--- title: Anthropic: Claude Sonnet 4 API | Text Generation | ModelsLab description: Balanced LLM with hybrid reasoning for coding & agents; 200K context window (1M preview), 64K output tokens, 72.7% SWE-bench score, 40 tps speed. url: https://modelslab.com/models/anthropic/anthropic-claude-sonnet-4/api.md canonical: https://modelslab.com/models/anthropic/anthropic-claude-sonnet-4/api.md type: product component: Playground/LLM/Index generated_at: 2026-04-15T02:06:22.082743Z --- Anthropic: Claude Sonnet 4 --- [LLMs.txt](https://modelslab.com/models/open_router/anthropic-claude-sonnet-4/llms.txt) [.md](https://modelslab.com/models/anthropic/anthropic-claude-sonnet-4.md) anthropic-claude-sonnet-4 anthropic Closed Source Model $9.000000 / call Anthropic: Claude Sonnet 4 --- 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 ### Anthropic: Claude Sonnet 4 anthropic anthropic-claude-sonnet-4 Copy model ID PricingInput $3.00 / 1M tokens Output $15.00 / 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) [ZG](https://modelslab.com/models/open_router/z-ai-glm-4-32b)[Open Router](https://modelslab.com/models/open_router) [Z.ai: GLM 4 32B Closed Source Model](https://modelslab.com/models/open_router/z-ai-glm-4-32b) [GO](https://modelslab.com/models/together_ai/zai-org-GLM-OCR)[Together AI](https://modelslab.com/models/together_ai) [GLM OCR Closed Source Model](https://modelslab.com/models/together_ai/zai-org-GLM-OCR) [XG](https://modelslab.com/models/open_router/x-ai-grok-3-beta)[Open Router](https://modelslab.com/models/open_router) [xAI: Grok 3 Beta Closed Source Model](https://modelslab.com/models/open_router/x-ai-grok-3-beta) [ML](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3-8B-Instruct-Lite)[Together AI](https://modelslab.com/models/together_ai) [Meta Llama 3 8B Instruct Lite Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Meta-Llama-3-8B-Instruct-Lite) [QV](https://modelslab.com/models/qwen/Qwen-Qwen2.5-VL-72B-Instruct)[ModelsLab](https://modelslab.com/models/qwen) [Qwen2.5-VL (72B) Instruct Closed Source Model](https://modelslab.com/models/qwen/Qwen-Qwen2.5-VL-72B-Instruct) [MM](https://modelslab.com/models/open_router/mistralai-mistral-small-3.2-24b-instruct)[Open Router](https://modelslab.com/models/open_router) [Mistral: Mistral Small 3.2 24B Closed Source Model](https://modelslab.com/models/open_router/mistralai-mistral-small-3.2-24b-instruct) [N3](https://modelslab.com/models/together_ai/nim-meta-llama-3.3-70b-instruct)[Together AI](https://modelslab.com/models/together_ai) [nim/meta/llama-3.3-70b-instruct Closed Source Model](https://modelslab.com/models/together_ai/nim-meta-llama-3.3-70b-instruct) [RS](https://modelslab.com/models/open_router/undi95-remm-slerp-l2-13b)[Open Router](https://modelslab.com/models/open_router) [ReMM SLERP 13B Closed Source Model](https://modelslab.com/models/open_router/undi95-remm-slerp-l2-13b) [G5](https://modelslab.com/models/together_ai/zai-org-GLM-5.1)[Together AI](https://modelslab.com/models/together_ai) [GLM 5.1 FP4 Closed Source Model](https://modelslab.com/models/together_ai/zai-org-GLM-5.1) [QQ](https://modelslab.com/models/open_router/qwen-qwen3.5-397b-a17b)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3.5 397B A17B Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3.5-397b-a17b) [QC](https://modelslab.com/models/together_ai/Qwen-Qwen3-Coder-480B-A35B-Instruct-FP8)[Together AI](https://modelslab.com/models/together_ai) [Qwen3 Coder 480B A35B Instruct Fp8 Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-Coder-480B-A35B-Instruct-FP8) [QV](https://modelslab.com/models/together_ai/Qwen-Qwen3-VL-32B-Instruct)[Together AI](https://modelslab.com/models/together_ai) [Qwen3-VL-32B-Instruct Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-VL-32B-Instruct) [![Gemini 2.0 Flash](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/f05a6bc4-dd20-49cc-bc2f-8a1c9b25e930.png)](https://modelslab.com/models/google/gemini-2.0-flash-001)[Google](https://modelslab.com/models/google) [Gemini 2.0 Flash Closed Source Model](https://modelslab.com/models/google/gemini-2.0-flash-001) [AA](https://modelslab.com/models/open_router/arcee-ai-maestro-reasoning)[Open Router](https://modelslab.com/models/open_router) [Arcee AI: Maestro Reasoning Closed Source Model](https://modelslab.com/models/open_router/arcee-ai-maestro-reasoning) [![Anthropic: Claude Haiku 4.5](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/b89d0017-305c-42f8-8327-14107b3de1a0.png)](https://modelslab.com/models/open_router/anthropic-claude-haiku-4.5)[Open Router](https://modelslab.com/models/open_router) [Anthropic: Claude Haiku 4.5 Closed Source Model](https://modelslab.com/models/open_router/anthropic-claude-haiku-4.5) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-30b-a3b-thinking-2507)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 30B A3B Thinking 2507 Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-30b-a3b-thinking-2507) [GG](https://modelslab.com/models/open_router/google-gemma-3n-e4b-it)[Open Router](https://modelslab.com/models/open_router) [Google: Gemma 3n 4B Closed Source Model](https://modelslab.com/models/open_router/google-gemma-3n-e4b-it) [ML](https://modelslab.com/models/together_ai/meta-llama-Llama-3.2-3B)[Together AI](https://modelslab.com/models/together_ai) [Meta Llama 3.2 3B Closed Source Model](https://modelslab.com/models/together_ai/meta-llama-Llama-3.2-3B) About Anthropic: Claude Sonnet 4 --- Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),... ### Technical Specifications Model IDanthropic-claude-sonnet-4CategoryLLM ModelsTaskText GenerationPrice$9.000000 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 Anthropic: Claude Sonnet 4 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": "anthropic-claude-sonnet-4", "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/anthropic/anthropic-claude-sonnet-4/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing Anthropic: Claude Sonnet 4 API costs $9.000000 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 Anthropic](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Anthropic: Claude Sonnet 4 FAQ --- ### What is Anthropic: Claude Sonnet 4? Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),... ### How do I use the Anthropic: Claude Sonnet 4 API? You can integrate Anthropic: Claude Sonnet 4 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "anthropic-claude-sonnet-4" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Anthropic: Claude Sonnet 4 cost? Anthropic: Claude Sonnet 4 costs $9.000000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Anthropic: Claude Sonnet 4 model ID? The model ID for Anthropic: Claude Sonnet 4 is "anthropic-claude-sonnet-4". Use this ID in your API requests to specify this model. ### Does Anthropic: Claude Sonnet 4 have a free tier? Yes, ModelsLab offers a free tier that lets you try Anthropic: Claude Sonnet 4 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*