Quickstart
Make your first BlazeInfer API call in about two minutes.
Create an account and add credits
Sign up in the BlazeInfer console and finish account setup (phone verification and billing address). Then add credits on the Credits page. API keys only work once your account has a credit balance.
Create an API key
Create a key in the BlazeInfer console under
API keys → Create key. Keys start with blz_ and are shown only once,
so copy the key now and store it somewhere safe.
You can give the key an optional expiry.
Set the key as an environment variable so your code never hard-codes the secret:
export BLAZE_API_KEY="blz_..."
test -n "$BLAZE_API_KEY" && echo "BLAZE_API_KEY is set"Make your first request
curl https://blaze.e2enetworks.net/v1/chat/completions \
-H "Authorization: Bearer $BLAZE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-4-31b-it",
"messages": [{"role": "user", "content": "Say hello in one sentence."}]
}'The Python and TypeScript examples print a short greeting, such as Hello!.
The curl example prints the full response, a standard OpenAI chat completion
object. Its usage block reports prompt_tokens, completion_tokens and
total_tokens. The response also carries an X-Request-Id header. Quote it
when you contact support.
Common errors
| Status | What it usually means | What to do |
|---|---|---|
401 | The key is missing, mistyped, expired or revoked | Check the Authorization: Bearer header and the key in the console |
404 | The model ID is unknown or not available | Check the ID against console |
429 | No credit left, or a temporary overload | Add credits. If you do have credit, retry with backoff |
503 | The model is temporarily unavailable | Retry, or use another model |
Errors come back as JSON. A 429 from a credit rule can also be plain text.
See Errors & retries for the full picture.