Guide

General GLM flagship for coding, analysis, and tool-heavy engineering workflows

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

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...

MiniMax-M2.5 from Synthetic - text input, 191,488 token context

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Coding-optimized GPT model for repository edits, reviews, and agentic software work

High-end Claude for difficult coding, planning, and slower expert reasoning

Qwen3 Coder Next from Chutes - text input, 262,144 token context

High-end Claude for difficult coding, planning, and slower expert reasoning

High-end Claude for difficult coding, planning, and slower expert reasoning

High-end Claude for difficult coding, planning, and slower expert reasoning

High-end Claude for difficult coding, planning, and slower expert reasoning

High-end Claude for difficult coding, planning, and slower expert reasoning

High-end Claude for difficult coding, planning, and slower expert reasoning

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

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

Coding-optimized GPT model for repository edits, reviews, and agentic software work

Coding-optimized GPT model for repository edits, reviews, and agentic software work

High-end Claude for difficult coding, planning, and slower expert reasoning

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

High-end Claude for difficult coding, planning, and slower expert reasoning

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

Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use

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

Legacy model retained for compatibility with older integrations

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

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

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for models that...

Speech transcription model for accurate audio-to-text and captioning workflows

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....

Budget GLM lane for fast coding help, routing, and everyday automation

StepFun flash lane for quick multimodal reasoning and coding assistance

StepFun flash lane for quick multimodal reasoning and coding assistance

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

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

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

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

Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing,...

Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing,...

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performance while maintaining computational efficiency. Optimized...

Kimi K2.5 from Fireworks AI - text, image, video input, 256,000 token context

Kimi K2.5 Turbo from Fireworks AI - text, image input, 256,000 token context

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

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