Guide

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

Efficient GLM model for fast reasoning, coding, and agent workflows

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

Hybrid-reasoning GLM release that made the 4.5 line broadly useful

Lighter GLM-4.5 variant for fast coding assistance and cheaper agents

Efficient Qwen model for fast chat, extraction, and high-volume workloads

Qwen coding model for software agents, repository edits, and code reasoning

Flagship GLM model for hybrid reasoning, coding, and agentic engineering

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...

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...

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...

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...

Qwen3 235B A22B Thinking 2507 from Synthetic - text input, 256,000 token context

Nemotron model for efficient reasoning, coding, and specialized AI agents

Qwen reasoning model for deliberate problem solving, math, and coding

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

Qwen reasoning model for deliberate problem solving, math, and coding

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...

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...

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...

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.

Qwen 3 Coder 480B from Synthetic - text input, 256,000 token context

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Qwen coding model for software agents, repository edits, and code reasoning

Qwen3 Coder 480B A35B Instruct from DeepInfra - text input, 262,144 token context

Qwen coding model for software agents, repository edits, and code reasoning

Legacy model retained for compatibility with older integrations

Hosted Qwen coder for software agents, repo edits, and long-context code

Hosted Qwen coder for software agents, repo edits, and long-context code

Qwen coding model for software agents, repository edits, and code reasoning

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...

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...

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...

Qwen3 Coder 480B A35B Instruct from Fireworks AI - text input, 256,000 token context

Qwen coding model for software agents, repository edits, and code reasoning

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

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,...

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use

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

Instruct model with native audio input for speech understanding and tool use

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

Open audio-language model for speech transcription, audio understanding, and voice-driven tool use

Kimi K2 Instruct from Groq - text input, 131,072 token context

Kimi model for long-context chat, coding, and agentic reasoning

Kimi model for long-context chat, coding, and agentic reasoning

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...

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.

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...

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.

Kimi K2 Instruct from Fireworks AI - text input, 128,000 token context