GET
/v1/schemas/cloudflare-workers-ai/chat/accounts/{account_id}/ai/run/@cf/meta/llama-3.1-8b-instruct-fp8
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace30c501632affe56d5dd8751e4c6616e3821d2af4099253eec753f3f2927214f7{
"fetchedAt": 1791349950,
"extractorVersion": "1",
"verifiedAt": null
} |
Request body
0 properties · 0 required · 0 $defsThis schema isn’t a plain object with properties — showing the raw JSON instead.
application/json
{
"provider": "cloudflare-workers-ai",
"activity": "chat",
"endpointId": "accounts/{account_id}/ai/run/@cf/meta/llama-3.1-8b-instruct-fp8",
"kind": "input",
"contentHash": "8b13f2375f87a453d61a2fa2c5df390e6a51b1ac0d5685367fc57a94ea70aca4",
"specRevision": null,
"provenance": {
"sourceUrl": "https://raw.githubusercontent.com/cloudflare/cloudflare-docs/production/src/content/workers-ai-models/llama-3.1-8b-instruct-fp8.json",
"sourceHash": "30c501632affe56d5dd8751e4c6616e3821d2af4099253eec753f3f2927214f7",
"fetchedAt": 1791349950,
"extractorVersion": "1",
"derivation": "upstream-spec",
"verifiedAt": null
},
"createdAt": 1791349950,
"supersededAt": null,
"schema": {
"type": "object",
"oneOf": [
{
"title": "Prompt",
"properties": {
"prompt": {
"type": "string",
"minLength": 1,
"description": "The input text prompt for the model to generate a response."
},
"lora": {
"type": "string",
"description": "Name of the LoRA (Low-Rank Adaptation) model to fine-tune the base model."
},
"response_format": {
"title": "JSON Mode",
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"json_object",
"json_schema"
]
},
"json_schema": {}
}
},
"raw": {
"type": "boolean",
"default": false,
"description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting."
},
"stream": {
"type": "boolean",
"default": false,
"description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events."
},
"max_tokens": {
"type": "integer",
"default": 256,
"description": "The maximum number of tokens to generate in the response."
},
"temperature": {
"type": "number",
"default": 0.6,
"minimum": 0,
"maximum": 5,
"description": "Controls the randomness of the output; higher values produce more random results."
},
"top_p": {
"type": "number",
"minimum": 0.001,
"maximum": 1,
"description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."
},
"top_k": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."
},
"seed": {
"type": "integer",
"minimum": 1,
"maximum": 9999999999,
"description": "Random seed for reproducibility of the generation."
},
"repetition_penalty": {
"type": "number",
"minimum": 0,
"maximum": 2,
"description": "Penalty for repeated tokens; higher values discourage repetition."
},
"frequency_penalty": {
"type": "number",
"minimum": -2,
"maximum": 2,
"description": "Decreases the likelihood of the model repeating the same lines verbatim."
},
"presence_penalty": {
"type": "number",
"minimum": -2,
"maximum": 2,
"description": "Increases the likelihood of the model introducing new topics."
}
},
"required": [
"prompt"
]
},
{
"title": "Messages",
"properties": {
"messages": {
"type": "array",
"description": "An array of message objects representing the conversation history.",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string",
"description": "The role of the message sender (e.g., 'user', 'assistant', 'system', 'tool')."
},
"content": {
"oneOf": [
{
"type": "string",
"description": "The content of the message as a string."
},
{
"type": "array",
"description": "Array of text content parts.",
"items": {
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "Type of the content (text)"
},
"text": {
"type": "string",
"description": "Text content"
}
}
}
}
]
}
},
"required": [
"role",
"content"
]
}
},
"functions": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"code": {
"type": "string"
}
},
"required": [
"name",
"code"
]
}
},
"tools": {
"type": "array",
"description": "A list of tools available for the assistant to use.",
"items": {
"type": "object",
"oneOf": [
{
"properties": {
"name": {
"type": "string",
"description": "The name of the tool. More descriptive the better."
},
"description": {
"type": "string",
"description": "A brief description of what the tool does."
},
"parameters": {
"type": "object",
"description": "Schema defining the parameters accepted by the tool.",
"properties": {
"type": {
"type": "string",
"description": "The type of the parameters object (usually 'object')."
},
"required": {
"type": "array",
"description": "List of required parameter names.",
"items": {
"type": "string"
}
},
"properties": {
"type": "object",
"description": "Definitions of each parameter.",
"additionalProperties": {
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "The data type of the parameter."
},
"description": {
"type": "string",
"description": "A description of the expected parameter."
}
},
"required": [
"type",
"description"
]
}
}
},
"required": [
"type",
"properties"
]
}
},
"required": [
"name",
"description",
"parameters"
]
},
{
"properties": {
"type": {
"type": "string",
"description": "Specifies the type of tool (e.g., 'function')."
},
"function": {
"type": "object",
"description": "Details of the function tool.",
"properties": {
"name": {
"type": "string",
"description": "The name of the function."
},
"description": {
"type": "string",
"description": "A brief description of what the function does."
},
"parameters": {
"type": "object",
"description": "Schema defining the parameters accepted by the function.",
"properties": {
"type": {
"type": "string",
"description": "The type of the parameters object (usually 'object')."
},
"required": {
"type": "array",
"description": "List of required parameter names.",
"items": {
"type": "string"
}
},
"properties": {
"type": "object",
"description": "Definitions of each parameter.",
"additionalProperties": {
"type": "object",
"properties": {
"type": {
"type": "string",
"description": "The data type of the parameter."
},
"description": {
"type": "string",
"description": "A description of the expected parameter."
}
},
"required": [
"type",
"description"
]
}
}
},
"required": [
"type",
"properties"
]
}
},
"required": [
"name",
"description",
"parameters"
]
}
},
"required": [
"type",
"function"
]
}
]
}
},
"response_format": {
"title": "JSON Mode",
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"json_object",
"json_schema"
]
},
"json_schema": {}
}
},
"raw": {
"type": "boolean",
"default": false,
"description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting."
},
"stream": {
"type": "boolean",
"default": false,
"description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events."
},
"max_tokens": {
"type": "integer",
"default": 256,
"description": "The maximum number of tokens to generate in the response."
},
"temperature": {
"type": "number",
"default": 0.6,
"minimum": 0,
"maximum": 5,
"description": "Controls the randomness of the output; higher values produce more random results."
},
"top_p": {
"type": "number",
"minimum": 0.001,
"maximum": 1,
"description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."
},
"top_k": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."
},
"seed": {
"type": "integer",
"minimum": 1,
"maximum": 9999999999,
"description": "Random seed for reproducibility of the generation."
},
"repetition_penalty": {
"type": "number",
"minimum": 0,
"maximum": 2,
"description": "Penalty for repeated tokens; higher values discourage repetition."
},
"frequency_penalty": {
"type": "number",
"minimum": -2,
"maximum": 2,
"description": "Decreases the likelihood of the model repeating the same lines verbatim."
},
"presence_penalty": {
"type": "number",
"minimum": -2,
"maximum": 2,
"description": "Increases the likelihood of the model introducing new topics."
}
},
"required": [
"messages"
]
}
]
}
}Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"cloudflare-workers-ai","endpointId":"accounts/{account_id}/ai/run/@cf/meta/llama-3.1-8b-instruct-fp8","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}