Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.gmicloud.ai/llms.txt

Use this file to discover all available pages before exploring further.

Large language models (LLMs) power chat, agents, code generation, retrieval, and vision-language workloads. Each page documents request formats, parameters, and examples for that model.

Technical topics

  • Chat & completions — Messages, system prompts, stop sequences, and sampling (temperature, top_p).
  • OpenAI-compatible APIs — Many models follow the same shapes as common chat completion endpoints.
  • Streaming — Token streaming for responsive UIs and lower perceived latency.
  • Reasoning & tools — Models may support extended thinking, tool calling, or structured outputs where noted on the model page.
  • Vision & OCR — Selected models accept images or documents for understanding or extraction.
  • Efficiency — Quantized (e.g. FP8) and MoE architectures trade size and cost against quality.

Model API & platform docs

For serving modes (serverless vs dedicated), billing, rate limits, task polling, and unified API patterns, see the API Reference section.

Full model list (88)

ModelModel IDOrganization
Anthropic Claude Haiku 4.5anthropic/claude-haiku-4.5anthropic
Anthropic Claude Opus 4.1anthropic/claude-opus-4.1anthropic
Anthropic Claude Opus 4.5anthropic/claude-opus-4.5anthropic
Anthropic Claude Opus 4.6anthropic/claude-opus-4.6anthropic
Anthropic Claude Opus 4.7anthropic/claude-opus-4.7anthropic
Anthropic Claude Sonnet 4anthropic/claude-sonnet-4anthropic
Anthropic Claude Sonnet 4.5anthropic/claude-sonnet-4.5anthropic
Anthropic Claude Sonnet 4.6anthropic/claude-sonnet-4.6anthropic
ByteDance Seed-2.0-Minibytedance/seed-2.0-minibytedance
CLIP-ViT-B-32-laion2B-s34B-b79Klaion/CLIP-ViT-B-32-laion2B-s34B-b79Klaion
DeepSeek Prover V2 671Bdeepseek-ai/DeepSeek-Prover-V2-671Bdeepseek-ai
DeepSeek V3.2deepseek-ai/DeepSeek-V3.2deepseek-ai
deepseek-ai/DeepSeek-V4-Flashdeepseek-ai/DeepSeek-V4-Flashdeepseek-ai
deepseek-ai/DeepSeek-V4-Prodeepseek-ai/DeepSeek-V4-Prodeepseek-ai
DeepSeek-R1-Distill-Llama-70Bdeepseek-ai/DeepSeek-R1-Distill-Llama-70Bdeepseek-ai
DeepSeek-R1-Distill-Qwen-1.5Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Bdeepseek-ai
DeepSeek-R1-Distill-Qwen-14Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-14Bdeepseek-ai
DeepSeek-R1-Distill-Qwen-7Bdeepseek-ai/DeepSeek-R1-Distill-Qwen-7Bdeepseek-ai
DeepSeek-V3-0324deepseek-ai/DeepSeek-V3-0324deepseek-ai
DeepSeek-V3.1deepseek-ai/DeepSeek-V3.1deepseek-ai
DeepSeek-V3.1-Terminusdeepseek-ai/DeepSeek-V3.1-Terminusdeepseek-ai
DeepSeek-V3.2deepseek-ai/DeepSeek-R1-0528deepseek-ai
DeepSeek-V3.2zai-org/GLM-4.7-FP8zai-org
DeepSeek-V3.2-Expdeepseek-ai/DeepSeek-V3.2-Expdeepseek-ai
DeepSeek-V3.2-Specialedeepseek-ai/DeepSeek-V3.2-Specialedeepseek-ai
GLM-4.5-Air-FP8zai-org/GLM-4.5-Air-FP8zai-org
GLM-4.5-FP8zai-org/GLM-4.5-FP8zai-org
GLM-4.6zai-org/GLM-4.6zai-org
GLM-4.7-Flashzai-org/GLM-4.7-Flashzai-org
GLM-5zai-org/GLM-5-FP8zai-org
GLM-5.1zai-org/GLM-5.1-FP8zai-org
Google Gemini 3 Flash Previewgoogle/gemini-3-flash-previewgoogle
Google Gemini 3.1 Flash-Lite Previewgoogle/gemini-3.1-flash-lite-previewgoogle
Google Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-previewgoogle
Google Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-itgoogle
Google Gemma 4 31Bgoogle/gemma-4-31b-itgoogle
HunyuanOCRtencent/HunyuanOCRtencent
KAT-Coder-Pro V2kwaipilot/kat-coder-pro-v2kwaipilot
Kimi-K2.6moonshotai/Kimi-K2.6moonshotai
Llama-3.1-8B-Instructmeta-llama/Llama-3.1-8B-Instructmeta-llama
Llama-3.3-70B-Instructmeta-llama/Llama-3.3-70B-Instructmeta-llama
Llama-4-Maverick-17B-128E-Instructmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8meta-llama
Llama-4-Scout-17B-16E-Instructmeta-llama/Llama-4-Scout-17B-16E-Instructmeta-llama
MiniMax-M2MiniMaxAI/MiniMax-M2MiniMaxAI
MiniMax-M2.1MiniMaxAI/MiniMax-M2.1MiniMaxAI
MiniMax-M2.5MiniMaxAI/MiniMax-M2.5MiniMaxAI
MiniMax-M2.7MiniMaxAI/MiniMax-M2.7MiniMaxAI
Moonshotai Kimi K2 Instruct 0905moonshotai/Kimi-K2-Instruct-0905moonshotai
Moonshotai Kimi K2 Instruct 0905moonshotai/Kimi-K2-Thinkingmoonshotai
Moonshotai Kimi-K2.5moonshotai/Kimi-K2.5moonshotai
Nemotron 3 Nano Omninvidia/NVIDIA-Nemotron-3-Nano-Omninvidia
olmOCR-2-7B-1025-FP8allenai/olmOCR-2-7B-1025-FP8allenai
OpenAI GPT OSS 120Bopenai/gpt-oss-120bopenai
OpenAI GPT OSS 20Bopenai/gpt-oss-20bopenai
OpenAI GPT-4oopenai/gpt-4oopenai
OpenAI GPT-4o-miniopenai/gpt-4o-miniopenai
OpenAI GPT-5openai/gpt-5openai
OpenAI GPT-5.1openai/gpt-5.1openai
OpenAI GPT-5.1-Chatopenai/gpt-5.1-chatopenai
OpenAI GPT-5.2openai/gpt-5.2openai
OpenAI GPT-5.2-Chatopenai/gpt-5.2-chatopenai
OpenAI GPT-5.2-codexopenai/gpt-5.2-codexopenai
OpenAI GPT-5.3-codexopenai/gpt-5.3-codexopenai
OpenAI GPT-5.4openai/gpt-5.4openai
OpenAI GPT-5.4-miniopenai/gpt-5.4-miniopenai
OpenAI GPT-5.4-nanoopenai/gpt-5.4-nanoopenai
OpenAI GPT-5.4-proopenai/gpt-5.4-proopenai
OpenAI gpt-5.5openai/gpt-5.5openai
Qwen3 Next 80B A3B InstructQwen/Qwen3-Next-80B-A3B-InstructQwen
Qwen3 Next 80B A3B ThinkingQwen/Qwen3-Next-80B-A3B-ThinkingQwen
Qwen3-235B-A22B-FP8Qwen/Qwen3-235B-A22B-FP8Qwen
Qwen3-235B-A22B-Instruct-2507-FP8Qwen/Qwen3-235B-A22B-Instruct-2507-FP8Qwen
Qwen3-235B-A22B-Thinking-2507-FP8Qwen/Qwen3-235B-A22B-Thinking-2507-FP8Qwen
Qwen3-32B-FP8Qwen/Qwen3-32B-FP8Qwen
Qwen3-Coder-30B-A3B-Instruct-FP8Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8Qwen
Qwen3-Coder-480B-A35B-Instruct-FP8Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8Qwen
Qwen3-VL-235B-A22B-Instruct-FP8Qwen/Qwen3-VL-235B-A22B-Instruct-FP8Qwen
Qwen3.5 122B A10BQwen/Qwen3.5-122B-A10BQwen
Qwen3.5 27BQwen/Qwen3.5-27BQwen
Qwen3.5 35B A3BQwen/Qwen3.5-35B-A3BQwen
Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17BQwen
Qwen3.6 Max PreviewQwen/Qwen3.6-Max-PreviewQwen
Qwen3.6 PlusQwen/Qwen3.6-Plus-2026-04-02Qwen
Qwen3.6 PlusQwen/Qwen3.6-PlusQwen
QwQ-32BQwen/Qwen3-30B-A3BQwen
Wan2.2-I2V-A14BWan-AI/Wan2.2-I2V-A14BWan-AI
Xiaomi MiMo-V2.5XiaomiMiMo/MiMo-V2.5XiaomiMiMo
Xiaomi MiMo-V2.5-ProXiaomiMiMo/MiMo-V2.5-ProXiaomiMiMo