Meta Llama API

Connect AISIX AI Gateway to the Meta Llama API so applications can use one caller-facing API while AISIX stores the upstream Llama credential, controls model access, and records usage.

The Llama API provides an OpenAI-compatible endpoint. AISIX discovers it through the community provider catalog and uses the openai adapter with bearer authentication.

Setting	Value used by AISIX
Catalog provider ID	llama
API base	https://api.llama.com/compat/v1/
Example upstream model	Llama-3.3-70B-Instruct
Authentication	Bearer API key

Prerequisites

Before configuring the provider, prepare:

• Access to AISIX Cloud with an environment, an attached gateway, and a write-scoped admin token. For On-Premises, follow the AISIX Cloud Quickstart. To request Hybrid Cloud access, contact API7.
• A Meta Llama API key and access to the model you plan to use.
• curl and jq.

Export the AISIX connection details:

export AISIX_CP="http://localhost:8080/api"
export AISIX_TOKEN="aisix_pat_YOUR_ADMIN_TOKEN"
export ENV_ID="YOUR_ENVIRONMENT_ID"
export AISIX_PROXY="http://127.0.0.1:3000"

Configure the Meta Llama API Upstream

Create a provider key, a model alias, and a caller API key.

Create a Provider Key

Export the upstream credential:

export LLAMA_API_KEY="YOUR_LLAMA_API_KEY"

Create the provider key:

PROVIDER_KEY_ID=$(
  curl -sS -X POST "$AISIX_CP/provider_keys" \
    -H "Authorization: Bearer $AISIX_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
      "display_name": "llama-api-prod",
      "provider": "llama",
      "api_key": "'"${LLAMA_API_KEY}"'",
      "api_base": "https://api.llama.com/compat/v1/",
      "allowed_environments": ["'"${ENV_ID}"'"]
    }' | jq -er '.provider_key.id'
)

echo "$PROVIDER_KEY_ID"

provider must be the catalog ID llama. Do not add adapter: AISIX derives the openai adapter for catalog providers and accepts an explicit adapter only for BYO provider keys.

The API base includes /compat/v1/. AISIX normalizes the trailing slash and appends /chat/completions, producing the upstream route https://api.llama.com/compat/v1/chat/completions.

Create a Model

Create a caller-facing alias for the upstream model:

MODEL_ID=$(
  curl -sS -X POST "$AISIX_CP/environments/$ENV_ID/models" \
    -H "Authorization: Bearer $AISIX_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
      "display_name": "llama-api-prod",
      "model_name": "Llama-3.3-70B-Instruct",
      "provider_key_id": "'"${PROVIDER_KEY_ID}"'"
    }' | jq -er '.model.id'
)

echo "$MODEL_ID"

display_name is the stable alias applications send to AISIX. model_name is the exact ID sent to Meta. Check the Meta Llama model documentation before substituting another model because availability can depend on the account and API release.

Create a Caller API Key

Create a caller key limited to this model:

AISIX_API_KEY=$(
  curl -sS -X POST "$AISIX_CP/environments/$ENV_ID/api_keys" \
    -H "Authorization: Bearer $AISIX_TOKEN" \
    -H "Content-Type: application/json" \
    -d '{
      "display_name": "llama-api-caller",
      "allowed_models": ["'"${MODEL_ID}"'"]
    }' | jq -er '.plaintext'
)

echo "$AISIX_API_KEY"

The plaintext caller key is returned only when the resource is created. Store it securely.

Verify the Provider Connection

Send a chat request through AISIX:

curl -sS -X POST "$AISIX_PROXY/v1/chat/completions" \
  -H "Authorization: Bearer $AISIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-api-prod",
    "messages": [
      {
        "role": "user",
        "content": "Say hello from the Meta Llama API."
      }
    ]
  }'

AISIX resolves llama-api-prod to Llama-3.3-70B-Instruct, sends a bearer-authenticated request to the Llama API, and returns an OpenAI-compatible response.

Endpoint Coverage

The normalized /v1/chat/completions route is the primary path for this provider. AISIX can also bridge compatible /v1/responses and /v1/messages requests through the same chat adapter. Embeddings require a model and endpoint that Meta exposes on this API base.

Image generation, video generation, and rerank use route-specific provider allowlists and do not accept the llama provider value. See Provider Compatibility.

Troubleshooting

Symptom	Check
Upstream 401 or 403	Confirm LLAMA_API_KEY is active and the account can use the selected model.
Upstream 404	Confirm the API base includes /compat/v1 and copy the current model ID from Meta.
Provider key creation returns 400	Use provider: "llama" without an adapter field.
AISIX returns model access denied	Confirm the caller key's allowed_models contains the model resource ID.

For credential rotation and provider-level overrides, see Provider Credentials.