Guide

Open Gemma instruction model for efficient chat and self-hosted deployments

GPT-4o mini Search Preview is a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...

Gemma 3 27B from Google - text, image input, 131,072 token context

Open multimodal Gemma instruction model for multilingual text generation and image understanding

Open multimodal Gemma instruction model for efficient text generation and image understanding

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

Open multimodal Gemma instruction model for multilingual text generation and image understanding

Open multimodal Gemma instruction model for efficient text generation and image understanding

Open Gemma instruction model for efficient chat and self-hosted deployments

Open Gemma instruction model for efficient chat and self-hosted deployments

Open Gemma instruction model for efficient chat and self-hosted deployments

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

Phi-4 Multimodal Instruct is a versatile 5.6B parameter foundation model that combines advanced reasoning and instruction-following capabilities across both text and visual inputs, providing accurate text outputs. The unified architecture enables efficient, low-latency inference, suitable for edge and mobile deployments. Phi-4 Multimodal Instruct supports text inputs in multiple languages including Arabic, Chinese, English, French, German, Japanese, Spanish, and more, with visual input optimized primarily for English. It delivers impressive performance on multimodal tasks involving mathematical, scientific, and document reasoning, providing developers and enterprises a powerful yet compact model for sophisticated interactive applications. For more information, see the [Phi-4 Multimodal blog post](https://azure.microsoft.com/en-us/blog/empowering-innovation-the-next-generation-of-the-phi-family/).

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks,...

Qwen reasoning model for deliberate problem solving, math, and coding

Fast DeepSeek model for efficient chat, coding help, and agent loops

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Compact open multilingual vision model for OCR and visual question answering

Open multilingual vision model for OCR, visual reasoning, and image question answering

Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge

Coding model for repository understanding, refactors, and agentic engineering tasks

Gemini 2.0 Flash Lite offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5),...

Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and...

Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and...

Claude Sonnet 3.7 from Anthropic - text, image, pdf input, 200,000 token context

Claude Sonnet 3.7 (latest) from Anthropic - text, image, pdf input, 200,000 token context

Claude Sonnet 3.7 from AWS Bedrock - text, image, pdf input, 200,000 token context

Sonar search model for current answers, retrieval, and citation-backed chat

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...

Grok 3 Fast from xAI - text input, 131,072 token context

Grok 3 Mini Fast Latest from xAI - text input, 131,072 token context

Grok 3 from xAI - text input, 131,072 token context

Grok 3 Fast Latest from xAI - text input, 131,072 token context

Grok 3 Latest from xAI - text input, 131,072 token context

Grok 3 Mini from xAI - text input, 131,072 token context

Grok 3 Mini Latest from xAI - text input, 131,072 token context

Grok 3 Mini Fast from xAI - text input, 131,072 token context

Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification)...

OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...

OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...

Llama 3.2 3B Instruct from Chutes - text input, 16,384 token context

Mistral Saba 24B from Groq - text input, 32,768 token context

Gemini Flash 2.0 offers a significantly faster time to first token (TTFT) compared to [Gemini Flash 1.5](/google/gemini-flash-1.5), while maintaining quality on par with larger models like [Gemini Pro 1.5](/google/gemini-pro-1.5). It...