Guide

2,840 step-by-step guides to setting up AI models from OpenAI, Anthropic, Google, OpenRouter, and more in TypingMind with your own API key.

Search and filter guides

Showing 2,449-2,499 of 2,840 guides
Hugging Face logo

Gemma 3 12B IT

Hugging Face · Mar 12, 2025

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

131.1K context
View
Hugging Face logo

Gemma 3 4B IT

Hugging Face · Mar 12, 2025

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

131.1K context
View
Novita logo

Gemma 3 27B IT

Novita · Mar 12, 2025

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

98.3K context
View
Novita logo

Gemma 3 12B IT

Novita · Mar 12, 2025

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

131.1K context
View
OpenRouter logo

TheDrummer: Skyfall 36B V2

OpenRouter · Mar 10, 2025

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

32.8K context
View
OpenRouter logo

Microsoft: Phi 4 Multimodal Instruct

OpenRouter · Mar 8, 2025

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/).

131.1K context
View
OpenRouter logo

Perplexity: Sonar Reasoning Pro

OpenRouter · Mar 7, 2025

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...

128K context
View
OpenRouter logo

Perplexity: Sonar Pro

OpenRouter · Mar 7, 2025

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...

200K context
View
OpenRouter logo

Perplexity: Sonar Deep Research

OpenRouter · Mar 7, 2025

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...

128K context
View
OpenRouter logo

Qwen: QwQ 32B

OpenRouter · Mar 5, 2025

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,...

131.1K context
View
Alibaba Cloud logo

QwQ Plus

Alibaba Cloud · Mar 5, 2025

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

131.1K context
View
Novita logo

DeepSeek V3 (Turbo)

Novita · Mar 5, 2025

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

64K context
View
Cohere logo

Aya Vision 8B

Cohere · Mar 4, 2025

Compact open multilingual vision model for OCR and visual question answering

16K context
View
Cohere logo

Aya Vision 32B

Cohere · Mar 4, 2025

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

16K context
View
Cohere logo

Command R7B Arabic

Cohere · Feb 27, 2025

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

128K context
View
Vercel AI Gateway logo

Mercury Coder Small Beta

Vercel AI Gateway · Feb 26, 2025

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

32K context
View
OpenRouter logo

Google: Gemini 2.0 Flash Lite

OpenRouter · Feb 25, 2025

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),...

1M context+1
View
OpenRouter logo

Anthropic: Claude 3.7 Sonnet (thinking)

OpenRouter · Feb 24, 2025

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...

200K context
View
OpenRouter logo

Anthropic: Claude 3.7 Sonnet

OpenRouter · Feb 24, 2025

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...

200K context
View
Anthropic logo

Claude Sonnet 3.7

Anthropic · Feb 19, 2025

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

200K context
View
Anthropic logo

Claude Sonnet 3.7 (latest)

Anthropic · Feb 19, 2025

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

200K context
View
AWS Bedrock logo

Claude Sonnet 3.7

AWS Bedrock · Feb 19, 2025

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

200K context
View
Vercel AI Gateway logo

Sonar

Vercel AI Gateway · Feb 19, 2025

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

127K context
View
OpenRouter logo

Mistral: Saba

OpenRouter · Feb 17, 2025

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...

32.8K context
View
xAI logo

Grok 3 Fast

xAI · Feb 17, 2025

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

131.1K context
View
xAI logo

Grok 3 Mini Fast Latest

xAI · Feb 17, 2025

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

131.1K context
View
xAI logo

Grok 3

xAI · Feb 17, 2025

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

131.1K context
View
xAI logo

Grok 3 Fast Latest

xAI · Feb 17, 2025

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

131.1K context
View
xAI logo

Grok 3 Latest

xAI · Feb 17, 2025

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

131.1K context
View
xAI logo

Grok 3 Mini

xAI · Feb 17, 2025

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

131.1K context
View
xAI logo

Grok 3 Mini Latest

xAI · Feb 17, 2025

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

131.1K context
View
xAI logo

Grok 3 Mini Fast

xAI · Feb 17, 2025

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

131.1K context
View
OpenRouter logo

Llama Guard 3 8B

OpenRouter · Feb 12, 2025

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)...

131.1K context
View
OpenRouter logo

OpenAI: o3 Mini High

OpenRouter · Feb 12, 2025

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...

200K context
View
OpenRouter logo

OpenAI: o3 Mini High (batch)

OpenRouter · Feb 12, 2025

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...

200K context
View
Chutes logo

Llama 3.2 3B Instruct

Chutes · Feb 12, 2025

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

16.4K context
View
Groq logo

Mistral Saba 24B

Groq · Feb 6, 2025

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

32.8K context
View
OpenRouter logo

Google: Gemini 2.0 Flash

OpenRouter · Feb 5, 2025

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...

1M context+2
View
OpenRouter logo

Qwen: Qwen VL Plus

OpenRouter · Feb 5, 2025

Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of pixels and extreme aspect ratios for...

131.1K context
View
OpenRouter logo

AionLabs: Aion-1.0

OpenRouter · Feb 4, 2025

Aion-1.0 is a multi-model system designed for high performance across various tasks, including reasoning and coding. It is built on DeepSeek-R1, augmented with additional models and techniques such as Tree...

131.1K context
View
OpenRouter logo

AionLabs: Aion-1.0-Mini

OpenRouter · Feb 4, 2025

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant...

131.1K context
View
OpenRouter logo

AionLabs: Aion-RP 1.0 (8B)

OpenRouter · Feb 4, 2025

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

32.8K context
View
OpenRouter logo

Qwen: Qwen VL Max

OpenRouter · Feb 1, 2025

Qwen VL Max is a visual understanding model with 7500 tokens context length. It excels in delivering optimal performance for a broader spectrum of complex tasks.

131.1K context
View
OpenRouter logo

Qwen: Qwen-Turbo

OpenRouter · Feb 1, 2025

Qwen-Turbo, based on Qwen2.5, is a 1M context model that provides fast speed and low cost, suitable for simple tasks.

131.1K context
View
OpenRouter logo

Qwen: Qwen2.5 VL 72B Instruct

OpenRouter · Feb 1, 2025

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

128K context
View
OpenRouter logo

Qwen: Qwen-Plus

OpenRouter · Feb 1, 2025

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

1M context
View
OpenRouter logo

Qwen: Qwen-Max

OpenRouter · Feb 1, 2025

Qwen-Max, based on Qwen2.5, provides the best inference performance among [Qwen models](/qwen), especially for complex multi-step tasks. It's a large-scale MoE model that has been pretrained on over 20 trillion...

32.8K context
View
Perplexity logo

Perplexity Sonar Deep Research

Perplexity · Feb 1, 2025

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

128K context
View
OpenRouter logo

OpenAI: o3 Mini

OpenRouter · Jan 31, 2025

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...

200K context
View
OpenRouter logo

OpenAI: o3 Mini (batch)

OpenRouter · Jan 31, 2025

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...

200K context
View
OpenRouter logo

Mistral: Mistral Small 3

OpenRouter · Jan 30, 2025

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

32.8K context
View