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 154-204 of 2,840 guides
Venice AI logo

NVIDIA Nemotron 3.5 Super VL 120B

Venice AI · Oct 15, 2026

Nemotron multimodal model for visual reasoning and agentic AI workflows

262.1K context+1
View
Together AI logo

Muse Spark Open

Together AI · Oct 15, 2026

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

1M context+1
View
Together AI logo

Nemotron 3.5 Super VL 120B A12B

Together AI · Oct 15, 2026

NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use

262.1K context+1
View
Vercel AI Gateway logo

NVIDIA Nemotron 3.5 Super VL

Vercel AI Gateway · Oct 15, 2026

Nemotron multimodal model for visual reasoning and agentic AI workflows

1M context
View
Vercel AI Gateway logo

Muse Spark Open

Vercel AI Gateway · Oct 15, 2026

Open Llama multimodal model for image understanding and text reasoning

1M context
View
Vercel AI Gateway logo

FLUX 3 Image Klein

Vercel AI Gateway · Oct 15, 2026

Image model for prompt-driven generation, editing, and visual design workflows

View
Ollama Cloud logo

Muse Spark Open

Ollama Cloud · Oct 15, 2026

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

1M context
View
Cloudflare AI Gateway logo

Muse Spark Open

Cloudflare AI Gateway · Oct 15, 2026

Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.

1M context+2
View
OpenRouter logo

Pareto Latest

OpenRouter · Oct 13, 2026

This model always redirects to the latest model in the Pareto family.

1M context
View
OpenRouter logo

Pareto 26.9

OpenRouter · Oct 13, 2026

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

262.1K context
View
OpenRouter logo

LiquidAI: LFM2.5-24B-A2B

OpenRouter · Oct 13, 2026

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

128K context
View
OpenRouter logo

Google: Gemini 4 Argon

OpenRouter · Oct 13, 2026

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

1M context+3
View
OpenRouter logo

Google: Gemini 4 Argon (batch)

OpenRouter · Oct 13, 2026

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

1M context+3
View
OpenRouter logo

ScaleDown: Summarize

OpenRouter · Oct 13, 2026

Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...

1M context
View
OpenRouter logo

ScaleDown: Extract

OpenRouter · Oct 13, 2026

Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...

1M context
View
Google logo

Gemini 4 Argon

Google · Oct 13, 2026

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

1M context+3
View
Venice AI logo

Gemini 4 Argon

Venice AI · Oct 13, 2026

Gemini multimodal model for text, image, audio, video, and document tasks

1M context+2
View
Vercel AI Gateway logo

Drama 3

Vercel AI Gateway · Oct 13, 2026

Speech generation model for controllable voice, narration, and audio delivery

View
Vercel AI Gateway logo

Gemini 4 Argon

Vercel AI Gateway · Oct 13, 2026

Gemini multimodal model for text, image, audio, video, and document tasks

1M context+1
View
Vercel AI Gateway logo

MAI-Image-2.6-Flash

Vercel AI Gateway · Oct 13, 2026

Image model for prompt-driven generation, editing, and visual design workflows

View
Vercel AI Gateway logo

MAI-Image-2.6

Vercel AI Gateway · Oct 13, 2026

Image model for prompt-driven generation, editing, and visual design workflows

View
Vercel AI Gateway logo

LFM2.5-24B-A2B

Vercel AI Gateway · Oct 13, 2026

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

128K context
View
OpenCode Go logo

Gemini 4 Argon Contributor

OpenCode Go · Oct 13, 2026

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

1M context+3
View
OpenCode Go logo

Gemini 4 Argon

OpenCode Go · Oct 13, 2026

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

1M context+3
View
Cloudflare AI Gateway logo

Gemini 4 Argon

Cloudflare AI Gateway · Oct 13, 2026

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents

1M context+3
View
OpenRouter logo

Meta: Muse Wonder

OpenRouter · Oct 12, 2026

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

1M context+3
View
Venice AI logo

Muse Wonder

Venice AI · Oct 12, 2026

Multimodal reasoning model for visual analysis, planning, and tool use

1M context+2
View
Vercel AI Gateway logo

Muse Wonder

Vercel AI Gateway · Oct 12, 2026

Open Llama multimodal model for image understanding and text reasoning

1M context+1
View
Meta logo

Muse Wonder

Meta · Oct 12, 2026

Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.

1M context+3
View
OpenCode Go logo

Cat Jam Free

OpenCode Go · Oct 12, 2026

A text-only reasoning model for coding and agentic workflows, with tool calling and structured JSON outputs.

1M context
View
Cloudflare AI Gateway logo

Muse Wonder

Cloudflare AI Gateway · Oct 12, 2026

Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.

1M context+2
View
Vercel AI Gateway logo

HeyGen Video

Vercel AI Gateway · Oct 9, 2026

Video model for prompt-guided generation, editing, and motion workflows

View
OpenRouter logo

StepFun: Step 5 Preview

OpenRouter · Oct 8, 2026

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...

1M context+1
View
Vercel AI Gateway logo

Apex

Vercel AI Gateway · Oct 8, 2026

Multimodal reasoning model for visual analysis, planning, and tool use

262.1K context
View
OpenRouter logo

Anthropic: Claude Haiku 5.5

OpenRouter · Oct 7, 2026

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

1M context+1
View
OpenRouter logo

Anthropic: Claude Haiku 5.5 (batch)

OpenRouter · Oct 7, 2026

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...

1M context+1
View
Anthropic logo

Claude Haiku 5.5

Anthropic · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
Venice AI logo

Claude Haiku 5.5

Venice AI · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context
View
AWS Bedrock logo

Claude Haiku 5.5 (EU)

AWS Bedrock · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
AWS Bedrock logo

Claude Haiku 5.5 (JP)

AWS Bedrock · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
AWS Bedrock logo

Claude Haiku 5.5 (Global)

AWS Bedrock · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
AWS Bedrock logo

Claude Haiku 5.5

AWS Bedrock · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
AWS Bedrock logo

Claude Haiku 5.5 (US)

AWS Bedrock · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
AWS Bedrock logo

Claude Haiku 5.5 (AU)

AWS Bedrock · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
Vercel AI Gateway logo

Glyph Cluster

Vercel AI Gateway · Oct 7, 2026

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

256K context
View
Vercel AI Gateway logo

Claude Haiku 5.5

Vercel AI Gateway · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
OpenCode Go logo

Claude Haiku 5.5

OpenCode Go · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
Cloudflare AI Gateway logo

Claude Haiku 5.5

Cloudflare AI Gateway · Oct 7, 2026

Fast Claude model for responsive assistance, classification, and lightweight agents

1M context+1
View
OpenRouter logo

Google: Nano Banana 2.1

OpenRouter · Oct 6, 2026

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

65.5K context
View
OpenRouter logo

Mistral: Mistral Large 4

OpenRouter · Oct 6, 2026

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

1M context
View
Mistral logo

Mistral Large 4

Mistral · Oct 6, 2026

Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work

1M context+1
View