyAPIVerified
DeepSeekdeepseek-coder$0.14$0.28$0.182128K OAI43d ago

Works with

CursorClineAiderContinueOpenCodeOpen WebUI

Any OpenAI-compatible client works — point the base URL at the provider endpoint.

Capabilities

codechat

Languages: en, zh, +300 langs

Code samples

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.deepseek.com",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="deepseek-coder",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
cURL
curl https://api.deepseek.com/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-coder",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Node.js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.deepseek.com",
  apiKey: "YOUR_API_KEY",
});

const resp = await client.chat.completions.create({
  model: "deepseek-coder",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Technical specs

Context

128K

Max output

8K

Parameters

236B (21B active)

Release

2024-07

Training cutoff

License

MIT (code) / DeepSeek License

Similar models

Frequently asked questions

How much does DeepSeek-Coder-V2 cost?

The cheapest tracked blended price is $0.182 per 1M tokens on DeepSeek. See the pricing matrix above for input/output splits per provider.

Can I use DeepSeek-Coder-V2 from outside China?

Availability depends on the hosting provider. Use our Path Planner on the DeepSeek page to map a verified official-vs-brokered access path, including payment and KYC constraints.

Is DeepSeek-Coder-V2 open source?

Yes — DeepSeek-Coder-V2 is open-weight under the MIT (code) / DeepSeek License license. You can self-host it or use any listed inference provider.

Is DeepSeek-Coder-V2 OpenAI-compatible?

Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.

What is the maximum context window?

DeepSeek-Coder-V2 supports up to 128K tokens of context with a maximum output of 8K tokens.

Need verified access to DeepSeek-Coder-V2?

We broker vetted intros to DeepSeek — payment, KYC and endpoint verification handled.

Request a brokerage intro