--- title: Arcee AI: Trinity Mini API | Text Generation | ModelsLab description: Compact 26B MoE LLM with 3B active params/token, 128K context, excels in reasoning, tool calling & agent workflows for cloud/on-prem apps.[1][2][3] url: https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/arcee-ai-trinity-mini.md canonical: https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/arcee-ai-trinity-mini.md type: product component: Playground/LLM/Index generated_at: 2026-05-21T09:25:41.547769Z --- Arcee AI: Trinity Mini --- [LLMs.txt](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/arcee-ai-trinity-mini/llms.txt) [.md](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/arcee-ai/arcee-ai-trinity-mini.md) arcee-ai-trinity-mini arcee-ai Closed Source Model $0.097500 / call Arcee AI: Trinity Mini --- 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 ### Arcee AI: Trinity Mini arcee-ai arcee-ai-trinity-mini Copy model ID PricingInput $0.045 / 1M tokens Output $0.15 / 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-frontend-v2-927501783998.us-east4.run.app/models?feature=llmaster) [MM](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/minimax-minimax-m2)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [MiniMax: MiniMax M2 Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/minimax-minimax-m2) [![Qwen 2.5 Coder 32B Instruct](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/d69ed8fc-70f1-4897-a128-eaab5d246da8.png)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen2.5-Coder-32B-Instruct)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai) [Qwen 2.5 Coder 32B Instruct Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-Qwen2.5-Coder-32B-Instruct) [![Qwen QwQ-32B](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/a4c5cb51-1924-4e47-a95b-6d54566ddb2a.png)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-QwQ-32B)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai) [Qwen QwQ-32B Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/Qwen-QwQ-32B) [OO](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-o3-mini)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [OpenAI: o3 Mini Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-o3-mini) [ZG](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/z-ai-glm-4.5-air-free)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [Z.ai: GLM 4.5 Air (free) Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/z-ai-glm-4.5-air-free) [RR](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/relace-relace-search)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [Relace: Relace Search Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/relace-relace-search) [![DeepSeek: R1 Distill Llama 70B](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/c69ce015-5725-4120-afed-a0bafd224b46.png)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/deepseek-deepseek-r1-distill-llama-70b)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [DeepSeek: R1 Distill Llama 70B Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/deepseek-deepseek-r1-distill-llama-70b) [![Meta Llama 3 8B Instruct](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/3b3ccb2f-4bd5-43a7-964f-55f49a4353a5.png)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Meta-Llama-3-8B-Instruct)[Together AI](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai) [Meta Llama 3 8B Instruct Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/together_ai/meta-llama-Meta-Llama-3-8B-Instruct) [DD](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/deepseek-deepseek-v3.2)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [DeepSeek: DeepSeek V3.2 Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/deepseek-deepseek-v3.2) [![Gemma-2 Instruct (27B)](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/2341f146-f559-418a-8df8-51f391df85dc.png)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/google_deepmind/google-gemma-2-27b-it)[ModelsLab](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/google_deepmind) [Gemma-2 Instruct (27B) Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/google_deepmind/google-gemma-2-27b-it) [SR](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/switchpoint-router)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [Switchpoint Router Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/switchpoint-router) [QQ](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/qwen-qwen3-max)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [Qwen: Qwen3 Max Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/qwen-qwen3-max) [ML](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/meta-llama-llama-4-scout)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [Meta: Llama 4 Scout Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/meta-llama-llama-4-scout) [OG](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-gpt-5-mini)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [OpenAI: GPT-5 Mini Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/openai-gpt-5-mini) [![Anthropic: Claude 3.5 Haiku](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/065e7f2a-3b41-4e5e-bdc7-4dbafffd4a96.png)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/anthropic-claude-3.5-haiku)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [Anthropic: Claude 3.5 Haiku Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/anthropic-claude-3.5-haiku) [ZG](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/z-ai-glm-4.6)[Open Router](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [Z.ai: GLM 4.6 Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router/z-ai-glm-4.6) [![Gemini 2.5 Flash Image Preview ](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/97c6f065-57f9-45b0-a190-08e5f97f70a8.png)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/google/gemini-2.5-flash-image-preview)[Google](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/google) [Gemini 2.5 Flash Image Preview Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/google/gemini-2.5-flash-image-preview) [![Meta Llama 3.1 8B Instruct Turbo](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/c3b4bc17-3e9e-40e2-b6ac-673dcedc13a3.png)](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/meta/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo)[ModelsLab](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/meta) [Meta Llama 3.1 8B Instruct Turbo Closed Source Model](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/meta/meta-llama-Meta-Llama-3.1-8B-Instruct-Turbo) About Arcee AI: Trinity Mini --- Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function... ### Technical Specifications Model IDarcee-ai-trinity-miniCategoryLLM ModelsTaskText GenerationPrice$0.097500 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 Arcee AI: Trinity Mini into your application with a single API call. Get your API key from the [pricing page](https://modelslab-frontend-v2-927501783998.us-east4.run.app/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": "arcee-ai-trinity-mini", "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 Arcee AI: Trinity Mini API costs $0.097500 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab-frontend-v2-927501783998.us-east4.run.app/pricing) ### Use Cases - AI chatbots and virtual assistants - Code generation and developer tools - Content writing and copywriting automation - Data analysis, summarization, and extraction [Learn more about Arcee AI: Trinity Mini](https://modelslab-frontend-v2-927501783998.us-east4.run.app/arcee-ai-trinity-mini) [Browse LLM Models](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models?feature=llmaster) [More from Arcee Ai](https://modelslab-frontend-v2-927501783998.us-east4.run.app/models/open_router) [View Pricing](https://modelslab-frontend-v2-927501783998.us-east4.run.app/pricing) Arcee AI: Trinity Mini FAQ --- ### What is Arcee AI: Trinity Mini? Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function... ### How do I use the Arcee AI: Trinity Mini API? You can integrate Arcee AI: Trinity Mini into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "arcee-ai-trinity-mini" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Arcee AI: Trinity Mini cost? Arcee AI: Trinity Mini costs $0.097500 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Arcee AI: Trinity Mini model ID? The model ID for Arcee AI: Trinity Mini is "arcee-ai-trinity-mini". Use this ID in your API requests to specify this model. ### Does Arcee AI: Trinity Mini have a free tier? Yes, ModelsLab offers a free tier that lets you try Arcee AI: Trinity Mini 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 - 2026-05-21*