OpenAI-Compatible API

This spec defines Lemonade's implementation of the OpenAI API.

Method	Endpoint	Description	Modality
`POST`	`/v1/chat/completions`	Chat Completions	messages -> completion
`POST`	`/v1/completions`	Text Completions	prompt -> completion
`POST`	`/v1/embeddings`	Embeddings	text -> vector representations
`POST`	`/v1/responses`	Responses API	prompt/messages -> event
`POST`	`/v1/audio/transcriptions`	Audio Transcription	audio file -> text
`POST`	`/v1/audio/speech`	Text to speech	text -> audio
`WS`	`/realtime`	Realtime Audio Transcription, OpenAI SDK compatible	streaming audio -> text
`POST`	`/v1/images/generations`	Image Generation	prompt -> image
`POST`	`/v1/images/edits`	Image Editing	image + prompt -> edited image
`POST`	`/v1/images/variations`	Image Variations	image -> varied image
`POST`	`/v1/images/upscale`	Image Upscaling	image + ESRGAN model -> upscaled image
`GET`	`/v1/models`	List models available locally	n/a
`GET`	`/v1/models/{model_id}`	Retrieve a specific model by ID	n/a

`POST /v1/chat/completions`

Chat Completions API. You provide a list of messages and receive a completion. This API will also load the model if it is not already loaded.

Parameters

Parameter	Required	Description
`messages`	Yes	Array of messages in the conversation. Each message should have a `role` ("user" or "assistant") and `content` (the message text).
`model`	Yes	The model to use for the completion.
`stream`	No	If true, tokens will be sent as they are generated. If false, the response will be sent as a single message once complete. Defaults to false.
`stop`	No	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. Can be a string or an array of strings.
`logprobs`	No	Include log probabilities of the output tokens. If true, returns the log probability of each output token. Defaults to false.
`temperature`	No	What sampling temperature to use.
`repeat_penalty`	No	Number between 1.0 and 2.0. 1.0 means no penalty. Higher values discourage repetition.
`top_k`	No	Integer that controls the number of top tokens to consider during sampling.
`top_p`	No	Float between 0.0 and 1.0 that controls the cumulative probability of top tokens to consider during nucleus sampling.
`tools`	No	A list of tools the model may call.
`max_tokens`	No	An upper bound for the number of tokens that can be generated for a completion. Mutually exclusive with `max_completion_tokens`. This value is now deprecated by OpenAI in favor of `max_completion_tokens`
`max_completion_tokens`	No	An upper bound for the number of tokens that can be generated for a completion. Mutually exclusive with `max_tokens`.

Example request

=== "PowerShell"

```powershell
Invoke-WebRequest `
  -Uri "http://localhost:13305/v1/chat/completions" `
  -Method POST `
  -Headers @{ "Content-Type" = "application/json" } `
  -Body '{
    "model": "Qwen3-0.6B-GGUF",
    "messages": [
      {
        "role": "user",
        "content": "What is the population of Paris?"
      }
    ],
    "stream": false
  }'
```

=== "Bash"

```bash
curl -X POST http://localhost:13305/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
        "model": "Qwen3-0.6B-GGUF",
        "messages": [
          {"role": "user", "content": "What is the population of Paris?"}
        ],
        "stream": false
      }'
```

Image understanding input format (OpenAI-compatible)

To send images to chat/completions, pass a messages[*].content array that mixes text and image_url items. The image can be provided as a base64 data URL (for example, from FileReader.readAsDataURL(...) in web apps).

curl -X POST http://localhost:13305/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
        "model": "Qwen2.5-VL-7B-Instruct",
        "messages": [
          {
            "role": "user",
            "content": [
              {"type": "text", "text": "What is in this image?"},
              {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD..."}}
            ]
          }
        ],
        "stream": false
      }'

Response format

=== "Non-streaming responses"

```json
{
  "id": "0",
  "object": "chat.completion",
  "created": 1742927481,
  "model": "Qwen3-0.6B-GGUF",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Paris has a population of approximately 2.2 million people in the city proper."
    },
    "finish_reason": "stop"
  }]
}
```

=== "Streaming responses" For streaming responses, the API returns a stream of server-sent events (however, Open AI recommends using their streaming libraries for parsing streaming responses):

```json
{
  "id": "0",
  "object": "chat.completion.chunk",
  "created": 1742927481,
  "model": "Qwen3-0.6B-GGUF",
  "choices": [{
    "index": 0,
    "delta": {
      "role": "assistant",
      "content": "Paris"
    }
  }]
}
```

`POST /v1/completions`

Text Completions API. You provide a prompt and receive a completion. This API will also load the model if it is not already loaded.

Parameters

Parameter	Required	Description
`prompt`	Yes	The prompt to use for the completion.
`model`	Yes	The model to use for the completion.
`stream`	No	If true, tokens will be sent as they are generated. If false, the response will be sent as a single message once complete. Defaults to false.
`stop`	No	Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. Can be a string or an array of strings.
`echo`	No	Echo back the prompt in addition to the completion. Available on non-streaming mode.
`logprobs`	No	Include log probabilities of the output tokens. If true, returns the log probability of each output token. Defaults to false. Only available when `stream=False`.
`temperature`	No	What sampling temperature to use.
`repeat_penalty`	No	Number between 1.0 and 2.0. 1.0 means no penalty. Higher values discourage repetition.
`top_k`	No	Integer that controls the number of top tokens to consider during sampling.
`top_p`	No	Float between 0.0 and 1.0 that controls the cumulative probability of top tokens to consider during nucleus sampling.
`max_tokens`	No	An upper bound for the number of tokens that can be generated for a completion, including input tokens.

Example request

=== "PowerShell"

```powershell
Invoke-WebRequest -Uri "http://localhost:13305/v1/completions" `
  -Method POST `
  -Headers @{ "Content-Type" = "application/json" } `
  -Body '{
    "model": "Qwen3-0.6B-GGUF",
    "prompt": "What is the population of Paris?",
    "stream": false
  }'
```

=== "Bash"

```bash
curl -X POST http://localhost:13305/v1/completions \
  -H "Content-Type: application/json" \
  -d '{
        "model": "Qwen3-0.6B-GGUF",
        "prompt": "What is the population of Paris?",
        "stream": false
      }'
```

Response format

The following format is used for both streaming and non-streaming responses:

{
  "id": "0",
  "object": "text_completion",
  "created": 1742927481,
  "model": "Qwen3-0.6B-GGUF",
  "choices": [{
    "index": 0,
    "text": "Paris has a population of approximately 2.2 million people in the city proper.",
    "finish_reason": "stop"
  }],
}

`POST /v1/embeddings`

Embeddings API. You provide input text and receive vector representations (embeddings) that can be used for semantic search, clustering, and similarity comparisons. This API will also load the model if it is not already loaded.

Note: This endpoint is only available for models using the llamacpp or flm recipes. ONNX models (OGA recipes) do not support embeddings.

Parameters

Parameter	Required	Description
`input`	Yes	The input text or array of texts to embed. Can be a string or an array of strings.
`model`	Yes	The model to use for generating embeddings.
`encoding_format`	No	The format to return embeddings in. Supported values: `"float"` (default), `"base64"`.

Example request

=== "PowerShell"

```powershell
Invoke-WebRequest `
  -Uri "http://localhost:13305/v1/embeddings" `
  -Method POST `
  -Headers @{ "Content-Type" = "application/json" } `
  -Body '{
    "model": "nomic-embed-text-v1-GGUF",
    "input": ["Hello, world!", "How are you?"],
    "encoding_format": "float"
  }'
```

=== "Bash"

```bash
curl -X POST http://localhost:13305/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
        "model": "nomic-embed-text-v1-GGUF",
        "input": ["Hello, world!", "How are you?"],
        "encoding_format": "float"
      }'
```

Response format

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0234, -0.0567, 0.0891, ...]
    },
    {
      "object": "embedding",
      "index": 1,
      "embedding": [0.0456, -0.0678, 0.1234, ...]
    }
  ],
  "model": "nomic-embed-text-v1-GGUF",
  "usage": {
    "prompt_tokens": 12,
    "total_tokens": 12
  }
}

Field Descriptions:

object - Type of response object, always "list"
data - Array of embedding objects
- object - Type of embedding object, always "embedding"
- index - Index position of the input text in the request
- embedding - Vector representation as an array of floats
model - Model identifier used to generate the embeddings
usage - Token usage statistics
- prompt_tokens - Number of tokens in the input
- total_tokens - Total tokens processed

`POST /v1/responses`

Responses API. You provide an input and receive a response. This API will also load the model if it is not already loaded.

Parameters

Parameter	Required	Description
`input`	Yes	A list of dictionaries or a string input for the model to respond to.
`model`	Yes	The model to use for the response.
`max_output_tokens`	No	The maximum number of output tokens to generate.
`temperature`	No	What sampling temperature to use.
`repeat_penalty`	No	Number between 1.0 and 2.0. 1.0 means no penalty. Higher values discourage repetition.
`top_k`	No	Integer that controls the number of top tokens to consider during sampling.
`top_p`	No	Float between 0.0 and 1.0 that controls the cumulative probability of top tokens to consider during nucleus sampling.
`stream`	No	If true, tokens will be sent as they are generated. If false, the response will be sent as a single message once complete. Defaults to false.

Streaming Events

The Responses API uses semantic events for streaming. Each event is typed with a predefined schema, so you can listen for events you care about. Our initial implementation only offers support to:

response.created
response.output_text.delta
response.completed

For a full list of event types, see the API reference for streaming.

Example request

=== "PowerShell"

```powershell
Invoke-WebRequest -Uri "http://localhost:13305/v1/responses" `
  -Method POST `
  -Headers @{ "Content-Type" = "application/json" } `
  -Body '{
    "model": "Llama-3.2-1B-Instruct-Hybrid",
    "input": "What is the population of Paris?",
    "stream": false
  }'
```

=== "Bash"

```bash
curl -X POST http://localhost:13305/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
        "model": "Llama-3.2-1B-Instruct-Hybrid",
        "input": "What is the population of Paris?",
        "stream": false
      }'
```

Response format

=== "Non-streaming responses"

```json
{
  "id": "0",
  "created_at": 1746225832.0,
  "model": "Llama-3.2-1B-Instruct-Hybrid",
  "object": "response",
  "output": [{
    "id": "0",
    "content": [{
      "annotations": [],
      "text": "Paris has a population of approximately 2.2 million people in the city proper."
    }]
  }]
}
```

=== "Streaming Responses" For streaming responses, the API returns a series of events. Refer to OpenAI streaming guide for details.

`POST /v1/audio/transcriptions`

Audio Transcription API. You provide an audio file and receive a text transcription. This API will also load the model if it is not already loaded.

Note: This endpoint uses whisper.cpp as the backend. Whisper models are automatically downloaded when first used.

Limitations: Only wav audio format and json response format are currently supported.

Parameters

Parameter	Required	Description
`file`	Yes	The audio file to transcribe. Supported formats: wav.
`model`	Yes	The Whisper model to use for transcription (e.g., `Whisper-Tiny`, `Whisper-Base`, `Whisper-Small`).
`language`	No	The language of the audio (ISO 639-1 code, e.g., `en`, `es`, `fr`). If not specified, Whisper will auto-detect the language.
`response_format`	No	The format of the response. Currently only `json` is supported.

Example request

=== "Windows"

```bash
curl -X POST http://localhost:13305/v1/audio/transcriptions ^
  -F "file=@C:\path\to\audio.wav" ^
  -F "model=Whisper-Tiny"
```

=== "Linux"

```bash
curl -X POST http://localhost:13305/v1/audio/transcriptions \
  -F "file=@/path/to/audio.wav" \
  -F "model=Whisper-Tiny"
```

Response format

{
  "text": "Hello, this is a sample transcription of the audio file."
}

Field Descriptions:

text - The transcribed text from the audio file

`WS /realtime`

Realtime Audio Transcription API via WebSocket (OpenAI SDK compatible). Stream audio from a microphone and receive transcriptions in real-time with Voice Activity Detection (VAD).

Limitations: Only 16kHz mono PCM16 audio format is supported. Uses the same Whisper models as the HTTP transcription endpoint.

Connection

The WebSocket server runs on a dynamically assigned port. Discover the port via the /v1/health endpoint (websocket_port field), then connect with the model name:

ws://localhost:<websocket_port>/realtime?model=Whisper-Tiny

Upon connection, the server sends a session.created message with a session ID.

Client → Server Messages

Message Type	Description
`session.update`	Configure the session (set model, VAD settings, or disable turn detection)
`input_audio_buffer.append`	Send audio data (base64-encoded PCM16)
`input_audio_buffer.commit`	Force transcription of buffered audio
`input_audio_buffer.clear`	Clear audio buffer without transcribing

Server → Client Messages

Message Type	Description
`session.created`	Session established, contains session ID
`session.updated`	Session configuration updated
`input_audio_buffer.speech_started`	VAD detected speech start
`input_audio_buffer.speech_stopped`	VAD detected speech end, transcription triggered
`input_audio_buffer.committed`	Audio buffer committed for transcription
`input_audio_buffer.cleared`	Audio buffer cleared
`conversation.item.input_audio_transcription.delta`	Interim/partial transcription (replaceable)
`conversation.item.input_audio_transcription.completed`	Final transcription result
`error`	Error message

Example: Configure Session

{
  "type": "session.update",
  "session": {
    "model": "Whisper-Tiny"
  }
}

Example: Send Audio

{
  "type": "input_audio_buffer.append",
  "audio": "<base64-encoded PCM16 audio>"
}

Audio should be:

16kHz sample rate
Mono (single channel)
16-bit signed integer (PCM16)
Base64 encoded
Sent in chunks (~85ms recommended)

Example: Transcription Result

{
  "type": "conversation.item.input_audio_transcription.completed",
  "transcript": "Hello, this is a test transcription."
}

VAD Configuration

VAD settings can be configured via session.update:

{
  "type": "session.update",
  "session": {
    "model": "Whisper-Tiny",
    "turn_detection": {
      "threshold": 0.01,
      "silence_duration_ms": 800,
      "prefix_padding_ms": 250
    }
  }
}

Parameter	Default	Description
`threshold`	0.01	RMS energy threshold for speech detection
`silence_duration_ms`	800	Silence duration to trigger speech end
`prefix_padding_ms`	250	Minimum speech duration before triggering

Set turn_detection to null to disable server-side VAD and use explicit commits instead:

{
  "type": "session.update",
  "session": {
    "model": "Whisper-Tiny",
    "turn_detection": null
  }
}

Code Examples

A complete, runnable example:

realtime_transcription.py - Python CLI for microphone streaming

# Stream from microphone
python examples/realtime_transcription.py --model Whisper-Tiny

Integration Notes

Audio Format: Server expects 16kHz mono PCM16. Higher sample rates must be downsampled client-side.
Chunk Size: Send audio in ~85-256ms chunks for optimal latency/efficiency.
VAD Behavior: Server automatically detects speech boundaries and triggers transcription on speech end.
Manual Commit: Set turn_detection to null, then use input_audio_buffer.commit to force transcription. In this mode the server buffers audio but does not emit VAD or interim transcription events.
Clear Buffer: Use input_audio_buffer.clear to discard audio without transcribing.
Chunking: We are still tuning the chunking to balance latency vs. accuracy.

`POST /v1/images/generations`

Image Generation API. You provide a text prompt and receive a generated image. This API uses stable-diffusion.cpp as the backend.

Note: Image generation uses Stable Diffusion models. Available models include SD-Turbo (fast, ~4 steps), SDXL-Turbo, SD-1.5, and SDXL-Base-1.0.

Performance: CPU inference takes ~4-5 minutes per image. GPU (Vulkan) is faster but may have compatibility issues with some hardware.

Parameters

Parameter	Required	Description
`prompt`	Yes	The text description of the image to generate.
`model`	Yes	The Stable Diffusion model to use (e.g., `SD-Turbo`, `SDXL-Turbo`).
`size`	No	The size of the generated image. Format: `WIDTHxHEIGHT` (e.g., `512x512`, `256x256`). Default: `512x512`.
`n`	No	Number of images to generate. Currently only `1` is supported.
`response_format`	No	Format of the response. Only `b64_json` (base64-encoded image) is supported.
`steps`	No	Number of inference steps. SD-Turbo works well with 4 steps. Default varies by model.
`cfg_scale`	No	Classifier-free guidance scale. SD-Turbo uses low values (~1.0). Default varies by model.
`seed`	No	Random seed for reproducibility. If not specified, a random seed is used.

Example request

=== "Bash"

```bash
curl -X POST http://localhost:13305/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
        "model": "SD-Turbo",
        "prompt": "A serene mountain landscape at sunset",
        "size": "512x512",
        "steps": 4,
        "response_format": "b64_json"
      }'
```

`POST /v1/images/edits`

Image Editing API. You provide a source image and a text prompt describing the desired change, and receive an edited image. This API uses stable-diffusion.cpp as the backend.

Note: This endpoint accepts multipart/form-data requests (not JSON). Use editing-capable models such as Flux-2-Klein-4B or SD-Turbo.

Performance: CPU inference takes several minutes per image. GPU (ROCm) is significantly faster.

Parameters

Parameter	Required	Description
`model`	Yes	The Stable Diffusion model to use (e.g., `Flux-2-Klein-4B`, `SD-Turbo`).
`image`	Yes	The source image file to edit (PNG). Sent as a file in multipart/form-data.
`prompt`	Yes	A text description of the desired edit.
`mask`	No	An optional mask image (PNG). White areas indicate regions to edit; black areas are preserved.
`size`	No	The size of the output image. Format: `WIDTHxHEIGHT` (e.g., `512x512`). Default: `512x512`.
`n`	No	Number of images to generate. Allowed range: `1`–`10`. Default: `1`. Values outside this range are rejected with `400 Bad Request`.
`response_format`	No	Format of the response. Only `b64_json` (base64-encoded image) is supported.
`steps`	No	Number of inference steps. Default varies by model.
`cfg_scale`	No	Classifier-free guidance scale. Default varies by model.
`seed`	No	Random seed for reproducibility.
`user`	No	OpenAI API compatibility field. Accepted but not forwarded to the backend.
`background`	No	OpenAI API compatibility field. Accepted but not forwarded to the backend.
`quality`	No	OpenAI API compatibility field. Accepted but not forwarded to the backend.
`input_fidelity`	No	OpenAI API compatibility field. Accepted but not forwarded to the backend.
`output_compression`	No	OpenAI API compatibility field. Accepted; silently ignored by the backend.

Example request

=== "Bash"

```bash
curl -X POST http://localhost:13305/v1/images/edits \
  -F "model=Flux-2-Klein-4B" \
  -F "prompt=Add a red barn and mountains in the background, photorealistic" \
  -F "size=512x512" \
  -F "n=1" \
  -F "response_format=b64_json" \
  -F "image=@/path/to/source_image.png"
```

=== "Python (OpenAI client)"

```python
from openai import OpenAI
client = OpenAI(base_url="http://localhost:13305/api/v1", api_key="not-needed")
with open("source_image.png", "rb") as image_file:
    response = client.images.edit(
        model="Flux-2-Klein-4B",
        image=image_file,
        prompt="Add a red barn and mountains in the background, photorealistic",
        size="512x512",
    )
import base64
image_data = base64.b64decode(response.data[0].b64_json)
open("edited_image.png", "wb").write(image_data)
```

`POST /v1/images/variations`

Image Variations API. You provide a source image and receive a variation of it. This API uses stable-diffusion.cpp as the backend.

Note: This endpoint accepts multipart/form-data requests (not JSON). Unlike /images/edits, a prompt parameter is not supported and will be ignored — the model generates a variation based solely on the input image.

Performance: CPU inference takes several minutes per image. GPU (ROCm) is significantly faster.

Parameters

Parameter	Required	Description
`model`	Yes	The Stable Diffusion model to use (e.g., `Flux-2-Klein-4B`, `SD-Turbo`).
`image`	Yes	The source image file (PNG). Sent as a file in multipart/form-data.
`size`	No	The size of the output image. Format: `WIDTHxHEIGHT` (e.g., `512x512`). Default: `512x512`.
`n`	No	Number of variations to generate. Integer between 1 and 10 inclusive. Default: `1`. Values outside this range result in a 400 Bad Request error.
`response_format`	No	Format of the response. Only `b64_json` (base64-encoded image) is supported.
`user`	No	OpenAI API compatibility field. Accepted but not forwarded to the backend.

Example request

=== "Bash"

```bash
curl -X POST http://localhost:13305/v1/images/variations \
  -F "model=Flux-2-Klein-4B" \
  -F "size=512x512" \
  -F "n=1" \
  -F "response_format=b64_json" \
  -F "image=@/path/to/source_image.png"
```

=== "Python (OpenAI client)"

```python
from openai import OpenAI
client = OpenAI(base_url="http://localhost:13305/api/v1", api_key="not-needed")
with open("source_image.png", "rb") as image_file:
    response = client.images.create_variation(
        model="Flux-2-Klein-4B",
        image=image_file,
        size="512x512",
        n=1,
    )
import base64
image_data = base64.b64decode(response.data[0].b64_json)
open("variation.png", "wb").write(image_data)
```

`POST /v1/images/upscale`

Image Upscaling API. You provide a base64-encoded image and a Real-ESRGAN model name, and receive a 4x upscaled image. This API uses the sd-cli binary from stable-diffusion.cpp to perform super-resolution.

Note: Available upscale models are RealESRGAN-x4plus (general-purpose, 64 MB) and RealESRGAN-x4plus-anime (optimized for anime-style art, 17 MB). Both produce a 4x resolution increase (e.g., 256x256 → 1024x1024).

Note: Unlike /images/edits and /images/variations, this endpoint accepts a JSON body (not multipart/form-data). The image must be provided as a base64-encoded string.

Parameters

Parameter	Required	Description	Status
`image`	Yes	Base64-encoded PNG image to upscale.
`model`	Yes	The ESRGAN model to use (e.g., `RealESRGAN-x4plus`, `RealESRGAN-x4plus-anime`).

Example request

A typical workflow is to generate an image first, then upscale it:

=== "Bash"

```bash
# Step 1: Generate an image and save the base64 response
RESPONSE=$(curl -s -X POST http://localhost:13305/v1/images/generations \
  -H "Content-Type: application/json" \
  -d '{
        "model": "SD-Turbo",
        "prompt": "A serene mountain landscape at sunset",
        "size": "512x512",
        "steps": 4,
        "response_format": "b64_json"
      }')

# Step 2: Build the upscale JSON payload and pipe it to curl via stdin
# (base64 images are too large for command-line interpolation)
echo "$RESPONSE" | python3 -c "
import sys, json
b64 = json.load(sys.stdin)['data'][0]['b64_json']
print(json.dumps({'image': b64, 'model': 'RealESRGAN-x4plus'}))
" | curl -X POST http://localhost:13305/v1/images/upscale \
  -H "Content-Type: application/json" \
  -d @-
```

=== "PowerShell"

```powershell
# Step 1: Generate an image
$genResponse = Invoke-WebRequest `
  -Uri "http://localhost:13305/v1/images/generations" `
  -Method POST `
  -Headers @{ "Content-Type" = "application/json" } `
  -Body '{
    "model": "SD-Turbo",
    "prompt": "A serene mountain landscape at sunset",
    "size": "512x512",
    "steps": 4,
    "response_format": "b64_json"
  }'

# Step 2: Extract the base64 image
$imageB64 = ($genResponse.Content | ConvertFrom-Json).data[0].b64_json

# Step 3: Upscale the image with Real-ESRGAN
$body = @{ image = $imageB64; model = "RealESRGAN-x4plus" } | ConvertTo-Json
Invoke-WebRequest `
  -Uri "http://localhost:13305/v1/images/upscale" `
  -Method POST `
  -Headers @{ "Content-Type" = "application/json" } `
  -Body $body
```

=== "Python (requests)"

```python
import requests
import base64

BASE_URL = "http://localhost:13305/api/v1"

# Step 1: Generate an image
gen_response = requests.post(f"{BASE_URL}/images/generations", json={
    "model": "SD-Turbo",
    "prompt": "A serene mountain landscape at sunset",
    "size": "512x512",
    "steps": 4,
    "response_format": "b64_json",
})
image_b64 = gen_response.json()["data"][0]["b64_json"]

# Step 2: Upscale the image with Real-ESRGAN (512x512 -> 2048x2048)
upscale_response = requests.post(f"{BASE_URL}/images/upscale", json={
    "image": image_b64,
    "model": "RealESRGAN-x4plus",
})

# Step 3: Save the upscaled image to a file
upscaled_b64 = upscale_response.json()["data"][0]["b64_json"]
with open("upscaled.png", "wb") as f:
    f.write(base64.b64decode(upscaled_b64))
```

Response format

{
  "created": 1742927481,
  "data": [
    {
      "b64_json": "<base64-encoded upscaled PNG>"
    }
  ]
}

Field Descriptions:

created - Unix timestamp of when the upscaled image was generated
data - Array containing the upscaled image
- b64_json - Base64-encoded PNG of the upscaled image

Error responses

Status Code	Condition	Example
400	Missing `image` field	`{"error": {"message": "Missing 'image' field (base64 encoded)", "type": "invalid_request_error"}}`
400	Missing `model` field	`{"error": {"message": "Missing 'model' field", "type": "invalid_request_error"}}`
404	Unknown model name	`{"error": {"message": "Upscale model not found: bad-model", "type": "invalid_request_error"}}`
500	Upscale failed	`{"error": {"message": "ESRGAN upscale failed", "type": "server_error"}}`

`POST /v1/audio/speech`

Speech Generation API. You provide a text input and receive an audio file. This API uses Kokoros as the backend.

Note: The model to use is called kokoro-v1. No other model is supported at the moment.

Limitations: Only mp3, wav, opus, and pcm are supported. Streaming is supported in audio (pcm) mode.

Parameters

Parameter	Required	Description
`input`	Yes	The text to speak.
`model`	Yes	The model to use (e.g., `kokoro-v1`).
`speed`	No	Speaking speed. Default: `1.0`.
`voice`	No	The voice to use. All OpenAI-defined voices can be used (`alloy`, `ash`, ...), as well as those defined by the kokoro model (`af_sky`, `am_echo`, ...). Default: `shimmer`
`response_format`	No	Format of the response. `mp3`, `wav`, `opus`, and `pcm` are supported. Default: `mp3`
`stream_format`	No	If set, the response will be streamed. Only `audio` is supported, which will output `pcm` audio. Default: not set

Example request

=== "Bash"

```bash
curl -X POST http://localhost:13305/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{
        "model": "kokoro-v1",
        "input": "Lemonade can speak!",
        "speed": 1.0,
        "steps": 4,
        "response_format": "mp3"
      }'
```

Response format

The generated audio file is returned as-is.

`GET /v1/models`

Returns a list of models available on the server in an OpenAI-compatible format. Each model object includes extended fields like checkpoint, recipe, size, downloaded, labels, and, when known, max_context_window.

By default, only models available locally (downloaded) are shown, matching OpenAI API behavior.

Parameters

Parameter	Required	Description
`show_all`	No	If set to `true`, returns all models from the catalog including those not yet downloaded. Defaults to `false`.

Example request

# Show only downloaded models (OpenAI-compatible)
curl http://localhost:13305/v1/models

# Show all models including not-yet-downloaded (extended usage)
curl http://localhost:13305/v1/models?show_all=true

Response format

{
  "object": "list",
  "data": [
    {
      "id": "Qwen3-0.6B-GGUF",
      "created": 1744173590,
      "object": "model",
      "owned_by": "lemonade",
      "checkpoint": "unsloth/Qwen3-0.6B-GGUF:Q4_0",
      "recipe": "llamacpp",
      "size": 0.38,
      "max_context_window": 40960,
      "downloaded": true,
      "suggested": true,
      "labels": ["reasoning"]
    },
    {
      "id": "Gemma-3-4b-it-GGUF",
      "created": 1744173590,
      "object": "model",
      "owned_by": "lemonade",
      "checkpoint": "ggml-org/gemma-3-4b-it-GGUF:Q4_K_M",
      "recipe": "llamacpp",
      "size": 3.61,
      "downloaded": true,
      "suggested": true,
      "labels": ["hot", "vision"]
    },
    {
      "id": "SD-Turbo",
      "created": 1744173590,
      "object": "model",
      "owned_by": "lemonade",
      "checkpoint": "stabilityai/sd-turbo:sd_turbo.safetensors",
      "recipe": "sd-cpp",
      "size": 5.2,
      "downloaded": true,
      "suggested": true,
      "labels": ["image"],
      "image_defaults": {
        "steps": 4,
        "cfg_scale": 1.0,
        "width": 512,
        "height": 512
      }
    }
  ]
}

Field Descriptions:

object - Type of response object, always "list"
data - Array of model objects with the following fields:
- id - Model identifier (used for loading and inference requests)
- created - Unix timestamp of when the model entry was created
- object - Type of object, always "model"
- owned_by - Owner of the model, always "lemonade"
- checkpoint - Full checkpoint identifier on Hugging Face
- recipe - Backend/device recipe used to load the model (e.g., "ryzenai-llm", "llamacpp", "flm")
- size - Model size in GB (omitted for models without size information)
- max_context_window - Optional integer indicating the maximum model-supported text context discovered from local static metadata. Currently populated for downloaded GGUF/llama.cpp models and installed FLM text-context models.
- downloaded - Boolean indicating if the model is downloaded and available locally
- suggested - Boolean indicating if the model is recommended for general use
- labels - Array of tags describing the model's capabilities and characteristics. See Model Labels for the full list.
- image_defaults - (Image models only) Default generation parameters for the model:
  - steps - Number of inference steps (e.g., 4 for turbo models, 20 for standard models)
  - cfg_scale - Classifier-free guidance scale (e.g., 1.0 for turbo models, 7.5 for standard models)
  - width - Default image width in pixels
  - height - Default image height in pixels

Model Labels

Labels describe what a model can do. A model may carry multiple labels.

Deployment labels — determine which backend endpoint the model is routed to:

Label	Endpoint	Description
`transcription`	`/audio/transcriptions`	Speech-to-text transcription model (e.g. Whisper). Mutually exclusive with LLM deployment.
`embeddings`	`/embeddings`	Produces text embedding vectors.
`reranking`	`/reranking`	Scores and reranks a list of passages given a query.
`image`	`/images/generations`	Text-to-image generation model.
`edit`	Image editing model; supports the `/images/edits` endpoint.
`tts`	`/audio/speech`	Text-to-speech synthesis model.

Input-modality labels — the model is deployed as an LLM but accepts additional input types in /chat/completions:

Label	Description
`vision`	Accepts image attachments in chat messages.
`chat-transcription`	Accepts audio attachments in chat messages (e.g. Qwen2.5-Omni).

Streaming labels — capability flags for real-time features:

Label	Description
`realtime-transcription`	Supports the WebSocket `/realtime` endpoint for live microphone transcription.

Runtime labels — affect backend launch defaults:

Label	Description
`mtp`	Enables llama.cpp MTP draft decoding defaults (`--spec-type draft-mtp --spec-draft-n-max 3 --spec-draft-p-min 0.75`); users can override these with `llamacpp_args`.

Characteristic labels — informational, do not affect routing:

Label	Description
`hot`	Featured or popular model, highlighted in the UI.
`reasoning`	Uses extended chain-of-thought reasoning (e.g. DeepSeek, Qwen3).
`tool-calling`	Supports function/tool calling in chat completions.
`coding`	Tuned for code generation and software tasks.
`upscaling`	Image upscaling model (e.g. Real-ESRGAN). Used as a component in image pipelines.
`experimental`	Not yet validated for production use.

`GET /v1/models/{model_id}`

Retrieve a specific model by its ID. Returns the same model object format as the list endpoint above.

Parameters

Parameter	Required	Description
`model_id`	Yes	The ID of the model to retrieve. Must match one of the model IDs from the models list.

Example request

curl http://localhost:13305/v1/models/Qwen3-0.6B-GGUF

Response format

Returns a single model object with the same fields as described in the models list endpoint above.

{
  "id": "Qwen3-0.6B-GGUF",
  "created": 1744173590,
  "object": "model",
  "owned_by": "lemonade",
  "checkpoint": "unsloth/Qwen3-0.6B-GGUF:Q4_0",
  "recipe": "llamacpp",
  "size": 0.38,
  "max_context_window": 40960,
  "downloaded": true,
  "suggested": true,
  "labels": ["reasoning"],
  "recipe_options": {
    "ctx_size": 8192,
    "llamacpp_args": "--no-mmap",
    "llamacpp_backend": "rocm"
  }
}

Error responses

If the model is not found, the endpoint returns a 404 error:

{
  "error": {
    "message": "Model Qwen3-0.6B-GGUF has not been found",
    "type": "not_found"
  }
}

FilesExpand file tree

openai.md

Latest commit

History

openai.md

File metadata and controls

OpenAI-Compatible API

POST /v1/chat/completions

Parameters

Example request

Image understanding input format (OpenAI-compatible)

Response format

POST /v1/completions

Parameters

Example request

Response format

POST /v1/embeddings

Parameters

Example request

Response format

POST /v1/responses

Parameters

Streaming Events

Example request

Response format

POST /v1/audio/transcriptions

Parameters

Example request

Response format

WS /realtime

Connection

Client → Server Messages

Server → Client Messages

Example: Configure Session

Example: Send Audio

Example: Transcription Result

VAD Configuration

Code Examples

Integration Notes

POST /v1/images/generations

Parameters

Example request

POST /v1/images/edits

Parameters

Example request

POST /v1/images/variations

Parameters

Example request

POST /v1/images/upscale

Parameters

Example request

Response format

Error responses

POST /v1/audio/speech

Parameters

Example request

Response format

GET /v1/models

Parameters

Example request

Response format

Model Labels

GET /v1/models/{model_id}

Parameters

Example request

Response format

Error responses

`POST /v1/chat/completions`

`POST /v1/completions`

`POST /v1/embeddings`

`POST /v1/responses`

`POST /v1/audio/transcriptions`

`WS /realtime`

`POST /v1/images/generations`

`POST /v1/images/edits`

`POST /v1/images/variations`

`POST /v1/images/upscale`

`POST /v1/audio/speech`

`GET /v1/models`

`GET /v1/models/{model_id}`