--- title: DeepSeek: DeepSeek V3 API | Text Generation | ModelsLab description: Build with DeepSeek: DeepSeek V3 API by Deepseek. Text generation, chat, code, and reasoning. Pay-per-use. Free tier. url: https://modelslab.com/models/deepseek/deepseek-deepseek-chat/api.md canonical: https://modelslab.com/models/deepseek/deepseek-deepseek-chat/api.md type: product component: Playground/LLM/Index generated_at: 2026-04-15T02:02:48.384286Z --- DeepSeek: DeepSeek V3 --- [LLMs.txt](https://modelslab.com/models/open_router/deepseek-deepseek-chat/llms.txt) [.md](https://modelslab.com/models/deepseek/deepseek-deepseek-chat.md) deepseek-deepseek-chat deepseek Closed Source Model $0.605000 / call DeepSeek: DeepSeek V3 --- Choose a prompt below to get started or type your own message Explain quantum computing in simple terms Write a Python function to sort a list Create a marketing email for a SaaS product Compare REST vs GraphQL APIs Send ### DeepSeek: DeepSeek V3 deepseek deepseek-deepseek-chat Copy model ID PricingInput $0.32 / 1M tokens Output $0.89 / 1M tokens API EndpointsOpenAI Compatible `https://modelslab.com/api/v7/llm/chat/completions`Endpoint Anthropic Compatible `https://modelslab.com/api/v7/llm/v1/messages`Messages `https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens `https://modelslab.com/api/v7/llm/v1/models`Models Use with Claude Code cURL Example ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses. Temperature0.7 Max Tokens1000 Top P0.9 Frequency Penalty0 Presence Penalty0 Model Info Support Related Models --- Discover similar models you might be interested in [View all LLM Models](https://modelslab.com/models?feature=llmaster) [OG](https://modelslab.com/models/open_router/openai-gpt-4.1-nano)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-4.1 Nano Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4.1-nano) [OG](https://modelslab.com/models/open_router/openai-gpt-5-nano)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-5 Nano Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5-nano) [QV](https://modelslab.com/models/together_ai/Qwen-Qwen3-VL-235B-A22B-Instruct-FP8)[Together AI](https://modelslab.com/models/together_ai) [Qwen3-VL-235B-A22B-Instruct-FP8 Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-VL-235B-A22B-Instruct-FP8) [GG](https://modelslab.com/models/open_router/google-gemma-3-12b-it-free)[Open Router](https://modelslab.com/models/open_router) [Google: Gemma 3 12B (free) Closed Source Model](https://modelslab.com/models/open_router/google-gemma-3-12b-it-free) [D1](https://modelslab.com/models/together_ai/agentica-org-DeepCoder-14B-Preview)[Together AI](https://modelslab.com/models/together_ai) [Deepcoder 14B Preview Closed Source Model](https://modelslab.com/models/together_ai/agentica-org-DeepCoder-14B-Preview) [Q1](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-1.5B-Instruct)[Together AI](https://modelslab.com/models/together_ai) [Qwen2.5 1.5B Instruct Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-1.5B-Instruct) [ML](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-8B)[Together AI](https://modelslab.com/models/together_ai) [Meta Llama 3.1 8B Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3.1-8B) [DV](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3-DE)[Together AI](https://modelslab.com/models/together_ai) [Deepseek V3 Closed Source Model](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3-DE) [NN](https://modelslab.com/models/open_router/nvidia-nemotron-nano-12b-v2-vl-free)[Open Router](https://modelslab.com/models/open_router) [NVIDIA: Nemotron Nano 12B 2 VL (free) Closed Source Model](https://modelslab.com/models/open_router/nvidia-nemotron-nano-12b-v2-vl-free) [MM](https://modelslab.com/models/open_router/mistralai-ministral-3b-2512)[Open Router](https://modelslab.com/models/open_router) [Mistral: Ministral 3 3B 2512 Closed Source Model](https://modelslab.com/models/open_router/mistralai-ministral-3b-2512) [ML](https://modelslab.com/models/open_router/meta-llama-llama-4-maverick)[Open Router](https://modelslab.com/models/open_router) [Meta: Llama 4 Maverick Closed Source Model](https://modelslab.com/models/open_router/meta-llama-llama-4-maverick) [SL](https://modelslab.com/models/open_router/sao10k-l3-euryale-70b)[Open Router](https://modelslab.com/models/open_router) [Sao10k: Llama 3 Euryale 70B v2.1 Closed Source Model](https://modelslab.com/models/open_router/sao10k-l3-euryale-70b) [![Meta: Llama 3 8B Instruct](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/07cb8c22-a068-40f8-a2e8-57d8b2371261.png)](https://modelslab.com/models/open_router/meta-llama-llama-3-8b-instruct)[Open Router](https://modelslab.com/models/open_router) [Meta: Llama 3 8B Instruct Closed Source Model](https://modelslab.com/models/open_router/meta-llama-llama-3-8b-instruct) [OO](https://modelslab.com/models/open_router/openai-o4-mini-high)[Open Router](https://modelslab.com/models/open_router) [OpenAI: o4 Mini High Closed Source Model](https://modelslab.com/models/open_router/openai-o4-mini-high) [PI](https://modelslab.com/models/open_router/prime-intellect-intellect-3)[Open Router](https://modelslab.com/models/open_router) [Prime Intellect: INTELLECT-3 Closed Source Model](https://modelslab.com/models/open_router/prime-intellect-intellect-3) [MM](https://modelslab.com/models/open_router/mistralai-mistral-7b-instruct-v0.1)[Open Router](https://modelslab.com/models/open_router) [Mistral: Mistral 7B Instruct v0.1 Closed Source Model](https://modelslab.com/models/open_router/mistralai-mistral-7b-instruct-v0.1) [RL](https://modelslab.com/models/refuel_ai/togethercomputer-Refuel-Llm-V2)[ModelsLab](https://modelslab.com/models/refuel_ai) [Refuel LLM V2 Closed Source Model](https://modelslab.com/models/refuel_ai/togethercomputer-Refuel-Llm-V2) [QQ](https://modelslab.com/models/open_router/qwen-qwen-vl-plus)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen VL Plus Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen-vl-plus) About DeepSeek: 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... ### Technical Specifications Model IDdeepseek-deepseek-chatCategoryLLM ModelsTaskText GenerationPrice$0.605000 per million tokensAddedFebruary 20, 2026 ### Key Features - Chat completion and multi-turn conversation API - Streaming response with token-by-token output - Function calling and tool use support - System prompts and role-based messaging - JSON mode and structured output ### Quick Start Integrate DeepSeek: DeepSeek V3 into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started. PythonJavaScriptcURLPHP ``` import requests import json url = "https://modelslab.com/api/v7/llm/chat/completions" headers = { "Content-Type": "application/json" } data = { "model_id": "deepseek-deepseek-chat", "messages": [ { "role": "user", "content": "Hello!" } ], "max_tokens": 1000, "key": "YOUR_API_KEY" } try: response = requests.post(url, headers=headers, json=data) response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX) result = response.json() print("API Response:") print(json.dumps(result, indent=2)) except requests.exceptions.HTTPError as http_err: print(f"HTTP error occurred: {http_err} - {response.text}") except Exception as err: print(f"Other error occurred: {err}") ``` View the [full API documentation](https://modelslab.com/models/deepseek/deepseek-deepseek-chat/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing DeepSeek: DeepSeek V3 API costs $0.605000 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing) ### Use Cases - AI chatbots and virtual assistants - Code generation and developer tools - Content writing and copywriting automation - Data analysis, summarization, and extraction [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Deepseek](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) DeepSeek: DeepSeek V3 FAQ --- ### What is DeepSeek: 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... ### How do I use the DeepSeek: DeepSeek V3 API? You can integrate DeepSeek: DeepSeek V3 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "deepseek-deepseek-chat" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does DeepSeek: DeepSeek V3 cost? DeepSeek: DeepSeek V3 costs $0.605000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the DeepSeek: DeepSeek V3 model ID? The model ID for DeepSeek: DeepSeek V3 is "deepseek-deepseek-chat". Use this ID in your API requests to specify this model. ### Does DeepSeek: DeepSeek V3 have a free tier? Yes, ModelsLab offers a free tier that lets you try DeepSeek: DeepSeek V3 and other AI models. Sign up to get free API credits and start building immediately. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-04-15*