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 511-561 of 787 guides
OpenRouter logo

MoonshotAI: Kimi K2 0905

OpenRouter · Sep 4, 2025

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

262.1K context
View
OpenRouter logo

MoonshotAI: Kimi K2 0905 (exacto)

OpenRouter · Sep 4, 2025

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It 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 supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.

262.1K context
View
OpenRouter logo

Deep Cogito: Cogito V2 Preview Llama 70B

OpenRouter · Sep 2, 2025

Cogito v2 70B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. Built with iterative policy improvement, it delivers strong performance across reasoning tasks while maintaining efficiency through shorter reasoning chains and improved intuition.

32.8K context
View
OpenRouter logo

Cogito V2 Preview Llama 109B

OpenRouter · Sep 2, 2025

An instruction-tuned, hybrid-reasoning Mixture-of-Experts model built on Llama-4-Scout-17B-16E. Cogito v2 can answer directly or engage an extended “thinking” phase, with alignment guided by Iterated Distillation & Amplification (IDA). It targets coding, STEM, instruction following, and general helpfulness, with stronger multilingual, tool-calling, and reasoning performance than size-equivalent baselines. The model supports long-context use (up to 10M tokens) and standard Transformers workflows. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

32.8K context
View
OpenRouter logo

StepFun: Step3

OpenRouter · Aug 28, 2025

Step3 is a cutting-edge multimodal reasoning model—built on a Mixture-of-Experts architecture with 321B total parameters and 38B active. It is designed end-to-end to minimize decoding costs while delivering top-tier performance in vision–language reasoning. Through the co-design of Multi-Matrix Factorization Attention (MFA) and Attention-FFN Disaggregation (AFD), Step3 maintains exceptional efficiency across both flagship and low-end accelerators.

65.5K context
View
OpenRouter logo

Qwen: Qwen3 30B A3B Thinking 2507

OpenRouter · Aug 28, 2025

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

81.9K context
View
OpenRouter logo

xAI: Grok Code Fast 1

OpenRouter · Aug 26, 2025

Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality...

256K context
View
OpenRouter logo

Nous: Hermes 4 70B

OpenRouter · Aug 26, 2025

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...

131.1K context
View
OpenRouter logo

Nous: Hermes 4 405B

OpenRouter · Aug 26, 2025

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...

131.1K context
View
OpenRouter logo

Google: Gemini 2.5 Flash Image Preview (Nano Banana)

OpenRouter · Aug 26, 2025

Gemini 2.5 Flash Image Preview, a.k.a. "Nano Banana," is a state of the art image generation model with contextual understanding. It is capable of image generation, edits, and multi-turn conversations.

32.8K context
View
OpenRouter logo

DeepSeek: DeepSeek V3.1

OpenRouter · Aug 21, 2025

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

163.8K context
View
OpenRouter logo

OpenAI: GPT-4o Audio

OpenRouter · Aug 15, 2025

The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs...

128K context
View
OpenRouter logo

Mistral: Mistral Medium 3.1

OpenRouter · Aug 13, 2025

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

131.1K context
View
OpenRouter logo

Mistral: Mistral Medium 3.1 (batch)

OpenRouter · Aug 13, 2025

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...

131.1K context
View
OpenRouter logo

Baidu: ERNIE 4.5 21B A3B

OpenRouter · Aug 12, 2025

A sophisticated text-based Mixture-of-Experts (MoE) model featuring 21B total parameters with 3B activated per token, delivering exceptional multimodal understanding and generation through heterogeneous MoE structures and modality-isolated routing. Supporting an...

131.1K context
View
OpenRouter logo

Baidu: ERNIE 4.5 VL 28B A3B

OpenRouter · Aug 12, 2025

A powerful multimodal Mixture-of-Experts chat model featuring 28B total parameters with 3B activated per token, delivering exceptional text and vision understanding through its innovative heterogeneous MoE structure with modality-isolated routing....

131.1K context
View
OpenRouter logo

Z.ai: GLM 4.5V

OpenRouter · Aug 11, 2025

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...

65.5K context
View
OpenRouter logo

AI21: Jamba Mini 1.7

OpenRouter · Aug 8, 2025

Jamba Mini 1.7 is a compact and efficient member of the Jamba open model family, incorporating key improvements in grounding and instruction-following while maintaining the benefits of the SSM-Transformer hybrid architecture and 256K context window. Despite its compact size, it delivers accurate, contextually grounded responses and improved steerability.

256K context
View
OpenRouter logo

AI21: Jamba Large 1.7

OpenRouter · Aug 8, 2025

Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...

256K context
View
OpenRouter logo

OpenAI: GPT-5 Chat

OpenRouter · Aug 7, 2025

GPT-5 Chat is designed for advanced, natural, multimodal, and context-aware conversations for enterprise applications.

128K context
View
OpenRouter logo

OpenAI: GPT-5

OpenRouter · Aug 7, 2025

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

400K context+1
View
OpenRouter logo

OpenAI: GPT-5 (batch)

OpenRouter · Aug 7, 2025

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...

400K context+1
View
OpenRouter logo

OpenAI: GPT-5 Mini

OpenRouter · Aug 7, 2025

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

400K context+1
View
OpenRouter logo

OpenAI: GPT-5 Mini (batch)

OpenRouter · Aug 7, 2025

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

400K context+1
View
OpenRouter logo

OpenAI: GPT-5 Nano

OpenRouter · Aug 7, 2025

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

400K context+1
View
OpenRouter logo

OpenAI: GPT-5 Nano (batch)

OpenRouter · Aug 7, 2025

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

400K context+1
View
OpenRouter logo

OpenAI: gpt-oss-120b (free)

OpenRouter · Aug 5, 2025

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

131.1K context
View
OpenRouter logo

OpenAI: gpt-oss-120b

OpenRouter · Aug 5, 2025

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

131.1K context
View
OpenRouter logo

OpenAI: gpt-oss-120b (exacto)

OpenRouter · Aug 5, 2025

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

131.1K context
View
OpenRouter logo

OpenAI: gpt-oss-120b (batch)

OpenRouter · Aug 5, 2025

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

131.1K context
View
OpenRouter logo

OpenAI: gpt-oss-20b (free)

OpenRouter · Aug 5, 2025

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

131.1K context
View
OpenRouter logo

OpenAI: gpt-oss-20b

OpenRouter · Aug 5, 2025

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

131.1K context
View
OpenRouter logo

OpenAI: gpt-oss-20b (batch)

OpenRouter · Aug 5, 2025

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

131.1K context
View
OpenRouter logo

Anthropic: Claude Opus 4.1

OpenRouter · Aug 5, 2025

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

200K context
View
OpenRouter logo

Anthropic: Claude Opus 4.1 (batch)

OpenRouter · Aug 5, 2025

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

200K context+1
View
OpenRouter logo

Mistral: Codestral 2508

OpenRouter · Aug 1, 2025

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

256K context
View
OpenRouter logo

Mistral: Codestral 2508 (batch)

OpenRouter · Aug 1, 2025

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

256K context
View
OpenRouter logo

Qwen: Qwen3 Coder 30B A3B Instruct

OpenRouter · Jul 31, 2025

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...

262.1K context
View
OpenRouter logo

Qwen: Qwen3 30B A3B Instruct 2507

OpenRouter · Jul 29, 2025

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

262.1K context
View
OpenRouter logo

Z.ai: GLM 4.5

OpenRouter · Jul 25, 2025

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

131.1K context
View
OpenRouter logo

Z.ai: GLM 4.5 Air (free)

OpenRouter · Jul 25, 2025

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

131.1K context
View
OpenRouter logo

Z.ai: GLM 4.5 Air

OpenRouter · Jul 25, 2025

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...

131.1K context
View
OpenRouter logo

Qwen: Qwen3 235B A22B Thinking 2507

OpenRouter · Jul 25, 2025

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

128K context
View
OpenRouter logo

Z.ai: GLM 4 32B

OpenRouter · Jul 24, 2025

GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent tasks. It...

128K context
View
OpenRouter logo

Qwen: Qwen3 Coder 480B A35B (free)

OpenRouter · Jul 23, 2025

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

1M context
View
OpenRouter logo

Qwen: Qwen3 Coder 480B A35B

OpenRouter · Jul 23, 2025

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...

262.1K context
View
OpenRouter logo

Qwen: Qwen3 Coder 480B A35B (exacto)

OpenRouter · Jul 23, 2025

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over repositories. The model features 480 billion total parameters, with 35 billion active per forward pass (8 out of 160 experts). Pricing for the Alibaba endpoints varies by context length. Once a request is greater than 128k input tokens, the higher pricing is used.

262.1K context
View
OpenRouter logo

ByteDance: UI-TARS 7B

OpenRouter · Jul 22, 2025

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...

128K context
View
OpenRouter logo

Google: Gemini 2.5 Flash Lite

OpenRouter · Jul 22, 2025

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

1M context+3
View
OpenRouter logo

Google: Gemini 2.5 Flash Lite (batch)

OpenRouter · Jul 22, 2025

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...

1M context+3
View
OpenRouter logo

Qwen: Qwen3 235B A22B Instruct 2507

OpenRouter · Jul 21, 2025

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

262.1K context
View