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

GPT-4o (Fast)
Vercel AI Gateway · May 13, 2024
Omni-era GPT for multimodal chat, practical coding, and general assistants

GPT-4o
Vercel AI Gateway · May 13, 2024
Omni-era GPT for multimodal chat, practical coding, and general assistants

GPT-4o
Cloudflare AI Gateway · May 13, 2024
Omni-era GPT for multimodal chat, practical coding, and general assistants

Titan Text Embeddings V2
Vercel AI Gateway · Apr 30, 2024
Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Hermes 2 Pro Llama 3 8B
Novita · Apr 30, 2024
Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue

Llama3 70B Instruct
Novita · Apr 25, 2024
Open Llama instruction model for multilingual chat, reasoning, and coding

Llama 3 8B Instruct
Novita · Apr 25, 2024
Open Llama instruction model for multilingual chat, reasoning, and coding

Meta: Llama 3 70B Instruct
OpenRouter · Apr 18, 2024
Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 70B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...

Meta: Llama 3 8B Instruct
OpenRouter · Apr 18, 2024
Meta's latest class of model (Llama 3) launched with a variety of sizes & flavors. This 8B instruct-tuned version was optimized for high quality dialogue usecases. It has demonstrated strong...

Llama 3 8B
Groq · Apr 18, 2024
Llama 3 8B from Groq - text input, 8,192 token context

Llama 3 70B
Groq · Apr 18, 2024
Llama 3 70B from Groq - text input, 8,192 token context

Meta Llama 3 8B Instruct Lite
Together AI · Apr 18, 2024
Compact Llama instruction model for fast chat and local deployment

Mistral: Mixtral 8x22B Instruct
OpenRouter · Apr 17, 2024
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...

Mixtral 8x22B
Mistral · Apr 17, 2024
Mistral model for multilingual chat, reasoning, and tool-assisted workflows

WizardLM-2 8x22B
OpenRouter · Apr 16, 2024
WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models. It is...

voyage-law-2
Vercel AI Gateway · Apr 15, 2024
Embedding model for semantic search, retrieval, clustering, and ranking pipelines

WizardLM 2 8x22B
Novita · Apr 15, 2024
Microsoft WizardLM instruction-tuned Mixtral MoE for multilingual dialogue and complex tasks

OpenAI: GPT-4 Turbo
OpenRouter · Apr 9, 2024
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

OpenAI: GPT-4 Turbo (batch)
OpenRouter · Apr 9, 2024
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

Qwen-VL Max
Alibaba Cloud · Apr 8, 2024
Qwen vision-language model for visual reasoning, documents, and agent tasks

Command R+
AWS Bedrock · Apr 4, 2024
Command R+ from AWS Bedrock - text input, 128,000 token context

Qwen Max
Alibaba Cloud · Apr 3, 2024
Flagship Qwen model for complex reasoning, coding, and agentic workflows

BGE Reranker V2 M3
Novita · Mar 15, 2024
Lightweight multilingual cross-encoder that scores query-document relevance

Anthropic: Claude 3 Haiku
OpenRouter · Mar 13, 2024
Claude 3 Haiku is Anthropic's fastest and most compact model for near-instant responsiveness. Quick and accurate targeted performance. See the launch announcement and benchmark results [here](https://www.anthropic.com/news/claude-3-haiku) #multimodal

Claude Haiku 3
Anthropic · Mar 13, 2024
Claude Haiku 3 from Anthropic - text, image, pdf input, 200,000 token context

Claude Haiku 3
AWS Bedrock · Mar 13, 2024
Claude Haiku 3 from AWS Bedrock - text, image, pdf input, 200,000 token context

Recraft V2
Vercel AI Gateway · Mar 13, 2024
Image model for prompt-driven generation, editing, and visual design workflows

Claude Haiku 3
Vercel AI Gateway · Mar 13, 2024
Legacy model retained for compatibility with older integrations

Command R
AWS Bedrock · Mar 11, 2024
Command R from AWS Bedrock - text input, 128,000 token context

Claude Sonnet 3
Anthropic · Mar 4, 2024
Claude Sonnet 3 from Anthropic - text, image, pdf input, 200,000 token context

Claude Sonnet 3
AWS Bedrock · Mar 4, 2024
Claude Sonnet 3 from AWS Bedrock - text, image, pdf input, 200,000 token context

Claude Opus 3
Anthropic · Feb 29, 2024
Claude Opus 3 from Anthropic - text, image, pdf input, 200,000 token context

Claude Opus 3
AWS Bedrock · Feb 29, 2024
Claude Opus 3 from AWS Bedrock - text, image, pdf input, 200,000 token context

Mistral Large
OpenRouter · Feb 26, 2024
This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

Gemini 1.5 Pro
Google · Feb 15, 2024
Gemini 1.5 Pro from Google - text, image, audio, video input, 1,000,000 token context

BGE M3
Novita · Jan 30, 2024
Multilingual embedding model combining dense, sparse, and multi-vector retrieval

OpenAI: GPT-3.5 Turbo (older v0613)
OpenRouter · Jan 25, 2024
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.

OpenAI: GPT-4 Turbo Preview
OpenRouter · Jan 25, 2024
The preview GPT-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. Training data: up to Dec 2023. **Note:** heavily rate limited by OpenAI while...

text-embedding-3-small
OpenAI · Jan 25, 2024
Embedding model for semantic search, retrieval, clustering, and ranking pipelines

text-embedding-3-large
OpenAI · Jan 25, 2024
Embedding model for semantic search, retrieval, clustering, and ranking pipelines

text-embedding-3-small
Vercel AI Gateway · Jan 25, 2024
Small, efficient OpenAI text embedding model

text-embedding-3-large
Vercel AI Gateway · Jan 25, 2024
Most capable OpenAI embedding model for English and non-English text

Qwen Plus
Alibaba Cloud · Jan 25, 2024
Qwen instruction model for multilingual chat, reasoning, and tool use

Qwen-VL Plus
Alibaba Cloud · Jan 25, 2024
Qwen vision-language model for visual reasoning, documents, and agent tasks

Mistral Tiny
OpenRouter · Jan 10, 2024
Note: This model is being deprecated. Recommended replacement is the newer [Ministral 8B](/mistral/ministral-8b) This model is currently powered by Mistral-7B-v0.2, and incorporates a "better" fine-tuning than [Mistral 7B](/models/mistralai/mistral-7b-instruct-v0.1), inspired by community work. It's best used for large batch processing tasks where cost is a significant factor but reasoning capabilities are not crucial.

Sonar
Perplexity · Jan 1, 2024
Fast web-grounded Sonar for current answers, citations, and lightweight retrieval

Sonar Pro
Perplexity · Jan 1, 2024
Deeper Sonar search model with broader retrieval and stronger synthesis

Sonar Reasoning Pro
Perplexity · Jan 1, 2024
Web-grounded Sonar for multi-step research questions that need cited reasoning

voyage-code-2
Vercel AI Gateway · Jan 1, 2024
Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Qwen Plus Character (Japanese)
Alibaba Cloud · Jan 1, 2024
Qwen instruction model for multilingual chat, reasoning, and tool use

Mistral: Mistral 7B Instruct v0.2
OpenRouter · Dec 28, 2023
A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length. An improved version of [Mistral 7B Instruct](/modelsmistralai/mistral-7b-instruct-v0.1), with the following changes: - 32k context window (vs 8k context in v0.1) - Rope-theta = 1e6 - No Sliding-Window Attention

