AI Proxy | APISIX & API7 API Gateway Docs

Parameters

See plugin common configurations for configuration options available to all plugins.

provider
string
required
vaild vaule:
openai, deepseek, azure-openai, aimlapi, gemini, vertex-ai, anthropic, openrouter, bedrock, openai-compatible
LLM service provider.
When set to openai, the plugin will proxy requests to https://api.openai.com/chat/completions.
When set to deepseek, the plugin will proxy requests to https://api.deepseek.com/chat/completions.
When set to gemini (available from APISIX 3.15.0 and Enterprise 3.9.2), the plugin will proxy requests to https://generativelanguage.googleapis.com/v1beta/openai/chat/completions. If you are proxying requests to an embedding model, you should configure the embedding model endpoint in the override.
When set to vertex-ai (available from APISIX 3.15.0 and Enterprise 3.9.2), the plugin proxies requests to Google Cloud Vertex AI. For chat completions, the plugin will proxy requests to https://{region}-aiplatform.googleapis.com/v1beta1/projects/{project_id}/locations/{region}/endpoints/openapi/chat/completions. For embeddings, the plugin will proxy requests to https://{region}-aiplatform.googleapis.com/v1/projects/{project_id}/locations/{region}/publishers/google/models/{model}:predict. These require configuring provider_conf with project_id and region. Alternatively, you can configure override for a custom endpoint.
When set to anthropic (available from APISIX 3.15.0 and Enterprise 3.9.2), the plugin will proxy requests to https://api.anthropic.com/v1/chat/completions.
When set to openrouter (available from APISIX 3.15.0 and Enterprise 3.9.2), the plugin will proxy requests to https://openrouter.ai/api/v1/chat/completions.
When set to bedrock (available from Enterprise 3.9.12, not available in APISIX yet), the plugin proxies requests to AWS Bedrock using the Converse API. Requires configuring auth.aws with IAM credentials and provider_conf.region with the AWS region. Supports both non-streaming and streaming (ConverseStream) when stream is set to true in the request body.
When set to aimlapi (available from APISIX 3.14.0 and Enterprise 3.8.17), the plugin uses the OpenAI-compatible driver and proxies the request to https://api.aimlapi.com/v1/chat/completions.
When set to openai-compatible, the plugin proxies requests to the custom endpoint configured in override.
When set to azure-openai, the plugin also proxies requests to the custom endpoint configured in override and additionally removes the model parameter from user requests.
auth
object
required
Authentication configurations.
- header
  object
  Authentication headers.
- query
  object
  Authentication query parameters.
- gcp
  object
  GCP service account authentication for Vertex AI. Available in API7 Enterprise from 3.9.2 and not in APISIX.
  service_account_json
  string
  GCP service account JSON content used for authentication. This can be configured using this parameter or by setting the GCP_SERVICE_ACCOUNT environment variable.
  max_ttl
  integer
  Maximum TTL for GCP access token caching, in seconds.
  expire_early_secs
  integer
  default: 60
  Number of seconds to expire the access token before its actual expiration time. This prevents edge cases where tokens expire during active requests.
- aws
  object
  AWS IAM credentials for SigV4 signing. Required when provider is bedrock (for Bedrock, auth.aws is sufficient and auth.header/auth.query are not required). Available in API7 Enterprise from version 3.9.12. Not available in APISIX yet.
  access_key_id
  string
  required
  AWS IAM access key ID.
  secret_access_key
  string
  required
  AWS IAM secret access key.
  session_token
  string
  AWS session token for temporary credentials (e.g. from STS AssumeRole).
options
object
Model configurations.
In addition to model, you can configure additional parameters and they will be forwarded to the upstream LLM service in the request body. For instance, if you are working with OpenAI, you can configure additional parameters such as temperature, top_p, and stream. See your LLM provider's API documentation for more available options.
- model
  string
  Name of the LLM model, such as gpt-4 or gpt-3.5. See your LLM provider's API documentation for more available models.
provider_conf
object
Provider-specific configuration. Required when provider is vertex-ai or bedrock.
Available in API7 Enterprise from 3.9.2 and not in APISIX.
- project_id
  string
  Google Cloud Project ID. Required when provider is vertex-ai.
- region
  string
  required
  Cloud region. For vertex-ai, this is the GCP region. For bedrock, this is the AWS region (e.g. us-east-1).
override
object
Override setting.
- endpoint
  string
  LLM provider endpoint. Required when provider is openai-compatible.
- llm_options
  object
  Provider-aware LLM option overrides. Available in API7 Enterprise from version 3.9.10. Not available in APISIX yet.
  max_tokens
  integer
  Maximum number of output tokens. The gateway automatically maps this to the correct field name for the target provider (e.g. max_completion_tokens for OpenAI Chat, max_output_tokens for OpenAI Responses API). Always force-overwrites the client value.
- request_body
  object
  Per target-protocol request body overrides. Keys are target protocol names (openai-chat, openai-responses, openai-embeddings, anthropic-messages); values are partial request bodies that are deep-merged into the outgoing body (objects merged recursively, arrays and scalars replaced wholesale). Available in API7 Enterprise from version 3.9.10. Not available in APISIX yet.
- request_body_force_override
  boolean
  default: false
  When false (default), client request body fields take priority and request_body override values only fill in missing fields. When true, request_body override values forcefully overwrite client fields. Available in API7 Enterprise from version 3.9.10. Not available in APISIX yet.
logging
object
Logging configurations. These configurations apply to access logs and logs sent to logging plugins, and do not affect the error log.
- summaries
  boolean
  default: false
  If true, log request LLM model, duration, request and response tokens.
- payloads
  boolean
  default: false
  If true, log request and response payload.
timeout
integer
default: 30000
vaild vaule:
between 1 and 600000 inclusive
Request timeout in milliseconds when requesting the LLM service.
keepalive
boolean
default: true
If true, keep the connection alive when requesting the LLM service.
keepalive_timeout
integer
default: 60000
vaild vaule:
greater than or equal to 1000
Keepalive timeout in milliseconds when requesting the LLM service.
keepalive_pool
integer
default: 30
vaild vaule:
greater than or equal to 1
Keepalive pool size for when connecting with the LLM service.
ssl_verify
boolean
default: true
If true, verify the LLM service's certificate.
max_stream_duration_ms
integer
Maximum wall-clock duration (in milliseconds) for a streaming AI response. If the upstream keeps sending data past this deadline, the connection is closed. Unset means no cap. Use this to protect the gateway from upstream bugs that produce tokens indefinitely. Available in API7 Enterprise from version 3.9.10. Not available in APISIX yet.
max_response_bytes
integer
Maximum total bytes read from the upstream for a single AI response (streaming or non-streaming). If exceeded, the connection is closed. Unset means no cap. Available in API7 Enterprise from version 3.9.10. Not available in APISIX yet.
streaming_flush_interval_ms
integer
default: 10
Background flush interval in milliseconds for streaming responses. A positive value starts a background thread that flushes output periodically to bound client latency when upstreams burst multiple tokens at once. Set to 0 to flush each chunk synchronously inline. Available in API7 Enterprise from version 3.9.13. Not available in APISIX yet.

Parameters​

Parameters