Skip to main content

Your first API call

Let's call a language model to confirm everything is set up.

Prerequisites​

  • You have an EcoLink account (sign up here)
  • You have an API key (create one here)
  • You have at least $0.01 of credit (new accounts get $1.00 free)

Call a chat model​

curl https://api.ecohash.com/v1/chat/completions \
  -H "Authorization: Bearer eco_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.1-8B-Instruct",
    "messages": [
      {"role": "user", "content": "In one sentence: what is EcoLink?"}
    ]
  }'

Response (truncated):

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1776391234,
  "model": "meta-llama/Llama-3.1-8B-Instruct",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "EcoLink is a GPU cloud platform providing on-demand GPU instances and pre-deployed inference models."
    },
    "finish_reason": "stop"
  }],
  "usage": { "prompt_tokens": 18, "completion_tokens": 24, "total_tokens": 42 }
}

That's it — you just ran inference on a Llama 3.1 8B model deployed in one of our regions.

With streaming​

Add "stream": true to get tokens as they're generated (server-sent events):

curl https://api.ecohash.com/v1/chat/completions \
  -H "Authorization: Bearer eco_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "meta-llama/Llama-3.1-8B-Instruct",
    "messages": [{"role": "user", "content": "Count to 10 slowly"}],
    "stream": true
  }'

Each line is a data: prefixed JSON chunk; the last one is data: [DONE]. See Chat completions for the full response schema.

With the OpenAI Python SDK​

from openai import OpenAI
client = OpenAI(
    api_key="eco_YOUR_KEY_HERE",
    base_url="https://api.ecohash.com/v1",
)

resp = client.chat.completions.create(
    model="meta-llama/Llama-3.1-8B-Instruct",
    messages=[{"role": "user", "content": "In one sentence: what is EcoLink?"}],
)
print(resp.choices[0].message.content)

Try image generation​

curl https://api.ecohash.com/v1/images/generations \
  -H "Authorization: Bearer eco_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-1-schnell",
    "prompt": "a photorealistic golden retriever wearing a top hat",
    "size": "1024x1024"
  }'

The response contains a base64-encoded PNG in data[0].b64_json or a hosted URL in data[0].url (depending on response_format).

Try speech-to-text​

curl https://api.ecohash.com/v1/audio/transcriptions \
  -H "Authorization: Bearer eco_YOUR_KEY_HERE" \
  -F model=large-v3 \
  -F file=@recording.mp3

Response:

{ "text": "Hello, this is a test of the EcoLink speech-to-text API." }

What to do next​