--- title: Moondream: Moondream 3 Preview | Text Generation | ModelsLab description: Build with Moondream: Moondream 3 Preview API by Moondream. Text generation, chat, code, and reasoning. Plans from $21/month. url: https://modelslab.com/models/moondream/moondream-moondream3-preview.md canonical: https://modelslab.com/models/moondream/moondream-moondream3-preview type: product component: Playground/LLM/Index generated_at: 2026-10-21T07:16:09.227240Z --- Moondream: Moondream 3 Preview --- [LLMs.txt](https://modelslab.com/models/moondream/moondream-moondream3-preview/llms.txt) [.md](https://modelslab.com/models/moondream/moondream-moondream3-preview.md) Moondream: Moondream 3 Preview --- 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 images and text files Send ### Moondream: Moondream 3 Preview moondream moondream-moondream3-preview Copy model ID PricingInput $0.30 / 1M tokens Output $2.50 / 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 Tokens4000 Top P0.9 Frequency Penalty0 Presence Penalty0 Thinkinglow lowmediumhigh Deeper thinking spends more of the Max Tokens budget before the answer starts. Model Info Support Looking for something different? --- Models that trade off differently against the one you are viewing ### Better quality Newer flagship models that generally produce stronger results. [OpenAI](https://modelslab.com/models/openai) [GPT 5.2](https://modelslab.com/models/openai/gpt-5.2) [OpenAI](https://modelslab.com/models/openai) [GPT 5.1](https://modelslab.com/models/openai/gpt5.1) [Google](https://modelslab.com/models/google) [Gemini 3 Pro Preview](https://modelslab.com/models/google/gemini-3-pro-preview) [OpenAI](https://modelslab.com/models/openai) [GPT-5.1-Codex-Max](https://modelslab.com/models/openai/gpt-5.1-codex-max) ### Lower cost per run Open-source models we host, unlimited on the $149/month plan. [ModelsLab](https://modelslab.com/models/modelslab) Popular [Modelslab: Custom LLM](https://modelslab.com/models/modelslab/uncensored-chat)Open Source Model [Qwen](https://modelslab.com/models/open_router) [Qwen: Qwen3 235B A22B Instruct 2507](https://modelslab.com/models/qwen/qwen-qwen3-235b-a22b-2507)Closed Source Model [OpenAI](https://modelslab.com/models/openai) [gpt-oss-20b](https://modelslab.com/models/openai/gpt-oss-20b)Closed Source Model [DeepSeek](https://modelslab.com/models/open_router) [DeepSeek: DeepSeek V4 Flash 0423](https://modelslab.com/models/deepseek/deepseek-deepseek-v4-flash)Closed Source Model [Google](https://modelslab.com/models/open_router) [Google: Gemini 3.1 Flash Lite](https://modelslab.com/models/google/google-gemini-3.1-flash-lite)Closed Source Model [Google](https://modelslab.com/models/open_router) [Gemma 4 31B-it FP8](https://modelslab.com/models/google/google-gemma-4-31B-it)Closed Source Model Related Models --- Discover similar models you might be interested in [View all LLM Models](https://modelslab.com/models?feature=llmaster) [#### Z.ai/Z.ai: GLM 5.1 z-ai-glm-5.1 From $2.90/M tokens](https://modelslab.com/models/z-ai/z-ai-glm-5.1) [#### Refuel AI/Refuel LLM V2 togethercomputer-Refuel-Llm-V2 From $0.72/M tokens](https://modelslab.com/models/refuel_ai/togethercomputer-Refuel-Llm-V2) [#### Z.ai/Z.ai: GLM Latest z-ai-glm-latest From $0.74/M tokens](https://modelslab.com/models/z-ai/z-ai-glm-latest) [#### Google/Google: Nano Banana (Gemini 2.5 Flash Image) google-gemini-2.5-flash-image From $1.40/M tokens](https://modelslab.com/models/google/google-gemini-2.5-flash-image) [#### ByteDance/ByteDance: UI-TARS 7B bytedance-ui-tars-1.5-7b From $0.15/M tokens](https://modelslab.com/models/bytedance/bytedance-ui-tars-1.5-7b) [#### Qwen/Qwen: Qwen3.7 Plus (batch) qwen-qwen3.7-plus-batch From $0.57/M tokens](https://modelslab.com/models/qwen/qwen-qwen3.7-plus-batch) [#### Qwen/Qwen: Qwen3.6 Plus qwen-qwen3.6-plus From $1.14/M tokens](https://modelslab.com/models/qwen/qwen-qwen3.6-plus) [#### Qwen/Qwen QwQ-32B Qwen-QwQ-32B From $1.20/M tokens](https://modelslab.com/models/qwen/Qwen-QwQ-32B) [#### Amazon/Amazon: Nova Lite 1.0 amazon-nova-lite-v1 From $0.15/M tokens](https://modelslab.com/models/amazon/amazon-nova-lite-v1) [#### Google/Gemini 2.5 Pro gemini-2.5-pro From $5.63/M tokens](https://modelslab.com/models/google/gemini-2.5-pro) [#### Qwen/Qwen: Qwen3.6 27B qwen-qwen3.6-27b From $1.13/M tokens](https://modelslab.com/models/qwen/qwen-qwen3.6-27b) [#### Meta/Typhoon 2.1 12B scb10x-scb10x-typhoon-2-1-gemma3-12b From $0.24/M tokens](https://modelslab.com/models/meta/scb10x-scb10x-typhoon-2-1-gemma3-12b) [#### Alibaba Cloud/Qwen: Qwen3.5-35B-A3B qwen-qwen3.5-35b-a3b From $1.13/M tokens](https://modelslab.com/models/alibaba_cloud/qwen-qwen3.5-35b-a3b) [#### Anthropic/Anthropic: Claude Opus 5.5 (batch) anthropic-claude-opus-5.5-batch From $6.00/M tokens](https://modelslab.com/models/anthropic/anthropic-claude-opus-5.5-batch) [#### Xiaomi/Xiaomi: MiMo-V2.6-Flash xiaomi-mimo-v2.6-flash From $0.21/M tokens](https://modelslab.com/models/xiaomi/xiaomi-mimo-v2.6-flash) [#### Perceptron/Perceptron: Perceptron Mk1 perceptron-perceptron-mk1 From $0.82/M tokens](https://modelslab.com/models/perceptron/perceptron-perceptron-mk1) [#### Google/Google: Gemini Pro Latest google-gemini-pro-latest From $6.00/M tokens](https://modelslab.com/models/google/google-gemini-pro-latest) [#### MiniMax/MiniMax: MiniMax M3.1 Flash (free) minimax-minimax-m3.1-flash-free Free](https://modelslab.com/models/minimax/minimax-minimax-m3.1-flash-free) About Moondream: Moondream 3 Preview --- Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with... ### Technical Specifications Model IDmoondream-moondream3-preview CategoryLLM Models TaskText Generation Price$1.4 per million tokens AddedOctober 15, 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 Moondream: Moondream 3 Preview 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": "moondream-moondream3-preview", "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}") ``` ### Pricing Moondream: Moondream 3 Preview API costs $1.4 per million tokens. Plans start at $21/month, and open-source models are unlimited on the $149/month plan. [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 Moondream](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Moondream: Moondream 3 Preview FAQ --- ### What is Moondream: Moondream 3 Preview? Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with... ### How do I use the Moondream: Moondream 3 Preview API? You can integrate Moondream: Moondream 3 Preview into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "moondream-moondream3-preview" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Moondream: Moondream 3 Preview cost? Moondream: Moondream 3 Preview costs $1.4 per million tokens. ModelsLab plans start at $21/month (Basic), and the $149/month Open Source plan includes unlimited generation on open-source models. ### What is the Moondream: Moondream 3 Preview model ID? The model ID for Moondream: Moondream 3 Preview is "moondream-moondream3-preview". Use this ID in your API requests to specify this model. ### Do I need a paid plan to use Moondream: Moondream 3 Preview? Yes. ModelsLab is subscription-based with no free tier — plans start at $21/month (Basic, 3,250 API calls). The $149/month Open Source Unlimited plan includes unlimited generation across open-source models; premium third-party models are billed per call from your wallet. --- *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 - 2026-10-21*