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

ERNIE 4.5 21B A3B
Novita · Jun 30, 2025
Open ERNIE text MoE with 21B total and 3B active parameters

ERNIE 4.5 VL 424B A47B
Novita · Jun 30, 2025
Multimodal reasoning model for visual analysis, planning, and tool use

ERNIE 4.5 300B A47B
Novita · Jun 30, 2025
Open-weight instruction model for adaptable chat and self-hosted production workloads

Inception: Mercury
OpenRouter · Jun 26, 2025
Mercury is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like GPT-4.1 Nano and Claude...

Mistral: Mistral Small 3.2 24B
OpenRouter · Jun 20, 2025
Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...

Mistral Small 3.2
Mistral · Jun 20, 2025
Efficient Mistral model for fast chat, extraction, and production assistants

Mistral Small 3.2 24B Instruct
Venice AI · Jun 20, 2025
Efficient Mistral model for fast chat, extraction, and production assistants

MiniMax: MiniMax M1
OpenRouter · Jun 17, 2025
MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom "lightning attention" mechanism, allowing it...

Google: Gemini 2.5 Flash
OpenRouter · Jun 17, 2025
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Google: Gemini 2.5 Flash (batch)
OpenRouter · Jun 17, 2025
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Google: Gemini 2.5 Pro
OpenRouter · Jun 17, 2025
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Google: Gemini 2.5 Pro (batch)
OpenRouter · Jun 17, 2025
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Gemini 2.5 Flash
Google · Jun 17, 2025
Fast Gemini workhorse for multimodal apps where latency and price matter

Gemini Live 2.5 Flash Preview Native Audio
Google · Jun 17, 2025
Gemini Live 2.5 Flash Preview Native Audio from Google - text, audio, video input, 131,072 token context

Gemini 2.5 Flash-Lite
Google · Jun 17, 2025
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Gemini 2.5 Flash Lite Preview 06-17
Google · Jun 17, 2025
Gemini 2.5 Flash Lite Preview 06-17 from Google - text, image, audio, video, pdf input, 1,048,576 token context

Gemini 2.5 Pro
Google · Jun 17, 2025
Google's proven reasoning model for coding, math, and multimodal analysis
MiniMax M1 80K
Hugging Face · Jun 17, 2025
MiniMax model for chat, coding, office work, and agentic tasks

Gemini 2.5 Flash Lite
Vercel AI Gateway · Jun 17, 2025
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

Gemini 2.5 Flash
Vercel AI Gateway · Jun 17, 2025
Fast Gemini workhorse for multimodal apps where latency and price matter

Gemini 2.5 Pro
Vercel AI Gateway · Jun 17, 2025
Google's proven reasoning model for coding, math, and multimodal analysis

MiniMax M1 80K
Novita · Jun 17, 2025
Open hybrid-attention MoE reasoning model with a million-token context and an 80K thinking budget

Gemini 2.5 Flash
Cloudflare AI Gateway · Jun 17, 2025
Fast Gemini workhorse for multimodal apps where latency and price matter

Gemini 2.5 Pro
Cloudflare AI Gateway · Jun 17, 2025
Google's proven reasoning model for coding, math, and multimodal analysis

Gemini 2.5 Flash-Lite
Cloudflare AI Gateway · Jun 17, 2025
Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

MoonshotAI: Kimi Dev 72B
OpenRouter · Jun 16, 2025
Kimi-Dev-72B is an open-source large language model fine-tuned for software engineering and issue resolution tasks. Based on Qwen2.5-72B, it is optimized using large-scale reinforcement learning that applies code patches in real repositories and validates them via full test suite execution—rewarding only correct, robust completions. The model achieves 60.4% on SWE-bench Verified, setting a new benchmark among open-source models for software bug fixing and code reasoning.

Claude Opus 4
DeepInfra · Jun 12, 2025
Claude Opus 4 from DeepInfra - text, image input, 200,000 token context

Qwen3-32B
Groq · Jun 11, 2025
Qwen instruction model for multilingual chat, reasoning, and tool use

Seedance v1.0 Pro
Vercel AI Gateway · Jun 11, 2025
Video model for prompt-guided generation, editing, and motion workflows

OpenAI: o3 Pro
OpenRouter · Jun 10, 2025
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

OpenAI: o3 Pro (batch)
OpenRouter · Jun 10, 2025
The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...

xAI: Grok 3 Mini
OpenRouter · Jun 10, 2025
A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.

xAI: Grok 3
OpenRouter · Jun 10, 2025
Grok 3 is the latest model from xAI. It's their flagship model that excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in...

o3-pro
OpenAI · Jun 10, 2025
High-effort o3 tier for difficult technical reasoning and careful answers

o3 Pro
Vercel AI Gateway · Jun 10, 2025
High-effort o3 tier for difficult technical reasoning and careful answers

Google: Gemini 2.5 Pro Preview 06-05
OpenRouter · Jun 5, 2025
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Gemini 2.5 Pro Preview 06-05
Google · Jun 5, 2025
Gemini 2.5 Pro Preview 06-05 from Google - text, image, audio, video, pdf input, 1,048,576 token context
Qwen 3 Embedding 4B
Hugging Face · Jun 5, 2025
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Qwen 3 Embedding 8B
Hugging Face · Jun 5, 2025
Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Qwen3 Embedding 0.6B
Vercel AI Gateway · Jun 5, 2025
Compact multilingual text embedding model for retrieval, code search, classification, and clustering

Qwen3 Embedding 4B
Vercel AI Gateway · Jun 5, 2025
Multilingual text embedding model for retrieval, code search, classification, and clustering

Qwen3 Embedding 8B
Vercel AI Gateway · Jun 5, 2025
Multilingual text embedding model for retrieval, code search, classification, and clustering

Qwen3 Reranker 8B
Novita · Jun 5, 2025
Multilingual query-document reranking model supporting more than 100 languages

Qwen3 Embedding 8B
Novita · Jun 5, 2025
Multilingual text embedding model for retrieval, code search, classification, and clustering

DeepSeek: DeepSeek R1 0528 Qwen3 8B
OpenRouter · May 29, 2025
DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro. It now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought. The distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.

FLUX.1 Kontext Max
Vercel AI Gateway · May 29, 2025
Image model for prompt-driven generation, editing, and visual design workflows

FLUX.1 Kontext Pro
Vercel AI Gateway · May 29, 2025
Image model for prompt-driven generation, editing, and visual design workflows

DeepSeek R1 0528 Qwen3 8B
Novita · May 29, 2025
DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning

DeepSeek: R1 0528 (free)
OpenRouter · May 28, 2025
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) 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. Fully open-source model.

DeepSeek: R1 0528
OpenRouter · May 28, 2025
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) 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...

Deepseek R1 05/28
Fireworks AI · May 28, 2025
Deepseek R1 05/28 from Fireworks AI - text input, 160,000 token context

