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.

Nebius AI Studio
DE
fp8
Context
128K
Max Output
128K
Input
$0.04
Output
$0.12

Apps using DeepSeek-Coder-V2

Top public apps this week using this model

1.
Favicon for https://cline.bot/
Cline
Autonomous coding agent right in your IDE
62.9Mtokens
2.
Favicon for https://roocode.com/
Roo Code
A whole dev team of AI agents in your editor
36.2Mtokens
3.
Favicon for https://openrouter.ai/chat
OpenRouter: Chatroom
Chat with multiple LLMs at once
2.37Mtokens
4.
Favicon for https://aider.chat/
Aider
AI pair programming in your terminal
1.9Mtokens
5.
Favicon for https://openwebui.com/
Open WebUI
Extensible, self-hosted AI interface
1Mtokens
6.
Favicon for https://github.com/HybridTalentComputing/Roo-Code-Chinese
Roo Code Chinese
new
663Ktokens
7.
Favicon for https://sillytavern.app/
SillyTavern
LLM frontend for power users
483Ktokens
8.
Favicon for https://chub.ai/
Chub AI
GenAI for everyone
412Ktokens
9.
Favicon for https://edgar-tidy.com/
EDGAR Tidy App
new
396Ktokens
10.
Favicon for https://docs.all-hands.dev/
OpenHands
AI coding agent that can run commands, browse the web, call APIs
281Ktokens
11.
Favicon for https://voideditor.com/
Void Editor
new
224Ktokens
12.
Favicon for https://litellm.ai/
liteLLM
Open-source library to simplify LLM calls
92Ktokens
13.
Favicon for https://github.com/sera-plz/ai-vault
AI Vault
new
89Ktokens
14.
Favicon for https://multimodel-invest-analyzer.replit.app/
Multi-Model Investment Analyzer
new
68Ktokens
15.
Favicon for https://kilocode.ai/
Kilo Code
new
61Ktokens
16.
Favicon for https://risuai.xyz/
RisuAI
Browse characters, choose models, and chat
54Ktokens
17.
Favicon for https://soundtrack-app.com/
SoundTrack App
new
49Ktokens
18.
Favicon for https://cherry-ai.com/
Cherry Studio
new
39Ktokens
19.
Favicon for https://your-website.com/
My Chat App
new
34Ktokens
20.
Favicon for https://lovable.dev/
Learn LLMs
new
33Ktokens

Recent activity on DeepSeek-Coder-V2

Tokens processed per day

Apr 30May 1May 2May 3May 4May 5May 6May 7May 806.5M13M19.5M26M

Uptime stats for DeepSeek-Coder-V2

Uptime stats for DeepSeek-Coder-V2 on the only provider

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it.

Learn more about our load balancing and customization options.

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:

The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Hugging Face:

R1 Distill Qwen 1.5B

DeepSeek R1 Distill Qwen 1.5B is a distilled large language model based on Qwen 2.5 Math 1.5B, using outputs from DeepSeek R1. It's a very small and efficient model which outperforms GPT 4o 0513 on Math Benchmarks.

Other benchmark results include:

The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

R1 Distill Qwen 32B

DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.

Other benchmark results include:

The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

R1 Distill Qwen 14B

DeepSeek R1 Distill Qwen 14B is a distilled large language model based on Qwen 2.5 14B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models.

Other benchmark results include:

The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a distilled large language model based on Llama-3.3-70B-Instruct, using outputs from DeepSeek R1. The model combines advanced distillation techniques to achieve high performance across multiple benchmarks, including:

The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

R1

DeepSeek R1 is here: Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.

Fully open-source model & technical report.

MIT licensed: Distill & commercialize freely!

DeepSeek V3

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations reveal that the model outperforms other open-source models and rivals leading closed-source models.

For model details, please visit the DeepSeek-V3 repo for more information, or see the launch announcement.

DeepSeek V2.5

DeepSeek-V2.5 is an upgraded version that combines DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct. The new model integrates the general and coding abilities of the two previous versions. For model details, please visit DeepSeek-V2 page for more information.

    DeepSeek-Coder-V2 | OpenRouter