Appearance
API reference
One API key for LLMs, embeddings, search, retrieval and agent tools. Base URL: https://api.usefully.info/v1.
Authenticate with Authorization: Bearer <key> (see Authentication). Errors use the standard error shape.
Generated from openapi.json.
System
Health and readiness.
GET /healthz
Liveness: the process is up and serving HTTP.
No API key needed.
| Status | Description | Body |
|---|---|---|
| 200 | string (text/plain) |
GET /readyz
Readiness: dependencies are reachable, so the instance can take traffic.
No API key needed.
| Status | Description | Body |
|---|---|---|
| 200 | Readiness (application/json) | |
| 503 | Readiness (application/json) |
GET /v1/status
Current service status. Public, cached by clients for ~30 s.
No API key needed.
| Status | Description | Body |
|---|---|---|
| 200 | Status (application/json) |
Billing
Credits, purchases and balance alerts.
GET /v1/billing
Balance and billing settings for the calling key's organization.
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | BillingOverview (application/json) |
POST /v1/billing/checkout
Starts a credit purchase. Credits are added when the payment is confirmed.
Requires an API key.
Request body: CheckoutRequest
| Status | Description | Body |
|---|---|---|
| 200 | CheckoutResponse (application/json) |
PUT /v1/billing/settings
Updates the low-balance alert setting.
Requires an API key.
Request body: SettingsUpdate
| Status | Description | Body |
|---|---|---|
| 200 | BillingOverview (application/json) |
GET /v1/currencies
No API key needed.
| Status | Description | Body |
|---|---|---|
| 200 | CurrencyList (application/json) |
Tools
Code sandboxes and headless browsers for agents, billed by time.
GET /v1/browser/sessions
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | SessionList (application/json) |
POST /v1/browser/sessions
Starts a browser. Connect with Playwright (chromium.connectOverCDP(connect_url)) or Puppeteer (puppeteer.connect({browserWSEndpoint: connect_url})).
Requires an API key.
Request body: CreateSession
| Status | Description | Body |
|---|---|---|
| 201 | SessionView (application/json) | |
| 400 | ErrorBody (application/json) | |
| 402 | ErrorBody (application/json) |
GET /v1/browser/sessions/{id}
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | SessionView (application/json) | |
| 404 | ErrorBody (application/json) |
DELETE /v1/browser/sessions/{id}
Ends a session and bills the minutes used. Ending one that already ended returns it unchanged.
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | SessionView (application/json) | |
| 404 | ErrorBody (application/json) |
POST /v1/sandbox/run
Runs code in a fresh sandbox and returns stdout, stderr, rich results and any error. Billed per second of sandbox time.
Requires an API key.
Request body: RunRequest
| Status | Description | Body |
|---|---|---|
| 200 | RunResponse (application/json) | |
| 400 | ErrorBody (application/json) | |
| 402 | ErrorBody (application/json) |
Chat
LLM chat (OpenAI-compatible and native Anthropic).
POST /v1/chat/completions
Creates a chat completion (OpenAI-compatible). Set stream: true for Server-Sent Events.
Requires an API key.
Request body: ChatRequest
| Status | Description | Body |
|---|---|---|
| 200 | A completion; with stream: true, a text/event-stream of data: <ChatChunk> events ending with data: [DONE] | ChatResponse (application/json); ChatChunk (text/event-stream) |
| 400 | ErrorBody (application/json) | |
| 401 | ErrorBody (application/json) | |
| 402 | Insufficient credits | ErrorBody (application/json) |
| 404 | ErrorBody (application/json) | |
| 429 | ErrorBody (application/json) | |
| 502 | ErrorBody (application/json) | |
| 503 | ErrorBody (application/json) |
POST /v1/messages
Native Anthropic Messages API for Claude models. The body is forwarded as-is (only model is rewritten), so Anthropic SDKs work unchanged.
Requires an API key.
Request body: object
| Status | Description | Body |
|---|---|---|
| 200 | An Anthropic Messages API response or SSE stream | object (application/json) |
| 400 | ErrorBody (application/json) | |
| 401 | ErrorBody (application/json) |
GET /v1/models
Lists available models. Public: no API key needed.
No API key needed.
| Status | Description | Body |
|---|---|---|
| 200 | ModelList (application/json) |
Search
Web search and page extraction, billed per query or page.
POST /v1/crawl
Starts crawling a website. Returns a job to poll; pages are billed as they're extracted.
Requires an API key.
Request body: CrawlRequest
| Status | Description | Body |
|---|---|---|
| 202 | JobView (application/json) | |
| 400 | ErrorBody (application/json) | |
| 402 | ErrorBody (application/json) |
POST /v1/extract
Extracts the main content of web pages as Markdown. Billed per page.
Requires an API key.
Request body: ExtractRequest
| Status | Description | Body |
|---|---|---|
| 200 | Per-URL results; failed pages aren't billed | ExtractResponse (application/json) |
| 400 | ErrorBody (application/json) | |
| 402 | ErrorBody (application/json) | |
| 429 | ErrorBody (application/json) |
GET /v1/jobs
Recent jobs, newest first.
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | JobList (application/json) |
GET /v1/jobs/{id}
A job's status and progress.
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | JobView (application/json) | |
| 404 | ErrorBody (application/json) |
POST /v1/jobs/{id}/cancel
Cancels a job. Pages already extracted stay billed and available.
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | JobView (application/json) | |
| 404 | ErrorBody (application/json) |
GET /v1/jobs/{id}/results
A page of a job's results (available while it runs).
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | JobResults (application/json) | |
| 404 | ErrorBody (application/json) |
POST /v1/research
Starts a research job. Poll GET /v1/jobs/{id}; progress events and the final report arrive in GET /v1/jobs/{id}/results, and the report and sources are in the job's summary.
Requires an API key.
Request body: ResearchRequest
| Status | Description | Body |
|---|---|---|
| 202 | JobView (application/json) | |
| 400 | ErrorBody (application/json) |
POST /v1/search
Searches the web. Billed per query.
Requires an API key.
Request body: SearchRequest
| Status | Description | Body |
|---|---|---|
| 200 | SearchResponse (application/json) | |
| 400 | ErrorBody (application/json) | |
| 402 | ErrorBody (application/json) | |
| 429 | ErrorBody (application/json) | |
| 502 | ErrorBody (application/json) |
Embeddings
Text embeddings (OpenAI-compatible) and reranking.
POST /v1/embeddings
Creates embeddings for one or more texts.
Requires an API key.
Request body: EmbeddingRequest
| Status | Description | Body |
|---|---|---|
| 200 | EmbeddingResponse (application/json) | |
| 400 | ErrorBody (application/json) | |
| 401 | ErrorBody (application/json) | |
| 402 | Insufficient credits | ErrorBody (application/json) |
| 404 | ErrorBody (application/json) | |
| 429 | ErrorBody (application/json) |
POST /v1/rerank
Orders documents by relevance to the query.
Requires an API key.
Request body: RerankRequest
| Status | Description | Body |
|---|---|---|
| 200 | RerankResponse (application/json) | |
| 400 | ErrorBody (application/json) | |
| 402 | ErrorBody (application/json) | |
| 429 | ErrorBody (application/json) |
Documents
File uploads and document parsing, billed per page.
GET /v1/files
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | FileList (application/json) |
POST /v1/files
Uploads a document (the request body is the file). Kept for 30 days.
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 201 | FileView (application/json) | |
| 400 | ErrorBody (application/json) | |
| 413 | ErrorBody (application/json) |
GET /v1/files/{id}
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | FileView (application/json) | |
| 404 | ErrorBody (application/json) |
DELETE /v1/files/{id}
Deletes a file and its content.
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 204 | ||
| 404 | ErrorBody (application/json) |
POST /v1/parse
Parses a document into Markdown, pages and elements. Billed per page.
Requires an API key.
Request body: ParseRequest
| Status | Description | Body |
|---|---|---|
| 200 | ParseResponse (application/json) | |
| 400 | ErrorBody (application/json) | |
| 402 | ErrorBody (application/json) | |
| 503 | ErrorBody (application/json) |
Account
Keys and account information.
GET /v1/key
Returns details and effective limits for the calling API key.
Requires an API key.
| Status | Description | Body |
|---|---|---|
| 200 | KeyInfo (application/json) | |
| 401 | ErrorBody (application/json) | |
| 429 | ErrorBody (application/json) |
Schemas
BillingOverview
| Field | Type | Description |
|---|---|---|
balance_usd | string | |
held_usd | string | |
low_balance_threshold_usd | string |
CapabilityStatus
| Field | Type | Description |
|---|---|---|
models_available | integer | Models with at least one healthy provider, out of all models. |
models_total | integer | |
status | Level |
ChatChunk
| Field | Type | Description |
|---|---|---|
choices | ChunkChoice[] | |
created | integer | |
id | string | |
model | string | |
object | string | |
provider? | string | |
usage? | ChatUsage |
ChatMessage
| Field | Type | Description |
|---|---|---|
content? | MessageContent | |
name? | string | |
role | Role | |
tool_call_id? | string | |
tool_calls? | ToolCall[] |
ChatRequest
| Field | Type | Description |
|---|---|---|
max_completion_tokens? | integer | |
max_tokens? | integer | |
messages | ChatMessage[] | |
model | string | A Usefully model ID such as anthropic/claude-opus-5-5, or a bare name like gpt-5-mini when it identifies exactly one model. |
n? | integer | |
parallel_tool_calls? | boolean | |
provider? | ProviderPreferences | |
reasoning_effort? | string | low, medium, high (and provider-specific levels). |
response_format? | object | |
stop? | Stop | |
stream? | boolean | |
stream_options? | StreamOptions | |
temperature? | number | |
tool_choice? | object | "auto", "none", "required" or {"type":"function","function":{"name":…}}. |
tools? | Tool[] | |
top_p? | number | |
user? | string |
ChatResponse
| Field | Type | Description |
|---|---|---|
choices | Choice[] | |
created | integer | |
id | string | |
model | string | |
object | string | |
provider? | string | The provider that served the request. |
usage? | ChatUsage |
ChatUsage
| Field | Type | Description |
|---|---|---|
completion_tokens | integer | |
completion_tokens_details? | CompletionTokensDetails | |
prompt_tokens | integer | |
prompt_tokens_details? | PromptTokensDetails | |
total_tokens | integer |
CheckoutRequest
| Field | Type | Description |
|---|---|---|
amount? | number | Credits to buy, in currency (default USD). Limits are about $5 to $10,000 in each currency; see GET /v1/currencies. A 3.5% fee is added. |
amount_usd? | number | Deprecated: same as amount with currency: "USD". |
currency? | string | USD (default), INR or EUR. |
CheckoutResponse
| Field | Type | Description |
|---|---|---|
amount | string | |
checkout_url | string | Send the customer here to pay. |
credit_usd | string | The credits this buys, in USD. |
currency | string | The currency charged, and the amounts in it (decimal strings). |
fee | string | |
fee_usd | string | |
session_id | string | |
total | string | |
total_usd | string |
Choice
| Field | Type | Description |
|---|---|---|
finish_reason? | string | |
index | integer | |
message | ResponseMessage |
ChunkChoice
| Field | Type | Description |
|---|---|---|
delta | Delta | |
finish_reason? | string | |
index | integer |
CompletionTokensDetails
| Field | Type | Description |
|---|---|---|
reasoning_tokens? | integer |
ContentPart
A content part. Types we don't translate (audio, files, …) are kept verbatim for OpenAI-compatible providers.
Type: KnownPart | object
CrawlRequest
| Field | Type | Description |
|---|---|---|
exclude_paths? | string[] | Never crawl paths matching these. |
include_paths? | string[] | Only crawl paths matching one of these (* matches anything), e.g. /docs/*. |
max_chars? | integer | Truncate each page's content (default 100,000 characters). |
max_depth? | integer | Link depth from the start page, 0–5 (default 2). |
max_pages? | integer | Pages to crawl, 1–1,000 (default 50). |
model? | string | |
provider? | ProviderPreferences | |
url | string | The start page. Only pages on the same host are crawled. |
use_sitemap? | boolean | Also start from the site's /sitemap.xml (default true). |
CreateSession
| Field | Type | Description |
|---|---|---|
block_ads? | boolean | Block ads (default true). |
region? | string | us-west-2, us-east-1, eu-central-1 or ap-southeast-1. |
timeout_minutes? | integer | Session length limit in minutes, 1–30 (default 5). Billing stops earlier if you release the session. |
viewport? | Viewport |
CurrencyList
| Field | Type | Description |
|---|---|---|
base | string | Credits and per-request prices are in this currency. |
data | CurrencyView[] | |
object | string |
CurrencyView
| Field | Type | Description |
|---|---|---|
code | string | |
max | integer | |
min | integer | |
name | string | |
per_usd | number | Units of this currency per 1 USD (credits are USD). |
presets | integer[] | Suggested purchase amounts, in whole units. |
purchasable | boolean | Whether credits can be bought in this currency here. |
symbol | string |
Delta
| Field | Type | Description |
|---|---|---|
content? | string | |
refusal? | string | |
role? | Role | |
tool_calls? | ToolCallDelta[] |
EmbeddingData
| Field | Type | Description |
|---|---|---|
embedding | EmbeddingVector | |
index | integer | |
object | string |
EmbeddingInput
Type: string | string[] | object
EmbeddingRequest
| Field | Type | Description |
|---|---|---|
dimensions? | integer | Output size, for models that support shortening. |
encoding_format? | string | float (default) or base64 (little-endian f32 bytes). |
input | EmbeddingInput | |
input_type? | string | query or document, for models that embed them differently (Voyage, Cohere). Ignored by models that don't. |
model | string | |
provider? | ProviderPreferences | |
user? | string |
EmbeddingResponse
| Field | Type | Description |
|---|---|---|
data | EmbeddingData[] | |
model | string | |
object | string | |
provider? | string | |
usage | EmbeddingUsage |
EmbeddingUsage
| Field | Type | Description |
|---|---|---|
prompt_tokens | integer | |
total_tokens | integer |
EmbeddingVector
Type: number[] | string
ErrorBody
| Field | Type | Description |
|---|---|---|
error | ErrorDetail |
ErrorDetail
| Field | Type | Description |
|---|---|---|
code | string | Stable machine-readable code, e.g. invalid_api_key. |
message | string | Human-readable explanation. Safe to show end users. |
provider? | string | Upstream provider involved, when the error came from one. |
request_id? | string | |
type | ErrorType |
ErrorType
Type: invalid_request, authentication, permission_denied, not_found, insufficient_credits, rate_limited, provider_error, timeout, content_filtered, internal, service_unavailable
ExtractError
| Field | Type | Description |
|---|---|---|
code | string | |
message | string |
ExtractRequest
| Field | Type | Description |
|---|---|---|
include_links? | boolean | Also return the absolute links found on each page. |
max_chars? | integer | Truncate each page's content to this many characters (default 100,000). |
model? | string | Extraction model. Default: usefully/extract. |
provider? | ProviderPreferences | |
urls | string[] | 1–10 http(s) URLs. |
ExtractResponse
| Field | Type | Description |
|---|---|---|
model | string | |
object | string | Always extract.results. |
results | ExtractResult[] | One entry per requested URL, in order. |
usage | ExtractUsage |
ExtractResult
| Field | Type | Description |
|---|---|---|
error? | ExtractError | |
page? | ExtractedPage | |
provider? | string | Which provider fetched it. |
status | string | ok or failed. |
url | string |
ExtractUsage
| Field | Type | Description |
|---|---|---|
cost_usd | string | |
pages | integer | Pages extracted (and billed). |
ExtractedPage
| Field | Type | Description |
|---|---|---|
content | string | The page's main content as Markdown. |
description? | string | |
final_url | string | Where the content came from, after redirects. |
language? | string | |
links? | string[] | Absolute http(s) links found on the page (when requested). |
published_at? | string | |
site_name? | string | |
title | string | |
url | string | The URL that was requested. |
FileList
| Field | Type | Description |
|---|---|---|
data | FileView[] | |
object | string |
FileView
| Field | Type | Description |
|---|---|---|
bytes | integer | |
content_type | string | |
created_at | string | |
expires_at | string | |
filename | string | |
id | string | |
object | string | Always file. |
sha256 | string |
Freshness
Type: day, week, month, year
FunctionCall
| Field | Type | Description |
|---|---|---|
arguments | string | JSON-encoded arguments. |
name | string |
FunctionDef
| Field | Type | Description |
|---|---|---|
description? | string | |
name | string | |
parameters? | object | JSON Schema for the arguments. |
strict? | boolean |
FunctionDelta
| Field | Type | Description |
|---|---|---|
arguments? | string | |
name? | string |
ImageUrl
| Field | Type | Description |
|---|---|---|
detail? | string | |
url | string | An https:// URL or a data:<mime>;base64,<data> URL. |
JobErrorView
| Field | Type | Description |
|---|---|---|
code | string | |
message | string |
JobList
| Field | Type | Description |
|---|---|---|
data | JobView[] | |
object | string |
JobProgress
| Field | Type | Description |
|---|---|---|
completed | integer | |
failed | integer | |
total | integer |
JobResults
| Field | Type | Description |
|---|---|---|
data | object[] | Items in discovery order. For crawls: {url, status, page?, error?}. |
next_after? | integer | Pass as after for the next page; absent when there are no more yet. |
object | string |
JobView
| Field | Type | Description |
|---|---|---|
completed_at? | string | |
created_at | string | |
error? | JobErrorView | |
id | string | |
kind | string | crawl. |
object | string | Always job. |
progress | JobProgress | |
status | string | queued, running, succeeded, failed or cancelled. |
summary | object | Totals when finished, e.g. {"pages": 42, "failed": 1, "cost_usd": "0.042"}. |
KeyInfo
| Field | Type | Description |
|---|---|---|
environment | string | live or test. |
key_id | string | |
limits | KeyLimits | |
org_id | string | |
project_id | string | |
scopes | string[] | Capabilities this key may use. Empty means all. |
KeyLimits
| Field | Type | Description |
|---|---|---|
daily_spend_limit_micros? | integer | Daily spend cap in micro-dollars, if set. |
requests_per_minute | integer | Effective requests per minute (the lower of key and plan limits). |
tokens_per_minute | integer | Effective tokens per minute. |
KnownPart
Type: object | object
Level
Type: operational, degraded, down
MaxPrice
| Field | Type | Description |
|---|---|---|
input? | number | |
output? | number |
MessageContent
Type: string | ContentPart[]
Model
| Field | Type | Description |
|---|---|---|
capabilities | ModelCapabilities | |
context_length | integer | |
created | integer | Unix seconds. |
description? | string | |
id | string | <author>/<name>, e.g. openai/gpt-5-mini. Bare names also work in requests. |
name | string | |
object | string | Always model. |
owned_by | string | |
pricing | ModelPricing | |
providers | string[] | Providers that can serve this model, for routing preferences. |
type | string | chat, embedding or search. |
ModelCapabilities
| Field | Type | Description |
|---|---|---|
json_mode | boolean | |
tools | boolean | |
vision | boolean |
ModelList
Lists available models with capabilities and per-million-token prices. No API key needed. The model catalog (OpenAI-compatible list with Usefully extensions).
| Field | Type | Description |
|---|---|---|
data | Model[] | |
object | string | Always list. |
ModelPricing
Prices in USD as decimal strings (exact; never floats).
| Field | Type | Description |
|---|---|---|
currency | string | Always USD. |
input_per_million_tokens | string | |
output_per_million_tokens | string | |
per_thousand_requests? | string | For models priced per request (search). |
ParseRequest
| Field | Type | Description |
|---|---|---|
file_id? | string | A file from POST /v1/files. Give this or url. |
mode? | string | fast (default) or premium (complex layouts and scans). |
url? | string | A public URL of a document. Give this or file_id. |
ParseResponse
| Field | Type | Description |
|---|---|---|
elements | object[] | Structure: {type: heading|paragraph|table|list, page, text, level?}. |
file_id | string | |
markdown | string | The whole document as Markdown. |
metadata | object | |
model | string | |
object | string | Always parse.result. |
pages | object[] | Per-page Markdown ({number, markdown}). |
usage | ParseUsage |
ParseUsage
| Field | Type | Description |
|---|---|---|
cost_usd | string | |
pages | integer |
PromptTokensDetails
| Field | Type | Description |
|---|---|---|
cached_tokens? | integer |
ProviderPreferences
| Field | Type | Description |
|---|---|---|
allow_fallbacks? | boolean | |
data_policy? | string | zdr, no_training or any. |
ignore? | string[] | Never use these providers. |
max_price? | MaxPrice | |
only? | string[] | Only use these providers. |
order? | string[] | Provider IDs to try first, in order. |
sort? | string | price, latency or throughput. Default: registry priority. |
ProviderStatus
| Field | Type | Description |
|---|---|---|
error_rate? | number | Share of recent requests that failed (0–1), when there's traffic. |
latency_ms? | number | Moving average latency of successful requests. |
status | Level |
Readiness
| Field | Type | Description |
|---|---|---|
database | string | |
redis | string | |
status | string | ok or unavailable. |
RerankRequest
| Field | Type | Description |
|---|---|---|
documents | string[] | 1–1,000 texts. |
model | string | A model with type rerank, e.g. cohere/rerank-v3.5. |
provider? | ProviderPreferences | |
query | string | |
return_documents? | boolean | Include each document's text in the results. |
top_n? | integer | How many to return, best first (default: all). |
RerankResponse
| Field | Type | Description |
|---|---|---|
model | string | |
object | string | Always rerank. |
provider | string | |
results | RerankResult[] | Best first. |
usage | RerankUsage |
RerankResult
| Field | Type | Description |
|---|---|---|
document? | string | |
index | integer | Position in the request's documents. |
relevance_score | number |
RerankUsage
| Field | Type | Description |
|---|---|---|
cost_usd | string | |
search_units | integer | |
total_tokens | integer |
ResearchRequest
| Field | Type | Description |
|---|---|---|
depth? | string | quick, standard (default) or deep. |
max_cost_usd? | number | Stop spending past this (default $1, at most $20). The report is still written. |
model? | string | The model that plans, reflects and writes (default anthropic/claude-sonnet-5-5). |
question | string | The question to research. |
ResponseMessage
| Field | Type | Description |
|---|---|---|
content? | string | |
refusal? | string | |
role | Role | |
tool_calls? | ToolCall[] |
Role
Type: system, developer, user, assistant, tool
RunRequest
| Field | Type | Description |
|---|---|---|
code | string | The code to run (≤ 100 KB). |
env_vars? | object | Environment variables for the code. |
language? | string | python (default), javascript, typescript, r, java or bash. |
timeout_secs? | integer | Execution limit in seconds, 1–300 (default 60). |
RunResponse
| Field | Type | Description |
|---|---|---|
duration_ms | integer | |
error? | object | {name, value, traceback} if the code raised or timed out. |
object | string | Always sandbox.run. |
results | object[] | Rich outputs (the last expression's value, charts, images as base64 PNG, HTML…). |
stderr | string | |
stdout | string | |
truncated | boolean | Output beyond 100,000 characters per stream (or 20 results) was cut. |
usage | RunUsage |
RunUsage
| Field | Type | Description |
|---|---|---|
cost_usd | string | |
seconds | integer | Sandbox seconds billed. |
SearchRequest
| Field | Type | Description |
|---|---|---|
exclude_domains? | string[] | |
freshness? | Freshness | |
include_content? | boolean | Return each page's text (up to max_content_chars). |
include_domains? | string[] | |
max_content_chars? | integer | |
model? | string | Search model. Default: usefully/web-search. |
num_results? | integer | 1–20, default 10. |
provider? | ProviderPreferences | |
query | string |
SearchResponse
| Field | Type | Description |
|---|---|---|
model | string | |
object | string | |
provider | string | The engine that answered. |
query | string | |
results | SearchResult[] | |
usage | SearchUsage |
SearchResult
| Field | Type | Description |
|---|---|---|
content? | string | Page text, when include_content was requested. |
published_at? | string | RFC 3339, when the engine knows it. |
score? | number | |
snippet | string | A short excerpt (≤300 characters). |
title | string | |
url | string |
SearchUsage
| Field | Type | Description |
|---|---|---|
cost_usd | string | |
requests | integer |
SessionList
| Field | Type | Description |
|---|---|---|
data | SessionView[] | |
object | string |
SessionView
| Field | Type | Description |
|---|---|---|
billed_minutes? | integer | Minutes billed, once ended. |
connect_url? | string | CDP WebSocket URL (only when the session is created). |
cost_usd? | string | |
created_at | string | |
ended_at? | string | |
expires_at | string | |
id | string | |
object | string | Always browser.session. |
status | string | running, completed or expired. |
timeout_minutes | integer |
SettingsUpdate
Unknown fields are refused, so a misspelt or retired setting (such as the old auto_topup_* fields) fails loudly instead of being ignored.
| Field | Type | Description |
|---|---|---|
low_balance_threshold_usd? | number |
Status
| Field | Type | Description |
|---|---|---|
capabilities | object | chat, embedding, search. |
providers | object | |
status | Level | Worst capability level. |
updated_at | string |
Stop
Type: string | string[]
StreamOptions
| Field | Type | Description |
|---|---|---|
include_usage? | boolean |
Tool
| Field | Type | Description |
|---|---|---|
function | FunctionDef | |
type | string |
ToolCall
| Field | Type | Description |
|---|---|---|
function | FunctionCall | |
id | string | |
type | string |
ToolCallDelta
| Field | Type | Description |
|---|---|---|
function? | FunctionDelta | |
id? | string | |
index | integer | |
type? | string |
Viewport
| Field | Type | Description |
|---|---|---|
height | integer | |
width | integer |