# Recommended Models ServerAssistantAI supports a wide range of language models from different providers, including premium and free options, allowing server owners to choose the model that best fits their needs. Here's what we recommend, listed from **most recommended to least**. ## Embedding Models Embedding models are used to convert text data into numerical representations called embeddings. These embeddings capture the semantic meaning and relationships between different pieces of text. When the `documents/` directory is updated, the content is sent to the embedding API. The resulting embeddings are saved to the `cache/` directory, allowing the AI to find relevant context efficiently without reprocessing or making new API requests for each query.
ProviderEmbedding ModelPricingDescription
Google-AIStudiotext-embedding-004Free & PaidGoogle's state-of-the-art embeddings for semantic search and classification tasks.
OpenAItext-embedding-3-largePaidOpenAI's large embedding model for text similarity and retrieval tasks.
Github-Modelsopenai/text-embedding-3-largeFree & PaidOpenAI's large embedding model for text similarity and retrieval tasks.
Cohereembed-english-v3.0Free & PaidEnglish embedding model great for noisy data, enabling better retrievals for RAG.
Cohereembed-multilingual-v3.0Free & PaidMultilingual embedding model great for noisy data, enabling better retrievals for RAG.
OpenAItext-embedding-3-smallPaidOpenAI's small embedding model for text similarity and retrieval tasks.
{% hint style="info" %} ServerAssistantAI only sends information to the embedding API when changes are made to the `documents/` directory. If no changes are detected, the plugin will use the previously cached embeddings to reduce API calls. {% endhint %} ## Large Language Models Large Language Models (LLMs) are powerful AI models that can understand and generate human-like text based on the input they receive. In ServerAssistantAI, when a user asks a question, the system retrieves relevant cached context from the embedding API results. This context, along with the user's question, is sent to the LLM to generate accurate and context-aware responses.
ProviderLarge Language ModelPricingDescription
OpenAIgpt-4oPaidOpenAI's most advanced model. Same intelligence as GPT-4 Turbo but 2x faster and 50% cheaper.
Github-Modelsopenai/gpt-4oFree & PaidOpenAI's most advanced model. Same intelligence as GPT-4 Turbo but 2x faster and 50% cheaper.
Anthropicclaude-opus-4.1-20250805PaidAnthropic's upgraded model with enhanced agentic tasks, real-world coding, and reasoning capabilities.
CerebrasAIqwen-3-235b-a22b-instruct-2507Free & PaidAlibaba’s frontier-scale model served on Cerebras. Delivers state-of-the-art non-reasoning performance with increadible speed.
Anthropicclaude-opus-4-20250514PaidAnthropic's most intelligent model with hybrid reasoning and 200K context window, excelling at coding and working autonomously for hours.
Google-AIStudiogemini-2.5-flashFree & PaidGoogle's fast thinking model optimized for speed and cost-efficiency with controllable thinking budgets for high-volume tasks.
OpenAIgpt-4.1PaidOpenAI's enhanced model with major coding improvements and 1 million token context window.
Github-Modelsopenai/gpt-4.1Free & PaidOpenAI's enhanced model with major coding improvements and 1 million token context window.
Groqdeepseek-r1-distill-llama-70bFree & PaidDeepSeek's efficient 70B reasoning model distilled from larger models.
Anthropicclaude-sonnet-4-20250514PaidAnthropic's high-performance model with 200K context window, achieving 72.7% on SWE-bench with superior instruction following.
OpenAIgpt-4.1-miniPaidOpenAI's efficient model competitive with GPT-4o but 50% faster and 83% cheaper with 1 million token context window.
Github-Modelsopenai/gpt-4.1-miniFree & PaidOpenAI's efficient model competitive with GPT-4o but 50% faster and 83% cheaper with 1 million token context window.
Google-AIStudiogemini-2.0-flash-001Free & PaidGoogle's next-generation flash model with native tool use, superior speed, and 1M token context window for multimodal applications.
Google-AIStudiogemma-3-27b-itFreeGoogle's open-source 27B parameter model optimized for instruction following and conversational AI with efficient performance.
Google-AIStudiogemini-1.5-proFree & PaidGemini 1.5 Pro offers long-context understanding, with a context window of up to 1 million tokens.
Groqqwen/qwen3-32bFree & PaidAlibaba's hybrid model switching between thinking and fast modes, supporting 119 languages and competing with top proprietary models.
Coherecommand-a-03-2025Free & PaidCohere's most performant 111B model with 256K context, delivering 150% higher throughput.
Anthropicclaude-3-sonnet-20240307PaidClaude 3.5 Sonnet delivers enhanced intelligence and speed, ideal for advanced tasks.
OpenAIgpt-4o-miniPaidOpenAI's most cost-efficient small model that’s smarter and cheaper than mostly all other paid models.
Github-Modelsopenai/gpt-4o-miniFree & PaidOpenAI's most cost-efficient small model that’s smarter and cheaper than mostly all other paid models.
Groqllama-3.1-70b-versatileFree & PaidMeta's Llama 3.1 70B instruction-tuned model outperforms all open-source chat models and even closed-source models and using Groq, the inference speed is 250+ Tokens per second!
OpenAIgpt-4-turboPaidOpenAI's GPT-4-Turbo model with 128K context, newer knowledge and more powerful than GPT-4.
Google-AIStudiogemini-1.5-flashFree & PaidGemini 1.5 Flash has higher rate limits than Gemini 1.5 Pro and is Google's fastest, most cost-efficient model.
Anthropicclaude-3-opus-20240307PaidAnthropic's most intelligent model with great performance on highly complex tasks.
Groqllama3-70b-8192Free & PaidMeta's Llama 3 70B instruction-tuned model which outperforms almost all open-source chat models and using Groq, the inference speed is 300+ Tokens per second!
Anthropicclaude-3-haiku-20240307PaidClaude 3 Haiku is Anthropic's fastest model for near-instant responsiveness.
HuggingFacemeta-llama/Meta-Llama-3-8B-InstructFreeMeta's Llama 3 8B instruction-tuned model and outperforming many open-source chat models.
HuggingFace01-ai/Yi-1.5-34B-ChatFree01.AI's Yi-1.5 model, offering strong performance in coding, math, reasoning, and instruction-following.
HuggingFacemistralai/Mixtral-8x7B-Instruct-v0.1FreeMistral AI's 8x7B instruction-following model, version 0.1.
OpenAIgpt-3.5-turboPaidOpenAI's GPT-3.5 model with a larger context size of 16K tokens.
{% hint style="warning" %} Please note that each model may have specific requirements or considerations for optimal performance. When selecting a model, consider factors such as: * System prompt configuration: Different models may require adjustments to the system prompt to achieve the best results. Check the documentation provided by the model's creators for tips on prompt engineering and configuration. * Open-source free LLMs have a higher chance of hallucinating compared to paid models. {% endhint %} [^1]: **Free** Rate Limits: * 2 Request Per Minute * 32,000 Tokens Per Minute * 50 Requests Per Day \ **Paid** Rate Limits: * 360 Request Per Minute * 2 Million Tokens Per Minute * 10,000 Requests Per Day [^2]: **Tier 1** Rate Limits: * 3,000 Request Per Minute * 1,000,000 Tokens Per Minute [^3]: **Free Rate Limits (Low Tier):** * 15 Requests Per Minute * 150 Requests Per Day * 64,000 Input Tokens Per Request * 5 Concurrent Requests **Paid Rate Limits:** * Production grade limits (see Azure documentation) [^4]: **Free** Rate Limits: * 5 Request Per Minute * 1,000 Total Requests Per Month * 100,000 Total Tokens Per Minute
**Paid** Rate Limits: * 10,000 Request Per Minute [^5]: **Free** Rate Limits: * 5 Request Per Minute * 1,000 Total Requests Per Month * 100,000 Total Tokens Per Minute \ **Paid** Rate Limits: * 10,000 Request Per Minute [^6]: **Tier 1** Rate Limits: * 500 Requests Per Minute * 30,000 Tokens Per Minute * No Daily Limits **Tier 2** Rate Limits: * 5,000 Requests Per Minute * 450,000 Tokens Per Minute * No Daily Limits [^7]: **Free Rate Limits (High Tier):** * 10 Requests Per Minute * 50 Requests Per Day * 8,000 Input Tokens Per Request * 4,000 Output Tokens Per Request **Paid Rate Limits:** * Production grade limits (see Azure documentation) [^8]: **Tier 1** Rate Limits: * 50 Requests Per Minute * 30,000 Input Tokens Per Minute * 8,000 Output Tokens Per Minute **Tier 2** Rate Limits: * 1,000 Requests Per Minute * 450,000 Input Tokens Per Minute * 90,000 Output Tokens Per Minute [^9]: **Free** Rate Limits: * 30 Requests Per Minute * 60,000 Tokens Per Minute * 14,400 Requests Per Day **Paid** Rate Limits: * Exploration Tier (see CerebrasAI documentation) [^10]: **Free** Rate Limits: * 10 Requests Per Minute * 250,000 Tokens Per Minute * 250 Requests Per Day **Tier 1** Rate Limits: * 1,000 Requests Per Minute * 1,000,000 Tokens Per Minute * 10,000 Requests Per Day **Tier 2** Rate Limits: * 2,000 Requests Per Minute * 3,000,000 Tokens Per Minute * 100,000 Requests Per Day [^11]: **Free** Rate Limits: * 30 Requests Per Minute * 6,000 Tokens Per Minute * 1,000 Requests Per Day **Paid** Rate Limits: * 1,000 Requests Per Minute * 300,000 Tokens Per Minute * 500,000 Requests Per Day [^12]: **Free Rate Limits (Low Tier):** * 15 Requests Per Minute * 150 Requests Per Day * 8,000 Input Tokens Per Request * 4,000 Output Tokens Per Request **Paid Rate Limits:** * Production grade limits (see Azure documentation) [^13]: **Free** Rate Limits: * 15 Requests Per Minute * 1,000,000 Tokens Per Minute * 200 Requests Per Day **Tier 1** Rate Limits: * 2,000 Requests Per Minute * 4,000,000 Tokens Per Minute * No daily limit **Tier 2** Rate Limits: * 10,000 Requests Per Minute * 10,000,000 Tokens Per Minute * No daily limit [^14]: **Free** Rate Limits: * 30 Requests Per Minute * 15,000 Tokens Per Minute * 14,400 Requests Per Day [^15]: **Free** Rate Limits: * 2 Request Per Minute * 32,000 Tokens Per Minute * 50 Requests Per Day
**Paid** Rate Limits: * 360 Request Per Minute * 2 Million Tokens Per Minute * 10,000 Requests Per Day [^16]: **Free** Rate Limits: * 60 Requests Per Minute * 6,000 Tokens Per Minute * 1,000 Requests Per Day **Paid** Rate Limits: * 1,000 Requests Per Minute * 300,000 Tokens Per Minute * 500,000 Requests Per Day [^17]: **Free** Rate Limits: * 20 Requests Per Minute * 1,000 Total Requests Per Month \ **Paid** Rate Limits: * 500 Requests Per Minute [^18]: **Tier 1** Rate Limits: * 50 Request Per Minute * 40,000 Tokens Per Minute * 1,000,000 Tokens Per Day [^19]: **Tier 1** Rate Limits: * 500 Request Per Minute * 30,000 Tokens Per Minute [^20]: **Free** Rate Limits: * 15 Request Per Minute * 1 Million Tokens Per Minute * 1,500 Requests Per Day
**Paid** Rate Limits: * 1,000 Request Per Minute * 2 Million Tokens Per Minute [^21]: **Tier 1** Rate Limits: * 50 Request Per Minute * 20,000 Tokens Per Minute * 1,000,000 Tokens Per Day [^22]: **Tier 1** Rate Limits: * 50 Request Per Minute * 50,000 Tokens Per Minute * 5,000,000 Tokens Per Day [^23]: **Tier 1** Rate Limits: * 3,500 Request Per Minute * 60,000 Tokens Per Minute * 10,000 Requests Per Day