Skip to main content
GMI Cloud offers 11 models through Lava’s AI Gateway, supporting Chat Completions. Authentication uses Authorization: Bearer. See the GMI Cloud API docs for provider-specific parameters.
Supports both managed API keys (from Lava) and BYOK mode.

Quick Start

const response = await fetch('https://api.lavapayments.com/v1/forward?u=https%3A%2F%2Fapi.gmi-serving.com%2Fv1%2Fchat%2Fcompletions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${forwardToken}`,
  },
  body: JSON.stringify({
    model: 'deepseek-ai/DeepSeek-R1-0528',
    messages: [{ role: "user", content: "Hello!" }],
  }),
});

Chat Completions

Target URL: https://api.gmi-serving.com/v1/chat/completions
Content Typeapplication/json
StreamingYes (set stream: true in request body)
ModelInput / 1M tokensOutput / 1M tokens
deepseek-ai/DeepSeek-R1-0528$0.80$2.30
deepseek-ai/DeepSeek-V3-0324$0.74$0.90
deepseek-ai/DeepSeek-Prover-V2-671B$0.50$2.18
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B$0.50$0.90
Qwen/QwQ-32B$0.50$1.50
deepseek-ai/DeepSeek-R1-Distill-Llama-70B$0.25$0.75
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.25$0.80
deepseek-ai/DeepSeek-R1-Distill-Qwen-14B$0.20$0.20
Qwen/Qwen3-235B-A22B-FP8$0.17$1.09
Qwen/Qwen3-32B-FP8$0.10$0.60
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B$0.10$0.20

Next Steps