LLM API Reference (V1)
Models
Catalog
List modelsgetRetrieve modelget
Chat
Completions
Create chat completionpost
Completions
Text
Create text completionpost
Embeddings
Vectors
Create embeddingspost
Images
Generations
Create imagepost
Edits
Edit imagepost
Audio
Speech
Create speechpost
Transcriptions
Create transcriptionpost
Translations
Create translationpost
Moderations
Checks
Create moderationpost
Files
Uploads
List filesgetUpload filepostRetrieve filegetDelete filedelete
Batches
Jobs
List batchesgetCreate batchpostRetrieve batchgetCancel batchpost
Rerank
Rankings
Create rerankpost
Health
Liveliness
Check livelinessget
Readiness
Check readinessget

LLM API Reference (V1)

Updated on July 14, 2026

Tradeics LLM is an OpenAI-compatible inference proxy for chat, embeddings, media, and admin-style utility routes.

  • Proxy root: https://llm.tradeics.example

  • OpenAI SDK base_url: https://llm.tradeics.example/v1

Scroll an endpoint to load request and response examples in the right panel. Multi-language SDK samples live in Call the LLM.

Authenticate with:

Authorization: Bearer <TRADEICS_LLM_API_KEY>

or:

x-tradeics-llm-api-key: <TRADEICS_LLM_API_KEY>

Try it with your API client

Postman Insomnia Bruno Hoppscotch OpenAPI HTTPie

Download the ⬇️ Postman collection or OpenAPI 3.1. Live proxy OpenAPI may also be at https://llm.tradeics.example/openapi.json. See API clients.

Catalogin Models

List models

GET
/v1/models

Lists model ids you can pass to chat, embeddings, images, and related routes.

  • GEThttps://llm.tradeics.example/v1/models
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Retrieve model

GET
/v1/models/{model_id}

Returns metadata for one model id.

URI Parameters
model_id
stringRequired

Model id from the catalog

  • GEThttps://llm.tradeics.example/v1/models/model_id
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Completionsin Chat

Create chat completion

POST
/v1/chat/completions

Creates a chat completion from a list of messages. Set stream: true for SSE token streaming.

Request Body
model
stringRequired

Model id from GET /v1/models

messages
arrayRequired

Conversation turns (system / user / assistant)

temperature
numberOptional

Sampling temperature

max_tokens
numberOptional

Max tokens to generate

top_p
numberOptional

Nucleus sampling

response_format (object, optional) - e.g. `{ "type": "json_object" }`
string
tools
arrayOptional

Tool / function definitions when enabled

stream
booleanOptional

Stream tokens when true

  • POSThttps://llm.tradeics.example/v1/chat/completions
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Textin Completions

Create text completion

POST
/v1/completions

Creates a completion for a raw prompt string.

Request Body
model
stringRequired

Completion-capable model id

prompt
stringRequired

Input prompt

max_tokens
numberOptional

Max tokens to generate

temperature
numberOptional

Sampling temperature

stop
arrayOptional

Stop sequences

  • POSThttps://llm.tradeics.example/v1/completions
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Vectorsin Embeddings

Create embeddings

POST
/v1/embeddings

Creates embeddings for one or more input strings (or token arrays when the model supports it).

Request Body
model
stringRequired

Embedding model id

input
arrayRequired

Texts to embed

encoding_format
stringOptional

float (default) or base64

dimensions
numberOptional

Output dimensions when the model supports truncation

  • POSThttps://llm.tradeics.example/v1/embeddings
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Generationsin Images

Create image

POST
/v1/images/generations

Generates one or more images from a text prompt.

Request Body
model
stringRequired

Image model id

prompt
stringRequired

Image description

n
numberOptional

Number of images (default 1)

size
stringOptional

e.g. 1024x1024

response_format (string, optional) - `url` or `b64_json`
string
  • POSThttps://llm.tradeics.example/v1/images/generations
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Editsin Images

Edit image

POST
/v1/images/edits

Edits an image with a prompt and optional mask (multipart when uploading files).

Request Body
model
stringRequired

Image edit model id

prompt
stringRequired

Edit instruction

image
stringRequired

Source image reference / upload field

mask
stringOptional

Mask reference / upload field

n
numberOptional

Number of images

  • POSThttps://llm.tradeics.example/v1/images/edits
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Speechin Audio

Create speech

POST
/v1/audio/speech

Turns text into audio (MP3 / other formats depending on model).

Request Body
model
stringRequired

TTS model id

input
stringRequired

Text to speak

voice
stringRequired

Voice id (e.g. alloy)

response_format
stringOptional

mp3, wav, opus

speed
numberOptional

Playback speed

  • POSThttps://llm.tradeics.example/v1/audio/speech
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Transcriptionsin Audio

Create transcription

POST
/v1/audio/transcriptions

Transcribes audio to text (multipart upload in clients; JSON example for proxy-compatible references).

Request Body
model
stringRequired

STT model id

file
stringRequired

Audio file field / reference

language
stringOptional

BCP 47 language hint

response_format (string, optional) - `json`, `text`, `verbose_json`
string
  • POSThttps://llm.tradeics.example/v1/audio/transcriptions
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Translationsin Audio

Create translation

POST
/v1/audio/translations

Transcribes audio and translates into English (OpenAI-compatible translation route).

Request Body
model
stringRequired

STT / translation model id

file
stringRequired

Audio file field / reference

response_format
stringOptional

json, text

  • POSThttps://llm.tradeics.example/v1/audio/translations
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Checksin Moderations

Create moderation

POST
/v1/moderations

Classifies whether input violates content policies.

Request Body
model
stringOptional

Moderation model id

input
stringRequired

Text to moderate

  • POSThttps://llm.tradeics.example/v1/moderations
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Uploadsin Files

List files

GET
/v1/files

Lists files owned by your organization / key.

  • GEThttps://llm.tradeics.example/v1/files
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Upload file

POST
/v1/files

Uploads a file for a stated purpose (batch, fine-tune, assistants, …).

Request Body
file
stringRequired

Multipart file field

purpose
stringRequired

Intended use

  • POSThttps://llm.tradeics.example/v1/files
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Retrieve file

GET
/v1/files/{file_id}

Returns metadata for one file.

URI Parameters
file_id
stringRequired

File id

  • GEThttps://llm.tradeics.example/v1/files/file_id
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Delete file

DELETE
/v1/files/{file_id}

Deletes a file.

URI Parameters
file_id
stringRequired

File id

  • DELETEhttps://llm.tradeics.example/v1/files/file_id
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Jobsin Batches

List batches

GET
/v1/batches

Lists batch jobs.

  • GEThttps://llm.tradeics.example/v1/batches
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Create batch

POST
/v1/batches

Creates a batch job from an uploaded .jsonl input file.

Request Body
input_file_id
stringRequired

File id with purpose batch

endpoint
stringRequired

Target route, e.g. /v1/chat/completions

completion_window
stringRequired

e.g. 24h

metadata
objectOptional

Free-form labels

  • POSThttps://llm.tradeics.example/v1/batches
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Retrieve batch

GET
/v1/batches/{batch_id}

Returns one batch job.

URI Parameters
batch_id
stringRequired

Batch id

  • GEThttps://llm.tradeics.example/v1/batches/batch_id
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Cancel batch

POST
/v1/batches/{batch_id}/cancel

Cancels a batch that is not yet completed.

URI Parameters
batch_id
stringRequired

Batch id

  • POSThttps://llm.tradeics.example/v1/batches/batch_id/cancel
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Rankingsin Rerank

Create rerank

POST
/v1/rerank

Scores documents against a query and returns a ranked list.

Request Body
model
stringRequired

Rerank model id

query
stringRequired

Search query

documents
arrayRequired

Candidate documents

top_n
numberOptional

Truncate results

  • POSThttps://llm.tradeics.example/v1/rerank
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Livelinessin Health

Check liveliness

GET
/health/liveliness

Returns a simple alive signal. No API key required.

  • GEThttps://llm.tradeics.example/health/liveliness
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)

Readinessin Health

Check readiness

GET
/health/readiness

Returns whether the proxy is ready to accept inference traffic (dependencies up).

  • GEThttps://llm.tradeics.example/health/readiness
  • Tiersapp
HTTP
Request
(loading)
Response
(loading)