DeepSeek-Coder-V2

deepseek/deepseek-coder

Created May 14, 2024128,000 context

$0.04/M input tokens$0.12/M output tokens

DeepSeek-Coder-V2, an open-source Mixture-of-Experts (MoE) code language model. It is further pre-trained from an intermediate checkpoint of DeepSeek-V2 with additional 6 trillion tokens.

The original V1 model was trained from scratch on 2T tokens, with a composition of 87% code and 13% natural language in both English and Chinese. It was pre-trained on project-level code corpus by employing a extra fill-in-the-blank task.

Providers for DeepSeek-Coder-V2

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

Apps using DeepSeek-Coder-V2

Top public apps this week using this model

Recent activity on DeepSeek-Coder-V2

Tokens processed per day

Uptime stats for DeepSeek-Coder-V2

Uptime stats for DeepSeek-Coder-V2 across all providers

Sample code and API for DeepSeek-Coder-V2

OpenRouter normalizes requests and responses across providers for you.

OpenRouter provides an OpenAI-compatible completion API to 300+ models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

from openai import OpenAI

client = OpenAI(
  base_url="https://openrouter.ai/api/v1",
  api_key="<OPENROUTER_API_KEY>",
)

completion = client.chat.completions.create(
  extra_headers={
    "HTTP-Referer": "<YOUR_SITE_URL>", # Optional. Site URL for rankings on openrouter.ai.
    "X-Title": "<YOUR_SITE_NAME>", # Optional. Site title for rankings on openrouter.ai.
  },
  extra_body={},
  model="deepseek/deepseek-coder",
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
)
print(completion.choices[0].message.content)

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

See the Request docs for all possible fields, and Parameters for explanations of specific sampling parameters.

More models from DeepSeek

DeepSeek Prover V2

DeepSeek Prover V2 is a 671B parameter model, speculated to be geared towards logic and mathematics. Likely an upgrade from DeepSeek-Prover-V1.5 Not much is known about the model yet, as DeepSeek released it on Hugging Face without an announcement or description.

DeepSeek V3 Base

Note that this is a base model mostly meant for testing, you need to provide detailed prompts for the model to return useful responses.

DeepSeek-V3 Base is a 671B parameter open Mixture-of-Experts (MoE) language model with 37B active parameters per forward pass and a context length of 128K tokens. Trained on 14.8T tokens using FP8 mixed precision, it achieves high training efficiency and stability, with strong performance across language, reasoning, math, and coding tasks.

DeepSeek-V3 Base is the pre-trained model behind DeepSeek V3

DeepSeek V3 0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.

It succeeds the DeepSeek V3 model and performs really well on a variety of tasks.

DeepSeek R1 Zero

DeepSeek-R1-Zero is a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT) as a preliminary step. It's 671B parameters in size, with 37B active in an inference pass.

It demonstrates remarkable performance on reasoning. With RL, DeepSeek-R1-Zero naturally emerged with numerous powerful and interesting reasoning behaviors.

DeepSeek-R1-Zero encounters challenges such as endless repetition, poor readability, and language mixing. See DeepSeek R1 for the SFT model.

R1 Distill Llama 8B

DeepSeek R1 Distill Llama 8B is a distilled large language model based on Llama-3.1-8B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including: