Bike4Mind · Schema
createCompletionRequest
CompanyArtificial IntelligenceOpen SourcePlatformWorkbench
Properties
| Name | Type | Description |
|---|---|---|
| model | string | |
| messages | array | |
| response_format | object | |
| stream | boolean | |
| tools | array | |
| temperature | number | |
| max_tokens | number | |
| sessionId | string | Your own identifier for the conversation this request belongs to. Recorded with the request's credit usage so spend can be grouped by conversation. Not interpreted otherwise. |
| options | object |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/bike4mind-com/json-schema/bike4mind-com-create-completion-request-schema.json",
"title": "createCompletionRequest",
"x-generated": "2026-11-02",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/bike4mind-com-openapi.json#/components/schemas/createCompletionRequest",
"type": "object",
"properties": {
"model": {
"type": "string",
"minLength": 1,
"maxLength": 256
},
"messages": {
"type": "array",
"items": {
"type": "object",
"properties": {
"role": {
"type": "string",
"enum": [
"user",
"assistant",
"system"
]
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "array",
"items": {}
}
],
"description": "A string, or an array of content blocks. A `system` message may instead hold only `tool_addition` / `tool_removal` blocks (`{ type, tool: { type: \"tool_reference\", name } }`) to load or unload a tool named in `tools` mid-conversation without invalidating the prompt cache. It must follow a user turn or an assistant turn ending in a tool search result, and be the last message or precede an assistant turn. Only on models whose `supports_tool_changes` is true and that are served by the direct Anthropic API; otherwise refused with `errorCode: \"tool_changes_unsupported\"` (or `invalid_tool_change` / `unknown_tool_reference` when malformed). A final non-blank assistant turn is an assistant prefill, except a server-tool continuation ending in `server_tool_use` or `tool_search_tool_result`. Plain system prompts and blank messages are ignored. It is accepted only when the selected model has `supports_assistant_prefill: true`; otherwise the request returns `400` with `errorCode: \"assistant_prefill_unsupported\"` without changing the message."
},
"cache": {
"type": "boolean"
}
},
"required": [
"role",
"content"
]
},
"minItems": 1
},
"response_format": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"text"
]
}
},
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"json_schema"
]
},
"json_schema": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"schema": {
"type": "object",
"additionalProperties": {}
},
"strict": {
"type": "boolean",
"default": true
}
},
"required": [
"name",
"schema"
]
}
},
"required": [
"type",
"json_schema"
]
}
]
},
"stream": {
"type": "boolean"
},
"tools": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"properties": {
"toolSchema": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"parameters": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"object"
]
},
"properties": {
"type": "object",
"additionalProperties": {}
},
"additionalProperties": {
"type": "boolean"
},
"required": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"type"
],
"additionalProperties": {}
},
"strict": {
"type": "boolean"
},
"defer_loading": {
"type": "boolean",
"description": "Keep this definition out of the model context until the tool search server tool (or a `tool_reference`) loads it. Honoured only on Claude models (direct Anthropic or Bedrock) whose `supports_tool_search` is true; on every other model it is ignored and the tool is sent as usual. At least one tool, or a `serverTool` entry, must stay non-deferred (`errorCode: \"all_tools_deferred\"`)."
},
"cache_control": {
"description": "Accepted for validation only and not forwarded. Rejected on a deferred tool (`errorCode: \"deferred_tool_cache_control\"`)."
}
},
"required": [
"name",
"description",
"parameters"
]
},
"_isMcpTool": {
"type": "boolean"
}
},
"required": [
"toolSchema"
]
},
{
"type": "object",
"properties": {
"serverTool": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"tool_search_tool_regex_20251119"
]
},
"name": {
"type": "string",
"enum": [
"tool_search_tool_regex"
]
}
},
"required": [
"type",
"name"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"tool_search_tool_bm25_20251119"
]
},
"name": {
"type": "string",
"enum": [
"tool_search_tool_bm25"
]
}
},
"required": [
"type",
"name"
]
}
],
"description": "A provider-run tool, sent to the provider as `{ type, name }`. Only the Anthropic tool search tools exist today, and only on Claude models (direct Anthropic or Bedrock) whose `supports_tool_search` is true; any other model is refused with `errorCode: \"tool_search_unsupported\"` rather than run without it."
}
},
"required": [
"serverTool"
]
}
]
}
},
"temperature": {
"type": "number"
},
"max_tokens": {
"type": "number"
},
"sessionId": {
"type": "string",
"minLength": 1,
"maxLength": 128,
"description": "Your own identifier for the conversation this request belongs to. Recorded with the request's credit usage so spend can be grouped by conversation. Not interpreted otherwise."
},
"options": {
"type": "object",
"properties": {
"temperature": {
"type": "number"
},
"maxTokens": {
"type": "number"
},
"stream": {
"type": "boolean"
},
"tools": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"properties": {
"toolSchema": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"parameters": {
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"object"
]
},
"properties": {
"type": "object",
"additionalProperties": {}
},
"additionalProperties": {
"type": "boolean"
},
"required": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"type"
],
"additionalProperties": {}
},
"strict": {
"type": "boolean"
},
"defer_loading": {
"type": "boolean",
"description": "Keep this definition out of the model context until the tool search server tool (or a `tool_reference`) loads it. Honoured only on Claude models (direct Anthropic or Bedrock) whose `supports_tool_search` is true; on every other model it is ignored and the tool is sent as usual. At least one tool, or a `serverTool` entry, must stay non-deferred (`errorCode: \"all_tools_deferred\"`)."
},
"cache_control": {
"description": "Accepted for validation only and not forwarded. Rejected on a deferred tool (`errorCode: \"deferred_tool_cache_control\"`)."
}
},
"required": [
"name",
"description",
"parameters"
]
},
"_isMcpTool": {
"type": "boolean"
}
},
"required": [
"toolSchema"
]
},
{
"type": "object",
"properties": {
"serverTool": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"tool_search_tool_regex_20251119"
]
},
"name": {
"type": "string",
"enum": [
"tool_search_tool_regex"
]
}
},
"required": [
"type",
"name"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"tool_search_tool_bm25_20251119"
]
},
"name": {
"type": "string",
"enum": [
"tool_search_tool_bm25"
]
}
},
"required": [
"type",
"name"
]
}
],
"description": "A provider-run tool, sent to the provider as `{ type, name }`. Only the Anthropic tool search tools exist today, and only on Claude models (direct Anthropic or Bedrock) whose `supports_tool_search` is true; any other model is refused with `errorCode: \"tool_search_unsupported\"` rather than run without it."
}
},
"required": [
"serverTool"
]
}
]
}
},
"response_format": {
"oneOf": [
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"text"
]
}
},
"required": [
"type"
]
},
{
"type": "object",
"properties": {
"type": {
"type": "string",
"enum": [
"json_schema"
]
},
"json_schema": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"schema": {
"type": "object",
"additionalProperties": {}
},
"strict": {
"type": "boolean",
"default": true
}
},
"required": [
"name",
"schema"
]
}
},
"required": [
"type",
"json_schema"
]
}
]
},
"reasoningEffort": {
"type": "string",
"enum": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh"
],
"description": "Reasoning effort hint. Honoured by the OpenAI (reasoning models only, and not alongside tools on some of them), Kimi (K3 only), DeepSeek and Anthropic Claude (direct and Bedrock) adapters; each maps it onto its own scale. On Claude, `none` turns thinking off where the model allows it (otherwise it runs at the lowest effort), so short `max_tokens` replies stream visible text from the start; `minimal` maps to `low`. When `thinking.enabled` is also set on a Claude model, thinking stays on and this sets its effort instead, with `none` and `minimal` mapping to `low`. Claude models that reason inside `max_tokens` never have that ceiling raised, and on older Claude models any level above `none` turns thinking on (it is off by default there), forces temperature to 1 and drops top_p, and a thinking budget that cannot fit under `max_tokens` is skipped. On the direct Anthropic API, a json_schema `response_format` with no tools is served by a forced tool on models that support forced tool use, and that tool cannot run alongside thinking, so there only `none` is honoured; models served by native structured outputs honour every level. Silently ignored by every other adapter (Gemini, xAI, Ollama) and by non-reasoning models, so sending it there is a no-op."
},
"thinking": {
"type": "object",
"properties": {
"enabled": {
"type": "boolean"
},
"budget_tokens": {
"type": "integer",
"minimum": 1024,
"maximum": 32000
}
},
"required": [
"enabled"
],
"description": "Ask a model that can think to think on this turn. On Claude, `reasoningEffort` then sets how much it thinks, and `budget_tokens` (default 16000, minimum 1024, maximum 32000) sizes thinking on older Claude models. Ignored by models that cannot think, and on the direct Anthropic API when a json_schema `response_format` is served by a forced tool, which cannot run alongside thinking."
},
"cacheTtl": {
"type": "string",
"enum": [
"5m",
"1h"
],
"description": "Prompt-cache lifetime for this request, where the server places cache breakpoints (Claude on the direct Anthropic API or Bedrock, on requests the server caches: CLI and Desktop always, other callers once the conversation has a prior assistant turn). `5m` (the default) writes at 1.25x the input rate; `1h` writes at 2x and keeps the cached prefix for an hour between requests. Reads cost the same either way. Models without 1-hour caching ignore `1h` and keep `5m`. Every breakpoint in a request must share one TTL: with `1h`, set no `cache_control` of your own unless it also carries `ttl: \"1h\"`."
}
}
}
},
"required": [
"model",
"messages"
]
}Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/bike4mind-com-create-completion-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.