Skip to main content
Kluster offers 11 models through Lava’s AI Gateway, supporting Chat Completions, Embeddings. Authentication uses Authorization: Bearer. See the Kluster API docs for provider-specific parameters.
Supports both managed (Lava’s API keys) and unmanaged (bring your own credentials) mode.

​
Quick Start

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

​
Chat Completions

Target URL: https://api.kluster.ai/v1/chat/completions
Content Typeapplication/json
StreamingYes (set stream: true in request body)
ModelInput / 1M tokensOutput / 1M tokens
deepseek-ai/DeepSeek-R1$3.00$5.00
deepseek-ai/DeepSeek-R1-0528$3.00$5.00
meta-llama/Llama-4-Scout-17B-16E-Instruct$0.80$0.45
deepseek-ai/DeepSeek-V3-0324$0.70$1.40
klusterai/Meta-Llama-3.3-70B-Instruct-Turbo$0.70$0.70
google/gemma-3-27b-it$0.35$0.35
Qwen/Qwen2.5-VL-7B-Instruct$0.30$0.30
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.20$0.80
klusterai/Meta-Llama-3.1-8B-Instruct-Turbo$0.18$0.18
Qwen/Qwen3-235B-A22B-FP8$0.15$2.00

​
Embeddings

Target URL: https://api.kluster.ai/v1/embeddings
Content Typeapplication/json
StreamingNo
ModelInput / 1M tokensOutput / 1M tokens
kluster-embeddings$0.02Free

​
Next Steps

All Providers

Browse all supported AI providers

Forward Proxy

Learn how to construct proxy URLs and authenticate requests