> ## Documentation Index
> Fetch the complete documentation index at: https://inference-docs.cerebras.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Chat Completions
> Generate conversational responses using a structured message format with roles (system, user, assistant, developer, tool). Best for chatbots, assistants, and multi-turn conversations.
Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. For details about parameters in reasoning models, refer to the [Reasoning Guide](/capabilities/reasoning).
## OpenAPI
````yaml POST /v1/chat/completions
openapi: 3.1.0
info:
title: Cerebras Inference API
version: 1.0.0
description: >
Generate conversational responses using a structured message format with
roles (system, user, assistant, developer, tool). Best for chatbots,
assistants, and multi-turn conversations.
servers:
- url: https://api.cerebras.ai
description: Cerebras Inference API
security:
- BearerAuth: []
paths:
/v1/chat/completions:
post:
summary: Create chat completion
description: >
Generate conversational responses using a structured message format with
roles (system, user, assistant, developer, tool). Best for chatbots,
assistants, and multi-turn conversations.
operationId: createChatCompletion
parameters:
- name: Content-Type
in: header
description: >
The media type of the request body. Supported values:
`application/json`, `application/vnd.msgpack`. Default:
`application/json`.
schema:
type: string
enum:
- application/json
- application/vnd.msgpack
default: application/json
- name: Content-Encoding
in: header
description: >
The compression encoding applied to the request body. When set, the
request body must be gzip-compressed. Can be combined with any
supported `Content-Type`. Supported values: `gzip`.
schema:
type: string
enum:
- gzip
- name: queue_threshold
in: header
description: >
Controls the queue time threshold for requests using the `flex` or
`auto` service tiers. Requests are preemptively rejected if the
rolling average queue time exceeds this threshold. Valid range:
`50`–`20000` (milliseconds). **Private Preview.**
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionRequest'
examples:
Default:
summary: Default
value:
model: gpt-oss-120b
messages:
- role: user
content: Hello!
Image Input:
summary: Image Input
value:
model: gemma-4-31b
messages:
- role: user
content:
- type: text
text: Describe this image in one concise sentence.
- type: image_url
image_url:
url: data:image/png;base64,{BASE64_IMAGE}
Streaming:
summary: Streaming
value:
model: gpt-oss-120b
messages:
- role: system
content: You are a helpful assistant.
- role: user
content: Hello!
stream: true
Tool Calling:
summary: Tool Calling
value:
model: gpt-oss-120b
messages:
- role: user
content: What is the weather like in Boston today?
tools:
- type: function
function:
name: get_current_weather
description: Get the current weather in a given location
parameters:
type: object
properties:
location:
type: string
description: The city and state, e.g. San Francisco, CA
unit:
type: string
enum:
- celsius
- fahrenheit
required:
- location
tool_choice: auto
responses:
'200':
description: Successful response
content:
application/json:
schema:
$ref: '#/components/schemas/ChatCompletionResponse'
examples:
Default:
summary: Default
value:
id: chatcmpl-b8d624a5-43d4-477a-8b94-61be750e2872
choices:
- finish_reason: stop
index: 0
message:
role: assistant
content: Hello! How can I assist you today?
tool_calls: null
logprobs: null
created: 1775679664
model: gpt-oss-120b
object: chat.completion
system_fingerprint: fp_4c26d27ac5dbffe28c72
usage:
prompt_tokens: 69
completion_tokens: 45
total_tokens: 114
Image Input:
summary: Image Input
value:
id: chatcmpl-a941cccf-098d-4646-99ae-f93c3b8f3c96
choices:
- finish_reason: stop
index: 0
message:
role: assistant
content: >-
A snippet of Python code defines a function to add
two numbers and prints the result.
tool_calls: null
logprobs: null
created: 1782514735
model: gemma-4-31b
object: chat.completion
system_fingerprint: fp_b2c59c382b338de84cfc
usage:
prompt_tokens: 298
completion_tokens: 18
total_tokens: 316
image_tokens: 275
prompt_tokens_details:
cached_tokens: 256
completion_tokens_details:
reasoning_tokens: 0
time_info:
queue_time: 0.000630072
prompt_time: 0.006339716
completion_time: 0.01440533
total_time: 0.0919649600982666
created: 1782514735.285658
Streaming:
summary: Streaming
value:
id: chatcmpl-29429662-a0ae-4139-815a-be566d744aae
object: chat.completion.chunk
created: 1775680004
model: gpt-oss-120b
system_fingerprint: fp_4c26d27ac5dbffe28c72
choices:
- delta:
content: Hello! How can I assist you today?
index: 0
finish_reason: stop
usage:
total_tokens: 108
completion_tokens: 26
prompt_tokens: 82
Tool Calling:
summary: Tool Calling
value:
id: chatcmpl-24e60ea3-bec1-4b35-a5d5-7a62cbba5668
choices:
- finish_reason: tool_calls
index: 0
message:
role: assistant
content: null
tool_calls:
- id: efa96a7b1
type: function
function:
name: get_current_weather
arguments: '{"location":"Boston, MA","unit":"fahrenheit"}'
logprobs: null
created: 1775679671
model: gpt-oss-120b
object: chat.completion
system_fingerprint: fp_4c26d27ac5dbffe28c72
usage:
prompt_tokens: 155
completion_tokens: 88
total_tokens: 243
x-codeSamples:
- lang: python
label: Default
source: |
from cerebras.cloud.sdk import Cerebras
import os
client = Cerebras(api_key=os.environ.get("CEREBRAS_API_KEY"))
chat_completion = client.chat.completions.create(
model="gpt-oss-120b",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(chat_completion)
- lang: javascript
label: Default
source: |
import Cerebras from '@cerebras/cerebras_cloud_sdk';
const client = new Cerebras({
apiKey: process.env['CEREBRAS_API_KEY'],
});
async function main() {
const response = await client.chat.completions.create({
messages: [{ role: 'user', content: 'Hello!' }],
model: 'gpt-oss-120b',
});
console.log(response);
}
main();
- lang: bash
label: Default
source: |
curl https://api.cerebras.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${CEREBRAS_API_KEY}" \
-d '{
"model": "gpt-oss-120b",
"messages": [{"role": "user", "content": "Hello!"}]
}'
- lang: python
label: Image Input
source: |
from cerebras.cloud.sdk import Cerebras
import os
import base64
client = Cerebras(api_key=os.environ.get("CEREBRAS_API_KEY"))
def encode_image(image_path):
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode("utf-8")
base64_image = encode_image("screenshot.png")
response = client.chat.completions.create(
model="gemma-4-31b",
messages=[
{
"role": "user",
"content": [
{"type": "text", "text": "Describe this image in one concise sentence."},
{
"type": "image_url",
"image_url": {
"url": f"data:image/png;base64,{base64_image}"
},
},
],
}
],
)
print(response.choices[0].message.content)
- lang: javascript
label: Image Input
source: |
import Cerebras from '@cerebras/cerebras_cloud_sdk';
import fs from 'fs';
const client = new Cerebras({
apiKey: process.env['CEREBRAS_API_KEY'],
});
async function main() {
const imageBuffer = fs.readFileSync('screenshot.png');
const base64Image = imageBuffer.toString('base64');
const response = await client.chat.completions.create({
model: 'gemma-4-31b',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Describe this image in one concise sentence.' },
{
type: 'image_url',
image_url: {
url: `data:image/png;base64,${base64Image}`,
},
},
],
},
],
});
console.log(response.choices[0].message.content);
}
main();
- lang: bash
label: Image Input
source: |
BASE64_IMAGE=$(base64 -i screenshot.png)
curl https://api.cerebras.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${CEREBRAS_API_KEY}" \
-d "{
\"model\": \"gemma-4-31b\",
\"messages\": [
{
\"role\": \"user\",
\"content\": [
{\"type\": \"text\", \"text\": \"Describe this image in one concise sentence.\"},
{
\"type\": \"image_url\",
\"image_url\": {
\"url\": \"data:image/png;base64,\${BASE64_IMAGE}\"
}
}
]
}
]
}"
- lang: python
label: Streaming
source: |
from cerebras.cloud.sdk import Cerebras
import os
client = Cerebras(api_key=os.environ.get("CEREBRAS_API_KEY"))
stream = client.chat.completions.create(
model="gpt-oss-120b",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"},
],
stream=True,
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")
- lang: javascript
label: Streaming
source: |
import Cerebras from '@cerebras/cerebras_cloud_sdk';
const client = new Cerebras({
apiKey: process.env['CEREBRAS_API_KEY'],
});
async function main() {
const stream = await client.chat.completions.create({
model: 'gpt-oss-120b',
messages: [
{ role: 'system', content: 'You are a helpful assistant.' },
{ role: 'user', content: 'Hello!' },
],
stream: true,
});
for await (const chunk of stream) {
if (chunk.choices[0].delta.content) {
process.stdout.write(chunk.choices[0].delta.content);
}
}
}
main();
- lang: bash
label: Streaming
source: |
curl https://api.cerebras.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${CEREBRAS_API_KEY}" \
-d '{
"model": "gpt-oss-120b",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
],
"stream": true
}'
- lang: python
label: Tool Calling
source: |
from cerebras.cloud.sdk import Cerebras
import os
client = Cerebras(api_key=os.environ.get("CEREBRAS_API_KEY"))
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
},
},
"required": ["location"],
"additionalProperties": False,
},
},
}
]
response = client.chat.completions.create(
model="gpt-oss-120b",
messages=[
{"role": "user", "content": "What's the weather like in Boston today?"}
],
tools=tools,
tool_choice="auto",
)
print(response.choices[0].message.tool_calls)
- lang: javascript
label: Tool Calling
source: |
import Cerebras from '@cerebras/cerebras_cloud_sdk';
const client = new Cerebras({
apiKey: process.env['CEREBRAS_API_KEY'],
});
async function main() {
const response = await client.chat.completions.create({
model: 'gpt-oss-120b',
messages: [
{ role: 'user', content: "What's the weather like in Boston today?" },
],
tools: [
{
type: 'function',
function: {
name: 'get_current_weather',
description: 'Get the current weather in a given location',
parameters: {
type: 'object',
properties: {
location: {
type: 'string',
description: 'The city and state, e.g. San Francisco, CA',
},
unit: { type: 'string', enum: ['celsius', 'fahrenheit'] },
},
required: ['location'],
additionalProperties: false,
},
},
},
],
tool_choice: 'auto',
});
console.log(response.choices[0].message.tool_calls);
}
main();
- lang: bash
label: Tool Calling
source: |
curl https://api.cerebras.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer ${CEREBRAS_API_KEY}" \
-d '{
"model": "gpt-oss-120b",
"messages": [
{"role": "user", "content": "What is the weather like in Boston today?"}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location"]
}
}
}
],
"tool_choice": "auto"
}'
components:
schemas:
ChatCompletionRequest:
type: object
required:
- model
- messages
properties:
messages:
type: array
description: >
A list of messages comprising the conversation so far. Depending on
the model you use, different message types (modalities) are
supported, like text and images.
items:
oneOf:
- $ref: '#/components/schemas/SystemMessage'
- $ref: '#/components/schemas/UserMessage'
- $ref: '#/components/schemas/AssistantMessage'
- $ref: '#/components/schemas/ToolMessage'
- $ref: '#/components/schemas/DeveloperMessage'
discriminator:
propertyName: role
mapping:
system:
$ref: '#/components/schemas/SystemMessage'
user:
$ref: '#/components/schemas/UserMessage'
assistant:
$ref: '#/components/schemas/AssistantMessage'
tool:
$ref: '#/components/schemas/ToolMessage'
developer:
$ref: '#/components/schemas/DeveloperMessage'
model:
type: string
description: The ID of the model to use for generating a response.
clear_thinking:
type: boolean
nullable: true
description: >
Controls whether thinking content from previous conversation turns
is included in the prompt context.
- `false` - Thinking from all previous turns is preserved in the
conversation history. Recommended for agentic workflows where
reasoning from past tool-calling turns may be relevant for future
tool calls.
- `true` (default) - Thinking from earlier turns is excluded.
Recommended for general chat conversations where reasoning from past
turns is less relevant for performance.
When this parameter is not specified or set to `null`, the API
defaults to `clear_thinking: true`.
Only supported on the `zai-glm-4.7` model. For additional
information, see [Preserved
thinking](https://docs.z.ai/guides/capabilities/thinking-mode#preserved-thinking)
in the Z.ai documentation.
frequency_penalty:
type: number
nullable: true
minimum: -2
maximum: 2
default: 0
description: >
A number between -2.0 and 2.0. Positive values reduce the likelihood
of the model repeating tokens by applying a penalty proportional to
how frequently each token has already appeared in the generated
output.
logit_bias:
type: object
nullable: true
additionalProperties:
type: number
default: null
description: >
Modify the likelihood of specified tokens appearing in the
completion. Accepts a JSON object that maps tokens (specified by
their token ID in the tokenizer) to an associated bias value from
-100 to 100. Mathematically, the bias is added to the logits
generated by the model prior to sampling. The exact effect will vary
per model, but values between -1 and 1 should decrease or increase
likelihood of selection; values like -100 or 100 should result in a
ban or exclusive selection of the relevant token.
logprobs:
type: boolean
default: false
description: |
Whether to return log probabilities of the output tokens.
max_completion_tokens:
type: integer
nullable: true
description: >
The maximum number of tokens that can be generated in the
completion, including reasoning tokens. The total length of input
tokens and generated tokens is limited by the model's context
length.
parallel_tool_calls:
type: boolean
nullable: true
default: true
description: >
Whether to enable parallel function calling during tool use. When
enabled (default), the model can request multiple tool calls
simultaneously in a single response. When disabled, only one tool
call is made at a time.
prediction:
type: object
nullable: true
description: >
Configuration for a [Predicted
Output](/capabilities/predicted-outputs), which can greatly speed up
response times when large parts of the model response are known in
advance. Most common when regenerating a file with mostly minor
changes.
required:
- type
- content
properties:
type:
type: string
enum:
- content
description: The type of predicted content. Always `content`.
content:
description: >
The content that should be matched when generating a model
response.
oneOf:
- type: string
description: >
The content used for a given Predicted Output. Typically the
text of a file you are regenerating with only minor changes.
- type: array
description: Array of text content parts.
items:
type: object
required:
- type
- text
properties:
type:
type: string
enum:
- text
text:
type: string
description: The text content.
presence_penalty:
type: number
nullable: true
minimum: -2
maximum: 2
default: 0
description: >
A number between -2.0 and 2.0. Positive values reduce the likelihood
of the model repeating tokens that have already appeared in the
output, encouraging the model to introduce new topics.
prompt_cache_key:
type: string
nullable: true
maxLength: 1024
default: null
description: >
An opaque identifier that groups related requests so they reuse the
same [prompt cache](/capabilities/prompt-caching). Requests sharing
the same 'prompt_cache_key' are routed together, which increases
cache hits and reduces time to first token.
Set it to a stable identifier like a conversation ID, user ID, or
session ID.
**Requires account-level enablement. [Contact
us](https://www.cerebras.ai/contact) or reach out to your account
representative to request access.**
reasoning_effort:
type: string
nullable: true
enum:
- low
- medium
- high
- none
description: >
Controls the amount of reasoning the model performs. Supported
values vary by model:
- **gpt-oss-120b**: `low`, `medium` (default), `high`
- **zai-glm-4.7**: `none` (disables reasoning)
- **gemma-4-31b**: `none` (default), `low`, `medium`, `high` (all
enable reasoning equivalently). `raw` and `hidden` reasoning formats
are not supported.
response_format:
nullable: true
description: >
An object that controls the format of the model response.
Setting `{ "type": "json_schema", ... }` enables Structured Outputs,
which enforces schema compliance. See [Structured
Outputs](/capabilities/structured-outputs) for details.
Setting `{ "type": "json_object" }` enables legacy JSON mode, which
ensures the model returns valid JSON but does not enforce a specific
schema. To use `json_object`, include a system or user message
specifying the desired format. `json_object` is not compatible with
streaming — `stream` must be set to `false`.
oneOf:
- $ref: '#/components/schemas/ResponseFormatText'
- $ref: '#/components/schemas/ResponseFormatJsonSchema'
- $ref: '#/components/schemas/ResponseFormatJsonObject'
seed:
type: integer
nullable: true
description: >
If specified, the system will make a best effort to sample
deterministically so repeated requests with the same `seed` and
parameters return the same result. Determinism is not guaranteed.
service_tier:
type: string
nullable: true
default: default
enum:
- priority
- default
- auto
- flex
description: >
Controls request prioritization.
**Note**: This feature is in **Private Preview**. For access or more
information, [contact us](https://www.cerebras.ai/contact) or reach
out to your account representative.
Available options:
- `priority` - Highest priority processing (Only available for
dedicated endpoints, not shared endpoints.)
- `default` - Standard priority processing
- `auto` - Automatically uses the highest available service tier
- `flex` - Lowest priority processing
See [Service Tiers](/capabilities/service-tiers) for more
information.
stop:
type: string
nullable: true
description: >
Up to 4 sequences where the API will stop generating further tokens.
The returned text will not contain the stop sequence.
stream:
type: boolean
nullable: true
description: |
If set to `true`, partial message deltas will be sent.
temperature:
type: number
nullable: true
minimum: 0
maximum: 2
description: >
Sampling temperature between 0 and 2.0. Higher values (e.g. 0.8)
make output more random; lower values (e.g. 0.2) make it more
focused and deterministic. We recommend altering this or `top_p`,
not both.
tool_choice:
description: >
Controls which (if any) tool is called by the model.
- `none` — no tool is called
- `auto` — (default when tools are present) the model chooses
whether to call a tool
- `required` — forces a tool call
A specific tool can be forced by passing an object specifying the
function name.
oneOf:
- type: string
enum:
- none
- auto
- required
- type: object
required:
- type
- function
properties:
type:
type: string
enum:
- function
function:
type: object
required:
- name
properties:
name:
type: string
description: The name of the function to call.
tools:
type: array
nullable: true
description: >
A list of tools the model may call. Use this to provide a list of
functions the model may generate JSON inputs for.
Currently, only functions are supported. Specifying tools consumes
prompt tokens; too many may degrade performance or hit context
length limits.
items:
type: object
required:
- type
- function
properties:
type:
type: string
enum:
- function
description: The type of the tool. Currently only `function` is supported.
function:
type: object
required:
- name
properties:
name:
type: string
description: >
The name of the function to call. Supported characters:
`a-z`, `A-Z`, `0-9`, `_`, `-`. Maximum length: 64.
description:
type: string
description: >
A description of what the function does, used by the model
to choose when and how to call the function.
parameters:
type: object
description: >
The parameters the function accepts, described as a JSON
Schema object. Omitting parameters defines a function with
an empty parameter list.
top_logprobs:
type: integer
nullable: true
minimum: 0
maximum: 20
description: >
An integer between 0 and 20 specifying the number of most likely
tokens to return at each token position, each with an associated log
probability. If using this parameter, `logprobs` must also be set to
`true`.
top_p:
type: number
nullable: true
minimum: 0
maximum: 1
description: >
Nucleus sampling parameter. The model considers only the tokens
comprising the top `top_p` probability mass (e.g. 0.1 means only the
tokens comprising the top 10% probability mass are considered). We
recommend altering this or `temperature`, not both.
user:
type: string
nullable: true
description: >
A unique identifier representing your end-user, which can help
monitor and detect abuse.
ChatCompletionResponse:
type: object
properties:
id:
type: string
description: A unique identifier for the chat completion.
choices:
type: array
description: >
A list of chat completion choices. Can be more than one if `n` is
greater than 1.
items:
type: object
properties:
finish_reason:
type: string
enum:
- stop
- length
- content_filter
- tool_calls
description: The reason the model stopped generating tokens.
index:
type: integer
description: The index of the choice in the list of choices.
logprobs:
type: object
nullable: true
description: Log probability information for the output tokens.
reasoning_logprobs:
type: object
nullable: true
description: >
Log probability information for the reasoning tokens, if
provided by the model.
message:
type: object
description: A chat completion message generated by the model.
properties:
content:
type: string
nullable: true
description: The contents of the message.
role:
type: string
description: The role of the author of this message.
reasoning:
type: string
description: |
The model's reasoning content when using reasoning models.
tool_calls:
type: array
nullable: true
description: Tool calls the model requested in its response.
items:
type: object
properties:
id:
type: string
description: The ID of the tool call.
type:
type: string
enum:
- function
description: The type of tool call.
function:
type: object
description: The function call details.
properties:
name:
type: string
description: The name of the function called.
arguments:
type: string
description: >
The JSON-encoded arguments supplied by the
model.
created:
type: integer
description: Unix timestamp (in seconds) of when the completion was created.
model:
type: string
description: The model used for the chat completion.
object:
type: string
enum:
- chat.completion
description: The object type. Always `chat.completion`.
system_fingerprint:
type: string
description: >
A fingerprint for the model or backend used to generate the
response.
service_tier:
type: string
nullable: true
description: |
The service tier used for the request, or `null` if not specified.
service_tier_used:
type: string
nullable: true
enum:
- priority
- default
- flex
description: >
The service tier used for processing the request. Only present when
`service_tier` is set to `auto` in the request.
usage:
type: object
description: Usage statistics for the completion request.
properties:
prompt_tokens:
type: integer
description: Number of tokens in the prompt.
completion_tokens:
type: integer
description: Number of tokens in the generated completion.
total_tokens:
type: integer
description: Total number of tokens used (prompt + completion).
image_tokens:
type: integer
description: >
Number of tokens used to represent image inputs. Present for
requests to vision-capable models.
prompt_tokens_details:
type: object
description: Detailed breakdown of prompt token usage.
properties:
cached_tokens:
type: integer
description: >
Number of prompt tokens served from the cache, reused from a
previous request.
completion_tokens_details:
type: object
description: |
Breakdown of completion tokens when using Predicted Outputs.
properties:
accepted_prediction_tokens:
type: integer
description: |
Tokens in the prediction that appeared in the completion.
rejected_prediction_tokens:
type: integer
description: >
Tokens in the prediction that did not appear in the
completion. Counted in total completion tokens for billing,
output, and context window limits.
reasoning_tokens:
type: integer
description: Tokens spent on model reasoning, if applicable.
time_info:
type: object
description: Performance timing information for the request.
properties:
queue_time:
type: number
description: Time spent in queue waiting for processing (seconds).
prompt_time:
type: number
description: Time spent processing prompt/input tokens (seconds).
completion_time:
type: number
description: |
Time spent generating completion/output tokens (seconds).
total_time:
type: number
description: >
Total time for the entire request from submission to completion
(seconds).
created:
type: number
description: Unix timestamp of when the time_info was recorded.
SystemMessage:
type: object
title: System message
description: >
Developer-provided instructions the model should follow regardless of
user messages.
required:
- role
- content
properties:
role:
type: string
enum:
- system
description: The role of the message author. Always `system`.
content:
description: The contents of the system message.
oneOf:
- type: string
description: Text content string.
- type: array
description: Array of text content parts.
items:
type: object
required:
- type
- text
properties:
type:
type: string
enum:
- text
text:
type: string
name:
type: string
description: >
An optional name for the participant. Provides the model with
information to differentiate between participants of the same role.
UserMessage:
type: object
title: User message
description: |
Messages sent by an end user, containing prompts or additional context.
required:
- role
- content
properties:
role:
type: string
enum:
- user
description: The role of the message author. Always `user`.
content:
description: |
The contents of the user message. Can include text and image
inputs. Supported content types differ by model.
oneOf:
- type: string
description: Text content string.
- type: array
description: Array of content parts (text and/or image).
items:
oneOf:
- type: object
title: Text
description: Text content part.
required:
- type
- text
properties:
type:
type: string
enum:
- text
text:
type: string
description: The text content.
- type: object
title: Image
description: >
Image content part. **Public Preview.** Images must be
provided as base64-encoded PNG or JPEG data. HTTPS image
URL ingestion is not supported yet.
required:
- type
- image_url
properties:
type:
type: string
enum:
- image_url
image_url:
type: object
required:
- url
properties:
url:
type: string
description: >
The image as a base64-encoded data URI. Format:
`data:image/{format};base64,{data}`. Supported
formats: `png`, `jpeg`. External URLs (e.g.
`https://...`) are not supported.
name:
type: string
description: >
An optional name for the participant. Provides the model with
information to differentiate between participants of the same role.
AssistantMessage:
type: object
title: Assistant message
description: Messages sent by the model in response to user messages.
required:
- role
properties:
role:
type: string
enum:
- assistant
description: The role of the message author. Always `assistant`.
content:
nullable: true
description: The contents of the assistant message.
oneOf:
- type: string
description: Text content string.
- type: array
description: >
Array of content parts. For assistant messages, only type `text`
is supported.
items:
type: object
required:
- type
- text
properties:
type:
type: string
enum:
- text
text:
type: string
name:
type: string
description: An optional name for the participant.
reasoning:
type: string
nullable: true
description: >
The reasoning content from the model's response. Include this when
passing back assistant messages that contained reasoning.
tool_calls:
type: array
description: Tool calls generated by the model, such as function calls.
items:
type: object
required:
- id
- type
- function
properties:
id:
type: string
description: The ID of the tool call.
type:
type: string
enum:
- function
description: The type of tool. Currently only `function` is supported.
function:
type: object
required:
- name
- arguments
properties:
name:
type: string
description: The name of the function to call.
arguments:
type: string
description: >
The arguments to call the function with, as generated by
the model in JSON format.
ToolMessage:
type: object
title: Tool message
description: Tool message containing the result of a tool call.
required:
- role
- content
- tool_call_id
properties:
role:
type: string
enum:
- tool
description: The role of the message author. Always `tool`.
content:
description: The contents of the tool message.
oneOf:
- type: string
description: Text content string.
- type: array
description: Array of text content parts.
items:
type: object
required:
- type
- text
properties:
type:
type: string
enum:
- text
text:
type: string
tool_call_id:
type: string
description: The tool call that this message is responding to.
DeveloperMessage:
type: object
title: Developer message
description: >
Developer-provided instructions the model should follow regardless of
user messages. For `gpt-oss-120b`, developer messages replace system
messages, but `system` is still accepted. Only available for the
`gpt-oss-120b` model.
required:
- role
- content
properties:
role:
type: string
enum:
- developer
description: The role of the message author. Always `developer`.
content:
description: The contents of the developer message.
oneOf:
- type: string
description: Text content string.
- type: array
description: Array of text content parts.
items:
type: object
required:
- type
- text
properties:
type:
type: string
enum:
- text
text:
type: string
name:
type: string
description: An optional name for the participant.
ResponseFormatText:
type: object
title: Text
description: Text format (default). Generates plain text responses.
required:
- type
properties:
type:
type: string
enum:
- text
description: The type of response format being defined. Always `text`.
ResponseFormatJsonSchema:
type: object
title: JSON Schema
description: >
JSON Schema format. Enforces schema compliance for structured output.
Recommended over `json_object` for models that support it.
required:
- type
- json_schema
properties:
type:
type: string
enum:
- json_schema
description: The type of response format being defined. Always `json_schema`.
json_schema:
type: object
required:
- name
properties:
name:
type: string
description: An optional name for your schema.
description:
type: string
description: >
A description of the response format's purpose, used by the
model to determine how to generate its response.
schema:
type: object
description: >
A valid [JSON Schema](https://json-schema.org/) object that
defines the structure, types, and requirements for the response.
Supports standard JSON Schema features including types
(`string`, `number`, `boolean`, `integer`, `object`, `array`,
`enum`, `anyOf`, `null`), nested structures, required fields,
and `additionalProperties` (must be set to `false`).
strict:
type: boolean
default: false
description: >
When `true`, enforces strict adherence to the schema. The model
will only return fields defined in the schema and with the
correct types. When `false`, behaves similar to JSON mode but
uses the schema as a guide. Defaults to `false`.
ResponseFormatJsonObject:
type: object
title: JSON Object
description: >
JSON object format (legacy). Ensures valid JSON output but does not
enforce a specific schema. Using `json_schema` is recommended for models
that support it.
To use `json_object`, include a system or user message specifying the
desired format. `json_object` is not compatible with streaming —
`stream` must be set to `false`.
required:
- type
properties:
type:
type: string
enum:
- json_object
description: The type of response format being defined. Always `json_object`.
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: >
API key for authentication. Obtain your key from the Cerebras Cloud
console and pass it as `Authorization: Bearer YOUR_API_KEY`.
````