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 562-612 of 787 guides
OpenRouter logo

Switchpoint Router

OpenRouter · Jul 11, 2025

Switchpoint AI's router instantly analyzes your request and directs it to the optimal AI from an ever-evolving library. As the world of LLMs advances, our router gets smarter, ensuring you...

131.1K context
View
OpenRouter logo

MoonshotAI: Kimi K2 0711 (free)

OpenRouter · Jul 11, 2025

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.

32.8K context
View
OpenRouter logo

MoonshotAI: Kimi K2 0711

OpenRouter · Jul 11, 2025

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

131.1K context
View
OpenRouter logo

THUDM: GLM 4.1V 9B Thinking

OpenRouter · Jul 11, 2025

GLM-4.1V-9B-Thinking is a 9B parameter vision-language model developed by THUDM, based on the GLM-4-9B foundation. It introduces a reasoning-centric "thinking paradigm" enhanced with reinforcement learning to improve multimodal reasoning, long-context understanding (up to 64K tokens), and complex problem solving. It achieves state-of-the-art performance among models in its class, outperforming even larger models like Qwen-2.5-VL-72B on a majority of benchmark tasks.

65.5K context
View
OpenRouter logo

Mistral: Devstral Medium

OpenRouter · Jul 10, 2025

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves...

131.1K context
View
OpenRouter logo

Mistral: Devstral Small 1.1

OpenRouter · Jul 10, 2025

Devstral Small 1.1 is a 24B parameter open-weight language model for software engineering agents, developed by Mistral AI in collaboration with All Hands AI. Finetuned from Mistral Small 3.1 and...

131.1K context
View
OpenRouter logo

Venice: Uncensored (free)

OpenRouter · Jul 9, 2025

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

32.8K context
View
OpenRouter logo

Venice: Uncensored

OpenRouter · Jul 9, 2025

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...

128K context
View
OpenRouter logo

xAI: Grok 4

OpenRouter · Jul 9, 2025

Grok 4 is xAI's latest reasoning model with a 256k context window. It supports parallel tool calling, structured outputs, and both image and text inputs. Note that reasoning is not...

256K context+1
View
OpenRouter logo

Google: Gemma 3n 2B (free)

OpenRouter · Jul 9, 2025

Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, designed to operate efficiently at an effective parameter size of 2B while leveraging a 6B architecture. Based...

8.2K context
View
OpenRouter logo

Tencent: Hunyuan A13B Instruct

OpenRouter · Jul 8, 2025

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

131.1K context
View
OpenRouter logo

TNG: DeepSeek R1T2 Chimera (free)

OpenRouter · Jul 8, 2025

DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0324 checkpoints with an Assembly-of-Experts merge. The tri-parent design yields strong reasoning performance while running roughly 20 % faster than the original R1 and more than 2× faster than R1-0528 under vLLM, giving a favorable cost-to-intelligence trade-off. The checkpoint supports contexts up to 60 k tokens in standard use (tested to ~130 k) and maintains consistent <think> token behaviour, making it suitable for long-context analysis, dialogue and other open-ended generation tasks.

163.8K context
View
OpenRouter logo

TNG: DeepSeek R1T2 Chimera

OpenRouter · Jul 8, 2025

DeepSeek-TNG-R1T2-Chimera is the second-generation Chimera model from TNG Tech. It is a 671 B-parameter mixture-of-experts text-generation model assembled from DeepSeek-AI’s R1-0528, R1, and V3-0324 checkpoints with an Assembly-of-Experts merge. The...

163.8K context
View
OpenRouter logo

Morph: Morph V3 Large

OpenRouter · Jul 7, 2025

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

262.1K context
View
OpenRouter logo

Morph: Morph V3 Large (batch)

OpenRouter · Jul 7, 2025

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

262.1K context
View
OpenRouter logo

Morph: Morph V3 Fast

OpenRouter · Jul 7, 2025

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

262.1K context
View
OpenRouter logo

Morph: Morph V3 Fast (batch)

OpenRouter · Jul 7, 2025

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...

81.9K context
View
OpenRouter logo

Baidu: ERNIE 4.5 VL 424B A47B

OpenRouter · Jun 30, 2025

ERNIE-4.5-VL-424B-A47B is a multimodal Mixture-of-Experts (MoE) model from Baidu’s ERNIE 4.5 series, featuring 424B total parameters with 47B active per token. It is trained jointly on text and image data...

123K context
View
OpenRouter logo

Baidu: ERNIE 4.5 300B A47B

OpenRouter · Jun 30, 2025

ERNIE-4.5-300B-A47B is a 300B parameter Mixture-of-Experts (MoE) language model developed by Baidu as part of the ERNIE 4.5 series. It activates 47B parameters per token and supports text generation in...

131.1K context
View
OpenRouter logo

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...

128K context
View
OpenRouter logo

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...

256K context
View
OpenRouter logo

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...

1M context
View
OpenRouter logo

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...

1M context+3
View
OpenRouter logo

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...

1M context+3
View
OpenRouter logo

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...

1M context+3
View
OpenRouter logo

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...

1M context+3
View
OpenRouter logo

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.

131.1K context
View
OpenRouter logo

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...

200K context
View
OpenRouter logo

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...

200K context
View
OpenRouter logo

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.

131.1K context
View
OpenRouter logo

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...

131.1K context
View
OpenRouter logo

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...

1M context+2
View
OpenRouter logo

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.

128K context
View
OpenRouter logo

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.

163.8K context
View
OpenRouter logo

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...

163.8K context
View
OpenRouter logo

Anthropic: Claude Opus 4

OpenRouter · May 22, 2025

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

200K context
View
OpenRouter logo

Anthropic: Claude Sonnet 4

OpenRouter · May 22, 2025

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...

200K context
View
OpenRouter logo

Mistral: Devstral Small 2505

OpenRouter · May 21, 2025

Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%). Devstral supports a 128k context window and uses a custom Tekken tokenizer. It is text-only, with the vision encoder removed, and is suitable for local deployment on high-end consumer hardware (e.g., RTX 4090, 32GB RAM Macs). Devstral is best used in agentic workflows via the OpenHands scaffold and is compatible with inference frameworks like vLLM, Transformers, and Ollama. It is released under the Apache 2.0 license.

128K context
View
OpenRouter logo

Google: Gemma 3n 4B (free)

OpenRouter · May 20, 2025

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

8.2K context
View
OpenRouter logo

Google: Gemma 3n 4B

OpenRouter · May 20, 2025

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

32.8K context
View
OpenRouter logo

OpenAI: Codex Mini

OpenRouter · May 16, 2025

codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.

200K context
View
OpenRouter logo

Nous: DeepHermes 3 Mistral 24B Preview

OpenRouter · May 9, 2025

DeepHermes 3 (Mistral 24B Preview) is an instruction-tuned language model by Nous Research based on Mistral-Small-24B, designed for chat, function calling, and advanced multi-turn reasoning. It introduces a dual-mode system that toggles between intuitive chat responses and structured “deep reasoning” mode using special system prompts. Fine-tuned via distillation from R1, it supports structured output (JSON mode) and function call syntax for agent-based applications. DeepHermes 3 supports a **reasoning toggle via system prompt**, allowing users to switch between fast, intuitive responses and deliberate, multi-step reasoning. When activated with the following specific system instruction, the model enters a *"deep thinking"* mode—generating extended chains of thought wrapped in `<think></think>` tags before delivering a final answer. System Prompt: You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

32.8K context
View
OpenRouter logo

Mistral: Mistral Medium 3

OpenRouter · May 7, 2025

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

131.1K context
View
OpenRouter logo

Google: Gemini 2.5 Pro Preview 05-06

OpenRouter · May 7, 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...

1M context+3
View
OpenRouter logo

Arcee AI: Spotlight

OpenRouter · May 5, 2025

Spotlight is a 7‑billion‑parameter vision‑language model derived from Qwen 2.5‑VL and fine‑tuned by Arcee AI for tight image‑text grounding tasks. It offers a 32 k‑token context window, enabling rich multimodal...

131.1K context
View
OpenRouter logo

Arcee AI: Maestro Reasoning

OpenRouter · May 5, 2025

Maestro Reasoning is Arcee's flagship analysis model: a 32 B‑parameter derivative of Qwen 2.5‑32 B tuned with DPO and chain‑of‑thought RL for step‑by‑step logic. Compared to the earlier 7 B...

131.1K context
View
OpenRouter logo

Arcee AI: Virtuoso Large

OpenRouter · May 5, 2025

Virtuoso‑Large is Arcee's top‑tier general‑purpose LLM at 72 B parameters, tuned to tackle cross‑domain reasoning, creative writing and enterprise QA. Unlike many 70 B peers, it retains the 128 k...

131.1K context
View
OpenRouter logo

Arcee AI: Coder Large

OpenRouter · May 5, 2025

Coder‑Large is a 32 B‑parameter offspring of Qwen 2.5‑Instruct that has been further trained on permissively‑licensed GitHub, CodeSearchNet and synthetic bug‑fix corpora. It supports a 32k context window, enabling multi‑file...

32.8K context
View
OpenRouter logo

Microsoft: Phi 4 Reasoning Plus

OpenRouter · May 1, 2025

Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer. While it offers improved benchmark scores over Phi-4-reasoning across tasks like AIME, OmniMath, and HumanEvalPlus, its responses are typically ~50% longer, resulting in higher latency. Designed for English-only applications, it is well-suited for structured reasoning workflows where output quality takes priority over response speed.

32.8K context
View
OpenRouter logo

Inception: Mercury Coder

OpenRouter · Apr 30, 2025

Mercury Coder 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 Claude 3.5 Haiku...

128K context
View
OpenRouter logo

Qwen: Qwen3 4B (free)

OpenRouter · Apr 30, 2025

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to support both general-purpose and reasoning-intensive tasks. It introduces a dual-mode architecture—thinking and non-thinking—allowing dynamic switching between high-precision logical reasoning and efficient dialogue generation. This makes it well-suited for multi-turn chat, instruction following, and complex agent workflows.

41K context
View