inference cloud

Gmi

Models, pricing and feature compatibility available through Gmi.

Deployments

17

Models

17

Labs

8

With pricing

17

Models on Gmi

Follow any model to compare this deployment with the same model through other providers.

ModelProvider model IDModeRegionInputOutputContextTools
Claude Opus 4anthropic/claude-opus-4Chatglobal$15.00 / 1M$75.00 / 1M409.6Ksupported
Claude Opus 4.5anthropic/claude-opus-4.5Chatglobal$5.00 / 1M$25.00 / 1M409.6Ksupported
Claude Sonnet 4anthropic/claude-sonnet-4Chatglobal$3.00 / 1M$15.00 / 1M409.6Ksupported
Claude Sonnet 4.5anthropic/claude-sonnet-4.5Chatglobal$3.00 / 1M$15.00 / 1M409.6Ksupported
DeepSeek-Ai Deepseek V3 0324deepseek-ai/DeepSeek-V3-0324Chatglobal$0.28 / 1M$0.88 / 1M163.8Ksupported
DeepSeek-Ai Deepseek V3 2deepseek-ai/DeepSeek-V3.2Chatglobal$0.28 / 1M$0.40 / 1M163.8Ksupported
Gemini 3 Flash Previewgoogle/gemini-3-flash-previewChatglobal$0.50 / 1M$3.00 / 1M1.05Msupported
Gemini 3 Pro Previewgoogle/gemini-3-pro-previewChatglobal$2.00 / 1M$12.00 / 1M1.05Msupported
Minimaxai Minimax M2 1MiniMaxAI/MiniMax-M2.1Chatglobal$0.30 / 1M$1.20 / 1M196.6Kunknown
Moonshotai Kimi K2 Thinkingmoonshotai/Kimi-K2-ThinkingChatglobal$0.80 / 1M$1.20 / 1M262.1Kunknown
GPT-4oopenai/gpt-4oChatglobal$2.50 / 1M$10.00 / 1M131.1Ksupported
GPT-4o miniopenai/gpt-4o-miniChatglobal$0.15 / 1M$0.60 / 1M131.1Ksupported
GPT-5openai/gpt-5Chatglobal$1.25 / 1M$10.00 / 1M409.6Ksupported
GPT-5.1openai/gpt-5.1Chatglobal$1.25 / 1M$10.00 / 1M409.6Ksupported
GPT-5.2openai/gpt-5.2Chatglobal$1.75 / 1M$14.00 / 1M409.6Ksupported
Qwen Qwen3 VL 235B A22B Instruct FP8Qwen/Qwen3-VL-235B-A22B-Instruct-FP8Chatglobal$0.30 / 1M$1.40 / 1M262.1Kunknown
Zai Org Glm 4 7 FP8zai-org/GLM-4.7-FP8Chatglobal$0.40 / 1M$2.00 / 1M202.8Kunknown

Labs available through Gmi