API Reference
The TensorZero Gateway exposes two primary API endpoints: /inference
and /feedback
.
The gateway also exposes auxiliary endpoints for Prometheus-compatible metrics (/metrics
), liveness probes (/status
), and readiness probes (/health
).
POST /inference
The inference endpoint is the core of the TensorZero Gateway API.
Under the hood, the gateway validates the request, samples a variant from the function, handles templating when applicable, and routes the inference to the appropriate model provider. If a problem occurs, it attempts to gracefully fallback to a different model provider or variant. After a successful inference, it returns the data to the client and asynchronously stores structured information in the database.
Request
additional_tools
- Type: a list of tools (see below)
- Required: no (default:
[]
)
A list of tools defined at inference time that the model is allowed to call. This field allows for dynamic tool use, i.e. defining tools at runtime.
You should prefer to define tools in the configuration file if possible. Only use this field if dynamic tool use is necessary for your use case.
Each tool is an object with the following fields: description
, name
, parameters
, and strict
.
The fields are identical to those in the configuration file, except that the parameters
field should contain the JSON schema itself rather than a path to it.
See Configuration Reference for more details.
allowed_tools
- Type: list of strings
- Required: no
A list of tool names that the model is allowed to call. The tools must be defined in the configuration file.
Any tools provided in additional_tools
are always allowed, irrespective of this field.
dryrun
- Type: boolean
- Required: no
If true
, the inference request will be executed but won’t be stored to the database.
The gateway will still call the downstream model providers.
This field is primarily for debugging and testing, and you should ignore it in production.
episode_id
- Type: UUID
- Required: no
The ID of an existing episode to associate the inference with.
For the first inference of a new episode, you should not provide an episode_id
. If null, the gateway will generate a new episode ID and return it in the response.
Only use episode IDs that were returned by the TensorZero gateway.
function_name
- Type: string
- Required: yes
The name of the function to call.
The function must be defined in the configuration file.
input
- Type: varies
- Required: yes
The input to the function.
The type of the input depends on the function type.
input.messages
- Type: list of messages (see below)
- Required: no (default:
[]
)
A list of messages to provide to the model.
Each message is an object with the following fields:
role
: The role of the message (assistant
oruser
).content
: The content of the message (see below).
The content
field can be have one of the following types:
- string: the text for a text message (only allowed if there is no schema for that role)
- object: the arguments for a structured text message (only allowed if there is a schema for that role)
- list of content blocks: the content blocks for the message (see below)
A content block is an object that can have type text
, tool_call
, or tool_result
.
We anticipate adding additional content block types in the future.
If the content block has type text
, it must have an additional field text
. The text
should be a string or object depending on whether there is a schema for that role, similar to the content
field above. If your message has a single text
content block, setting content
to a string or object is the short-hand equivalent to using this structure.
If the content block has type tool_call
, it must have the following additional fields:
arguments
: The arguments for the tool call.id
: The ID for the content block.name
: The name of the tool for the content block.
If the content block has type tool_result
, it must have the following additional fields:
id
: The ID for the content block.name
: The name of the tool for the content block.result
: The result of the tool call.
This is the most complex field in the entire API. See this example for more details.
Example
input.system
- Type: string or object
- Required: no
The input for the system message.
If the function does not have a system schema, this field should be a string.
If the function has a system schema, this field should be an object that matches the schema.
output_schema
- Type: object (valid JSON Schema)
- Required: no
If set, this schema will override the output_schema
defined in the function configuration for a JSON function.
This schema is used for validating the output of the function, and sent to providers which support structured outputs.
parallel_tool_calls
- Type: boolean
- Required: no
If true
, the function will be allowed to request multiple tool calls in a single conversation turn.
Most model providers do not support parallel tool calls. In those cases, the gateway ignores this field. At the moment, only Fireworks AI and OpenAI support parallel tool calls.
params
- Type: object (see below)
- Required: no (default:
{}
)
Override inference-time parameters for a particular variant type. This fields allows for dynamic inference parameters, i.e. defining parameters at runtime.
This field’s format is { variant_type: { param: value, ... }, ... }
.
You should prefer to set these parameters in the configuration file if possible.
Only use this field if you need to set these parameters dynamically at runtime.
Note that the parameters will apply to every variant of the specified type.
Currently, we support the following:
chat_completion
max_tokens
seed
temperature
See Configuration Reference for more details on the parameters, and Examples below for usage.
Example
For example, if you wanted to dynamically override the temperature
parameter for a chat_completion
variants, you’d include the following in the request body:
See “Chat Function with Dynamic Inference Parameters” for a complete example.
stream
- Type: boolean
- Required: no
If true
, the gateway will stream the response from the model provider.
tool_choice
- Type: string
- Required: no
If set, overrides the tool choice strategy for the request.
The supported tool choice strategies are:
none
: The function should not use any tools.auto
: The model decides whether or not to use a tool. If it decides to use a tool, it also decides which tools to use.required
: The model should use a tool. If multiple tools are available, the model decides which tool to use.{ specific = "tool_name" }
: The model should use a specific tool. The tool must be defined in thetools
section of the configuration file or provided inadditional_tools
.
variant_name
- Type: string
- Required: no
If set, pins the inference request to a particular variant (not recommended).
You should generally not set this field, and instead let the TensorZero gateway assign a variant. This field is primarily used for testing or debugging purposes.
Response
The response format depends on the function type (as defined in the configuration file) and whether the response is streamed or not.
Chat Function
When the function type is chat
, the response is structured as follows.
In regular (non-streaming) mode, the response is a JSON object with the following fields:
content
- Type: a list of content blocks (see below)
The content blocks generated by the model.
A content block can have type
equal to text
or tool_call
.
If type
is text
, the content block has the following fields:
text
: The text for the content block.
If type
is tool_call
, the content block has the following fields:
arguments
(object): The validated arguments for the tool call (null
if invalid).id
(string): The ID of the content block.name
(string): The validated name of the tool (null
if invalid).raw_arguments
(string): The arguments for the tool call generated by the model (which might be invalid).raw_name
(string): The name of the tool generated by the model (which might be invalid).
episode_id
- Type: UUID
The ID of the episode associated with the inference.
inference_id
- Type: UUID
The ID assigned to the inference.
variant_name
- Type: string
The name of the variant used for the inference.
usage
- Type: object (optional)
The usage metrics for the inference.
The object has the following fields:
input_tokens
: The number of input tokens used for the inference.output_tokens
: The number of output tokens used for the inference.
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
content
- Type: a list of content block chunks (see below)
The content deltas for the inference.
A content block chunk can have type
equal to text
or tool_call
.
If type
is text
, the chunk has the following fields:
id
: The ID of the content block.text
: The text delta for the content block.
If type
is tool_call
, the chunk has the following fields (all strings):
id
: The ID of the content block.raw_name
: The name of the tool. We do not validate this field during streaming inference.raw_arguments
: The arguments delta for the tool call. We do not validate this field during streaming inference.
episode_id
- Type: UUID
The ID of the episode associated with the inference.
inference_id
- Type: UUID
The ID assigned to the inference.
variant_name
- Type: string
The name of the variant used for the inference.
usage
- Type: object (optional)
The usage metrics for the inference.
The object has the following fields:
input_tokens
: The number of input tokens used for the inference.output_tokens
: The number of output tokens used for the inference.
JSON Function
When the function type is json
, the response is structured as follows.
In regular (non-streaming) mode, the response is a JSON object with the following fields:
inference_id
- Type: UUID
The ID assigned to the inference.
episode_id
- Type: UUID
The ID of the episode associated with the inference.
output
- Type: object (see below)
The output object contains the following fields:
raw
: The raw response from the model provider (which might be invalid JSON).parsed
: The parsed response from the model provider (null
if invalid JSON).
variant_name
- Type: string
The name of the variant used for the inference.
usage
- Type: object (optional)
The usage metrics for the inference.
The object has the following fields:
input_tokens
: The number of input tokens used for the inference.output_tokens
: The number of output tokens used for the inference.
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
episode_id
- Type: UUID
The ID of the episode associated with the inference.
inference_id
- Type: UUID
The ID assigned to the inference.
raw
- Type: string
The raw response delta from the model provider.
The TensorZero Gateway does not provide a parsed
field for streaming JSON inferences.
If your application depends on a well-formed JSON response, we recommend using regular (non-streaming) inference.
variant_name
- Type: string
The name of the variant used for the inference.
usage
- Type: object (optional)
The usage metrics for the inference.
The object has the following fields:
input_tokens
: The number of input tokens used for the inference.output_tokens
: The number of output tokens used for the inference.
Examples
Chat Function
Chat Function
Configuration
Request
Response
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
Chat Function with Schemas
Chat Function with Schemas
Configuration
Request
Response
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
Chat Function with Tool Use
Chat Function with Tool Use
Configuration
Request
Response
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
Chat Function with Multi-Turn Tool Use
Chat Function with Multi-Turn Tool Use
Configuration
Request
Response
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
Chat Function with Dynamic Tool Use
Chat Function with Dynamic Tool Use
Configuration
Request
Response
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
Chat Function with Dynamic Inference Parameters
Chat Function with Dynamic Inference Parameters
Configuration
Request
Response
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
JSON Function
JSON Function
Configuration
Request
Response
In streaming mode, the response is an SSE stream of JSON messages, followed by a final [DONE]
message.
Each JSON message has the following fields:
POST /feedback
The /feedback
endpoint assigns feedback to a particular inference or episode.
Each feedback is associated with a metric that is defined in the configuration file.
Request
dryrun
- Type: boolean
- Required: no
If true
, the feedback request will be executed but won’t be stored to the database (i.e. no-op).
This field is primarily for debugging and testing, and you should ignore it in production.
episode_id
- Type: UUID
- Required: when the metric level is
episode
The episode ID to provide feedback for.
You should use this field when the metric level is episode
.
Only use episode IDs that were returned by the TensorZero gateway.
inference_id
- Type: UUID
- Required: when the metric level is
inference
The inference ID to provide feedback for.
You should use this field when the metric level is inference
.
Only use inference IDs that were returned by the TensorZero gateway.
metric_name
- Type: string
- Required: yes
The name of the metric to provide feedback.
For example, if your metric is defined as [metrics.draft_accepted]
in your configuration file, then you would set metric_name: "draft_accepted"
.
The metric names comment
and demonstration
are reserved for special types of feedback.
A comment
is free-form text (string) that can be assigned to either an inference or an episode.
The demonstration
metric is being finalized and is not yet available.
value
- Type: varies
- Required: yes
The value of the feedback.
The type of the value depends on the metric type (e.g. boolean for a metric with type = "boolean"
).
Response
feedback_id
- Type: UUID
The ID assigned to the feedback.
Examples
Inference-Level Boolean Metric
Episode-Level Float Metric
Auxiliary Endpoints
GET /metrics
The TensorZero Gateway exposes a Prometheus-compatible /metrics
endpoint for monitoring.
At the moment, the only available metric is request_count
, which counts the number of successful requests to the gateway.
The metric reports counts for both inference and feedback requests.
Example Response
GET /status
The /status
endpoint is a simple liveness probe.
It returns HTTP status code 200 if the gateway is running.
Example Response
GET /health
The /health
endpoint is a simple readiness probe that checks if the gateway can communicate with the database.
It returns HTTP status code 200 if the gateway is ready to serve requests.