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

Mistral Small 3
DeepInfra · Jan 30, 2025
Efficient Mistral model for fast chat, extraction, and production assistants

DeepSeek: R1 Distill Qwen 32B
OpenRouter · Jan 29, 2025
DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](https://huggingface.co/Qwen/Qwen2.5-32B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new...

DeepSeek: R1 Distill Qwen 14B
OpenRouter · Jan 29, 2025
DeepSeek R1 Distill Qwen 14B is a distilled large language model based on [Qwen 2.5 14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. Other benchmark results include: - AIME 2024 pass@1: 69.7 - MATH-500 pass@1: 93.9 - CodeForces Rating: 1481 The model leverages fine-tuning from DeepSeek R1's outputs, enabling competitive performance comparable to larger frontier models.

Perplexity: Sonar
OpenRouter · Jan 27, 2025
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...

DeepSeek R1 Distill LLama 70B
Novita · Jan 27, 2025
DeepSeek reasoning model for multi-step analysis, math, coding, and tools

DeepSeek: R1 Distill Llama 70B
OpenRouter · Jan 23, 2025
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

ALLaM-2-7b
Groq · Jan 23, 2025
ALLaM-2-7b instruction tuned model by SDAIA

DeepSeek: R1
OpenRouter · Jan 20, 2025
DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....

DeepSeek R1 Distill Llama 70B
Groq · Jan 20, 2025
DeepSeek R1 Distill Llama 70B from Groq - text input, 131,072 token context

DeepSeek R1 0528 TEE
Chutes · Jan 20, 2025
DeepSeek R1 0528 TEE from Chutes - text input, 163,840 token context

DeepSeek R1
Synthetic · Jan 20, 2025
DeepSeek R1 from Synthetic - text input, 128,000 token context

DeepSeek V3
Synthetic · Jan 20, 2025
DeepSeek V3 from Synthetic - text input, 128,000 token context

DeepSeek-R1
AWS Bedrock · Jan 20, 2025
Classic open reasoning model for transparent math, coding, and deliberate problem solving

DeepSeek-R1 (US)
AWS Bedrock · Jan 20, 2025
Classic open reasoning model for transparent math, coding, and deliberate problem solving
DeepSeek-R1
Hugging Face · Jan 20, 2025
Classic open reasoning model for transparent math, coding, and deliberate problem solving

DeepSeek-R1
Together AI · Jan 20, 2025
Classic open reasoning model for transparent math, coding, and deliberate problem solving

DeepSeek-R1
Vercel AI Gateway · Jan 20, 2025
Classic open reasoning model for transparent math, coding, and deliberate problem solving

DeepSeek R1 Distill Qwen 14B
Novita · Jan 20, 2025
Qwen reasoning model for deliberate problem solving, math, and coding

DeepSeek R1 (Turbo)
Novita · Jan 20, 2025
Classic open reasoning model for transparent math, coding, and deliberate problem solving

DeepSeek R1 Distill Qwen 32B
Novita · Jan 20, 2025
Qwen reasoning model for deliberate problem solving, math, and coding

Qwen-Omni Turbo
Alibaba Cloud · Jan 19, 2025
Qwen omni model for text, vision, audio, and multimodal agent tasks

MiniMax: MiniMax-01
OpenRouter · Jan 15, 2025
MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...

GPT-5.2 Codex
Venice AI · Jan 15, 2025
Code-specialist GPT for repository edits, reviews, and long-running software agents

Claude Sonnet 4.5
Venice AI · Jan 15, 2025
Claude Sonnet 4.5 from Venice AI - text, image input, 198,000 token context

Microsoft: Phi 4
OpenRouter · Jan 10, 2025
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

Sao10K: Llama 3.1 70B Hanami x1
OpenRouter · Jan 8, 2025
This is [Sao10K](/sao10k)'s experiment over [Euryale v2.2](/sao10k/l3.1-euryale-70b).

voyage-3-large
Vercel AI Gateway · Jan 7, 2025
Embedding model for semantic search, retrieval, clustering, and ranking pipelines

InternVL3 78B TEE
Chutes · Jan 6, 2025
InternVL3 78B TEE from Chutes - text, image input, 32,768 token context

Qwen-MT Plus
Alibaba Cloud · Jan 1, 2025
Translation model for multilingual conversion, localization, and cross-language workflows

Qwen-MT Turbo
Alibaba Cloud · Jan 1, 2025
Translation model for multilingual conversion, localization, and cross-language workflows

LucidNova RF1 100B
LucidQuery · Dec 28, 2024
Reasoning model for deliberate analysis, multi-step problem solving, and tool use

DeepSeek: DeepSeek V3
OpenRouter · Dec 26, 2024
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

DeepSeek-V3
DeepInfra · Dec 26, 2024
Open DeepSeek MoE chat model for coding, math, and general reasoning
DeepSeek-V3
Hugging Face · Dec 26, 2024
DeepSeek chat model for instruction following, coding, and analysis

DeepSeek-V3
Together AI · Dec 26, 2024
Open DeepSeek MoE chat model for coding, math, and general reasoning

DeepSeek-V3
Novita · Dec 26, 2024
Open DeepSeek MoE chat model for coding, math, and general reasoning

o3-mini
OpenAI · Dec 20, 2024
Smaller o-series reasoner for economical coding, math, and planning tasks

o3-mini
Vercel AI Gateway · Dec 20, 2024
Smaller o-series reasoner for economical coding, math, and planning tasks

o3-mini
Cloudflare AI Gateway · Dec 20, 2024
Smaller o-series reasoner for economical coding, math, and planning tasks

Sao10K: Llama 3.3 Euryale 70B
OpenRouter · Dec 18, 2024
Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).

OpenAI: o1
OpenRouter · Dec 17, 2024
The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...

OpenAI: o1 (batch)
OpenRouter · Dec 17, 2024
The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learning to reason...

Cohere: Command R7B (12-2024)
OpenRouter · Dec 14, 2024
Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

Command R7B
Cohere · Dec 13, 2024
Cohere retrieval model for long-context chat and enterprise RAG workflows

Grok 2 (1212)
xAI · Dec 12, 2024
Grok 2 (1212) from xAI - text input, 131,072 token context

Google: Gemini 2.0 Flash Experimental (free)
OpenRouter · Dec 11, 2024
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 introduces notable enhancements in multimodal understanding, coding capabilities, complex instruction following, and function calling. These advancements come together to deliver more seamless and robust agentic experiences.

Gemini 2.0 Flash-Lite
Google · Dec 11, 2024
Legacy model retained for compatibility with older integrations

Gemini 2.0 Flash
Google · Dec 11, 2024
Earlier Gemini Flash workhorse for responsive multimodal apps and tool use

Meta: Llama 3.3 70B Instruct (free)
OpenRouter · Dec 6, 2024
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Meta: Llama 3.3 70B Instruct
OpenRouter · Dec 6, 2024
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Llama 3.3 70B
Groq · Dec 6, 2024
Open Llama instruction model for multilingual chat, reasoning, and coding

