Model Catalog
The Model Catalog.
One Unified API.
All 9 models currently available through AnRouter, spanning reasoning, code generation, multimodal input, agents, and long-context work. Each card shows the live capability, context, and input / cache / output prices.
DeepSeek
deepseek-v4.1-flash-1017
DeepSeek V4.1 Flash is a 552B-parameter mixture-of-experts model with a one-million-token context window, multimodal input, reasoning, coding, and tool use. Maximum output is 131,072 tokens.
Z.AI
glm-5.2
GLM 5.2 is a long-horizon reasoning and coding model with a one-million-token context window, multimodal input, flexible reasoning effort, and parallel tool use. Maximum output is 131,072 tokens.
Z.AI
glm-5.3
GLM 5.3 is a post-trained GLM model for complex coding and long-horizon agentic work, with a one-million-token context window, multimodal input, and tool use. Maximum output is 131,072 tokens.
Z.AI
glm-5.3-flash
GLM 5.3 Flash is a natively multimodal 320B-parameter MoE model with approximately 18B active parameters per token and a one-million-token context window, optimized for coding and agent workflows. Maximum output is 131,072 tokens.
MiniMax
minimax-m3.1-flash
MiniMax M3.1 Flash is an open-weight model with always-on reasoning, image input, structured output, and tool use (tool choice is automatic). In our tests the context window holds about 860,000 tokens. Maximum output is 131,072 tokens.
Qwen
qwen3.8-27b
Qwen 3.8 27B is a multimodal reasoning and tool-use model with a 262,144-token context window, designed for coding, agent workflows, and general-purpose language tasks. Maximum output is 32,768 tokens.
Qwen
qwen3.8-flash-next
Qwen 3.8 Flash Next is a fast multimodal reasoning and tool-use model with a 262,144-token context window, optimized for interactive coding and high-throughput agent workloads. Maximum output is 131,072 tokens.
Xiaomi MiMo
mimo-v2.6-pro
MiMo V2.6 Pro is a multimodal reasoning and tool-use model with a 1,048,576-token context window, designed for coding, agent workflows, structured output, and long-context tasks. Maximum output is 131,072 tokens.
Xiaomi MiMo
mimo-v2.6-flash
MiMo V2.6 Flash is a multimodal reasoning and tool-use model with a 1,048,576-token context window, optimized for fast coding, agent workflows, structured output, and long-context tasks. Maximum output is 131,072 tokens.
Integrations
Ready to integrate?
One API key. Every model. Drop-in OpenAI-compatible.