GLM 5.2 Fast from fireworks-aiUse GLM 5.2 Fast from fireworks-ai with API Key
GLM 5.2 Fast from Fireworks AI - text input, 1,048,575 token context
Guide
Learn more about how to use AI models with TypingMind
GLM 5.2 Fast from fireworks-ai
Sakana: Fugu Ultra via OpenRouterAccess Sakana: Fugu Ultra via OpenRouter
Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...
Google: Nano Banana 2 (Gemini 3.1 Flash Image) via OpenRouterAccess Google: Nano Banana 2 (Gemini 3.1 Flash Image) via OpenRouter
Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...
Google: Nano Banana Pro (Gemini 3 Pro Image) via OpenRouterAccess Google: Nano Banana Pro (Gemini 3 Pro Image) via OpenRouter
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
Cohere: North Mini Code (free) via OpenRouterAccess Cohere: North Mini Code (free) via OpenRouter
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
Z.ai: GLM 5.2 via OpenRouterAccess Z.ai: GLM 5.2 via OpenRouter
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
GLM 5.2 from fireworks-aiUse GLM 5.2 from fireworks-ai with API Key
GLM 5.2 from Fireworks AI - text input, 1,048,575 token context
AGI-01 Swift from lucidqueryUse AGI-01 Swift from lucidquery with API Key
AGI-01 Swift from LucidQuery - text, image input, 300,000 token context
AGI-01 Frontier from lucidqueryUse AGI-01 Frontier from lucidquery with API Key
AGI-01 Frontier from LucidQuery - text, image input, 300,000 token context
GLM 5.2 from veniceUse GLM 5.2 from venice with API Key
GLM 5.2 from Venice AI - text input, 1,000,000 token context
OpenRouter: Fusion via OpenRouterAccess OpenRouter: Fusion via OpenRouter
Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...
Kimi K2.7 Code from veniceUse Kimi K2.7 Code from venice with API Key
Kimi K2.7 Code from Venice AI - text, image input, 256,000 token context
GLM 5.2 TEE from chutesUse GLM 5.2 TEE from chutes with API Key
GLM 5.2 TEE from Chutes - text input, 1,048,576 token context
GLM-5.2 from deepinfraUse GLM-5.2 from deepinfra with API Key
GLM-5.2 from Deep Infra - text input, 1,048,576 token context
GLM-5.2 from huggingfaceUse GLM-5.2 from huggingface with API Key
GLM-5.2 from Hugging Face - text input, 262,144 token context
MoonshotAI: Kimi K2.7 Code via OpenRouterAccess MoonshotAI: Kimi K2.7 Code via OpenRouter
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Kimi K2.7 Code Fast from fireworks-aiUse Kimi K2.7 Code Fast from fireworks-ai with API Key
Kimi K2.7 Code Fast from Fireworks AI - text, image input, 262,000 token context
MiniMax-M3 from fireworks-aiUse MiniMax-M3 from fireworks-ai with API Key
MiniMax-M3 from Fireworks AI - text input, 512,000 token context
Qwen 3.7 Plus from fireworks-aiUse Qwen 3.7 Plus from fireworks-ai with API Key
Qwen 3.7 Plus from Fireworks AI - text, image input, 262,144 token context
Kimi K2.7 Code from fireworks-aiUse Kimi K2.7 Code from fireworks-ai with API Key
Kimi K2.7 Code from Fireworks AI - text, image input, 262,000 token context
Kimi K2.7 Code from moonshotaiUse Kimi K2.7 Code from moonshotai with API Key
Kimi K2.7 Code from Moonshot AI - text, image, video input, 262,144 token context
Kimi K2.7 Code HighSpeed from moonshotaiUse Kimi K2.7 Code HighSpeed from moonshotai with API Key
Kimi K2.7 Code HighSpeed from Moonshot AI - text, image, video input, 262,144 token context
MiniMax M3 Preview from veniceUse MiniMax M3 Preview from venice with API Key
MiniMax M3 Preview from Venice AI - text input, 524,288 token context
MiniMax-M3 from syntheticUse MiniMax-M3 from synthetic with API Key
MiniMax-M3 from Synthetic - text, image input, 524,288 token context
Kimi K2.7 Code from huggingfaceUse Kimi K2.7 Code from huggingface with API Key
Kimi K2.7 Code from Hugging Face - text, image input, 262,144 token context
MiMo-V2.5 from veniceUse MiMo-V2.5 from venice with API Key
MiMo-V2.5 from Venice AI - text, image, audio, video input, 1,000,000 token context
Claude Fable 5 from veniceUse Claude Fable 5 from venice with API Key
Claude Fable 5 from Venice AI - text, image input, 1,000,000 token context
Anthropic: Claude Fable Latest via OpenRouterAccess Anthropic: Claude Fable Latest via OpenRouter
This model always redirects to the latest model in the Claude Fable family.
Anthropic: Claude Fable 5 via OpenRouterAccess Anthropic: Claude Fable 5 via OpenRouter
Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...
Claude Fable 5 from anthropicUse Claude Fable 5 from anthropic with API Key
Claude Fable 5 from Anthropic - text, image, pdf input, 1,000,000 token context
Claude Fable 5 (Global) from AWS BedrockUse Claude Fable 5 (Global) from AWS Bedrock with API Key
Claude Fable 5 (Global) from Amazon Bedrock - text, image input, 1,000,000 token context
Claude Fable 5 (US) from AWS BedrockUse Claude Fable 5 (US) from AWS Bedrock with API Key
Claude Fable 5 (US) from Amazon Bedrock - text, image input, 1,000,000 token context
Claude Fable 5 (EU) from AWS BedrockUse Claude Fable 5 (EU) from AWS Bedrock with API Key
Claude Fable 5 (EU) from Amazon Bedrock - text, image input, 1,000,000 token context
Nex AGI: Nex-N2-Pro via OpenRouterAccess Nex AGI: Nex-N2-Pro via OpenRouter
Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...
NVIDIA: Nemotron 3.5 Content Safety (free) via OpenRouterAccess NVIDIA: Nemotron 3.5 Content Safety (free) via OpenRouter
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
NVIDIA: Nemotron 3 Ultra (free) via OpenRouterAccess NVIDIA: Nemotron 3 Ultra (free) via OpenRouter
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
NVIDIA: Nemotron 3 Ultra via OpenRouterAccess NVIDIA: Nemotron 3 Ultra via OpenRouter
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
NVIDIA Nemotron 3 Ultra from veniceUse NVIDIA Nemotron 3 Ultra from venice with API Key
NVIDIA Nemotron 3 Ultra from Venice AI - text input, 256,000 token context
Qwen: Qwen3.7 Plus via OpenRouterAccess Qwen: Qwen3.7 Plus via OpenRouter
Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...
Qwen 3.7 Plus from veniceUse Qwen 3.7 Plus from venice with API Key
Qwen 3.7 Plus from Venice AI - text, image, video input, 1,000,000 token context
MiniMax M3 from veniceUse MiniMax M3 from venice with API Key
MiniMax M3 from Venice AI - text, image, video input, 500,000 token context
MiniMax-M3 from huggingfaceUse MiniMax-M3 from huggingface with API Key
MiniMax-M3 from Hugging Face - text, image input, 524,288 token context
MiniMax: MiniMax M3 via OpenRouterAccess MiniMax: MiniMax M3 via OpenRouter
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Step 3.7 Flash from huggingfaceUse Step 3.7 Flash from huggingface with API Key
Step 3.7 Flash from Hugging Face - text, image input, 262,144 token context
StepFun: Step 3.7 Flash via OpenRouterAccess StepFun: Step 3.7 Flash via OpenRouter
Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...
Claude Opus 4.8 from anthropicUse Claude Opus 4.8 from anthropic with API Key
Claude Opus 4.8 from Anthropic - text, image, pdf input, 1,000,000 token context
Claude Opus 4.8 Fast from veniceUse Claude Opus 4.8 Fast from venice with API Key
Claude Opus 4.8 Fast from Venice AI - text, image input, 1,000,000 token context
Claude Opus 4.8 from veniceUse Claude Opus 4.8 from venice with API Key
Claude Opus 4.8 from Venice AI - text, image input, 1,000,000 token context
Claude Opus 4.8 (JP) from AWS BedrockUse Claude Opus 4.8 (JP) from AWS Bedrock with API Key
Claude Opus 4.8 (JP) from Amazon Bedrock - text, image, pdf input, 1,000,000 token context
Claude Opus 4.8 (AU) from AWS BedrockUse Claude Opus 4.8 (AU) from AWS Bedrock with API Key
Claude Opus 4.8 (AU) from Amazon Bedrock - text, image, pdf input, 1,000,000 token context
Claude Opus 4.8 (Global) from AWS BedrockUse Claude Opus 4.8 (Global) from AWS Bedrock with API Key
Claude Opus 4.8 (Global) from Amazon Bedrock - text, image, pdf input, 1,000,000 token context
