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 2,296-2,346 of 2,840 guides
AWS Bedrock logo

Nova Premier (US)

AWS Bedrock · Apr 30, 2025

Multimodal model for complex analysis, long-context understanding, tool use, and model distillation

1M context
View
Novita logo

Deepseek Prover V2 671B

Novita · Apr 30, 2025

Flagship DeepSeek model for coding, reasoning, and agentic work

160K context
View
Groq logo

Llama Prompt Guard 2 22M

Groq · Apr 29, 2025

Safety model for policy screening, moderation, and risk-aware routing workflows

512 context
View
Groq logo

Prompt Guard 2 86M

Groq · Apr 29, 2025

Safety model for policy screening, moderation, and risk-aware routing workflows

512 context
View
Fireworks AI logo

Qwen3 235B-A22B

Fireworks AI · Apr 29, 2025

Qwen3 235B-A22B from Fireworks AI - text input, 128,000 token context

128K context
View
Venice AI logo

Venice Small

Venice AI · Apr 29, 2025

Venice Small from Venice AI - text input, 32,000 token context

32K context
View
Venice AI logo

Qwen 3 Coder 480b

Venice AI · Apr 29, 2025

Qwen 3 Coder 480b from Venice AI - text input, 256,000 token context

256K context
View
DeepInfra logo

Llama Guard 4 12B

DeepInfra · Apr 29, 2025

Multimodal Llama 4-based safety classifier for moderating prompts and responses

163.8K context
View
Hugging Face logo

Qwen3 8B

Hugging Face · Apr 29, 2025

Dense 8B Qwen3 model with switchable thinking for chat, reasoning, and tool use

41K context
View
Hugging Face logo

Llama Guard 4 12B

Hugging Face · Apr 29, 2025

Multimodal Llama 4-based safety classifier for moderating prompts and responses

163.8K context
View
Novita logo

Qwen3 235B A22B

Novita · Apr 29, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

41K context
View
Novita logo

Qwen3 30B A3B

Novita · Apr 29, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

41K context
View
Novita logo

Qwen3 32B

Novita · Apr 29, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

41K context
View
Novita logo

Qwen3 8B

Novita · Apr 29, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

128K context
View
Novita logo

Qwen3 4B

Novita · Apr 29, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

128K context
View
OpenRouter logo

Qwen: Qwen3 30B A3B

OpenRouter · Apr 28, 2025

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

41K context
View
OpenRouter logo

Qwen: Qwen3 8B

OpenRouter · Apr 28, 2025

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...

131.1K context
View
OpenRouter logo

Qwen: Qwen3 14B

OpenRouter · Apr 28, 2025

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

41K context
View
OpenRouter logo

Qwen: Qwen3 32B

OpenRouter · Apr 28, 2025

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

131.1K context
View
OpenRouter logo

Qwen: Qwen3 235B A22B

OpenRouter · Apr 28, 2025

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

131.1K context
View
Chutes logo

Qwen3 32B TEE

Chutes · Apr 28, 2025

Dense open Qwen model for self-hosted chat, reasoning, and coding

41K context
View
Synthetic logo

Qwen 3 235B Instruct

Synthetic · Apr 28, 2025

Qwen 3 235B Instruct from Synthetic - text input, 256,000 token context

256K context
View
AWS Bedrock logo

Palmyra X5

AWS Bedrock · Apr 28, 2025

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

1M context
View
AWS Bedrock logo

Qwen3 32B

AWS Bedrock · Apr 28, 2025

Dense open Qwen model for self-hosted chat, reasoning, and coding

32.8K context
View
AWS Bedrock logo

Palmyra X5 (US)

AWS Bedrock · Apr 28, 2025

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

1M context
View
DeepInfra logo

Qwen3 32B

DeepInfra · Apr 28, 2025

Dense open Qwen model for self-hosted chat, reasoning, and coding

41K context
View
DeepInfra logo

Qwen3 30B A3B

DeepInfra · Apr 28, 2025

Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

41K context
View
Hugging Face logo

Qwen3 32B

Hugging Face · Apr 28, 2025

Dense open Qwen model for self-hosted chat, reasoning, and coding

131.1K context
View
Hugging Face logo

Qwen3 235B-A22B

Hugging Face · Apr 28, 2025

Large open Qwen MoE for multilingual reasoning, coding, and tool use

41K context
View
Hugging Face logo

Qwen3 30B A3B

Hugging Face · Apr 28, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

41K context
View
Vercel AI Gateway logo

Qwen 3.32B

Vercel AI Gateway · Apr 28, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

128K context
View
Vercel AI Gateway logo

Qwen3-14B

Vercel AI Gateway · Apr 28, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

41K context
View
Vercel AI Gateway logo

Qwen3-30B-A3B

Vercel AI Gateway · Apr 28, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

41K context
View
OpenRouter logo

TNG: DeepSeek R1T Chimera (free)

OpenRouter · Apr 27, 2025

DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE Transformer architecture and is optimized for general text generation tasks. The model merges pretrained weights from both source models to balance performance across reasoning, efficiency, and instruction-following tasks. It is released under the MIT license and intended for research and commercial use.

163.8K context
View
OpenRouter logo

TNG: DeepSeek R1T Chimera

OpenRouter · Apr 27, 2025

DeepSeek-R1T-Chimera is created by merging DeepSeek-R1 and DeepSeek-V3 (0324), combining the reasoning capabilities of R1 with the token efficiency improvements of V3. It is based on a DeepSeek-MoE Transformer architecture and is optimized for general text generation tasks. The model merges pretrained weights from both source models to balance performance across reasoning, efficiency, and instruction-following tasks. It is released under the MIT license and intended for research and commercial use.

163.8K context
View
OpenAI logo

gpt-image-1

OpenAI · Apr 24, 2025

OpenAI image model for production generation, edits, and brand-safe visual workflows

View
Vercel AI Gateway logo

GPT Image 1

Vercel AI Gateway · Apr 24, 2025

OpenAI image model for production generation, edits, and brand-safe visual workflows

View
Google logo

Gemini 2.5 Flash Preview 04-17

Google · Apr 17, 2025

Gemini 2.5 Flash Preview 04-17 from Google - text, image, audio, video, pdf input, 1,048,576 token context

1M context+2
View
OpenRouter logo

OpenAI: o4 Mini High

OpenRouter · Apr 16, 2025

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...

200K context+1
View
OpenRouter logo

OpenAI: o4 Mini High (batch)

OpenRouter · Apr 16, 2025

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining...

200K context+1
View
OpenRouter logo

OpenAI: o3

OpenRouter · Apr 16, 2025

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

200K context+1
View
OpenRouter logo

OpenAI: o3 (batch)

OpenRouter · Apr 16, 2025

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....

200K context+1
View
OpenRouter logo

OpenAI: o4 Mini

OpenRouter · Apr 16, 2025

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

200K context+1
View
OpenRouter logo

OpenAI: o4 Mini (batch)

OpenRouter · Apr 16, 2025

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

200K context+1
View
OpenAI logo

o4-mini

OpenAI · Apr 16, 2025

Fast o-series model for compact reasoning, coding, and tool use

200K context
View
OpenAI logo

o3

OpenAI · Apr 16, 2025

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

200K context+1
View
Vercel AI Gateway logo

o3 (Fast)

Vercel AI Gateway · Apr 16, 2025

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

200K context+1
View
Vercel AI Gateway logo

o4-mini (Fast)

Vercel AI Gateway · Apr 16, 2025

Fast o-series model for compact reasoning, coding, and tool use

200K context+1
View
Vercel AI Gateway logo

o3

Vercel AI Gateway · Apr 16, 2025

Deliberate o-series reasoner for hard math, coding, and multi-step analysis

200K context+1
View
Vercel AI Gateway logo

o4-mini

Vercel AI Gateway · Apr 16, 2025

Fast o-series model for compact reasoning, coding, and tool use

200K context+1
View
Novita logo

Qwen2.5 7B Instruct

Novita · Apr 16, 2025

Qwen instruction model for multilingual chat, reasoning, and tool use

32K context
View