Supported Models

Available Models

Lilac currently supports the following models. We’re actively adding more — reach out if there’s a model you’d like to see.

Model	Model ID	Context Length	Quantization	Input Price	Cache Read Price	Output Price
Kimi K2.6	`moonshotai/kimi-k2.6`	262,144 tokens	INT4	$0.70 / M tokens	$0.20 / M tokens	$3.50 / M tokens
GLM 5.1	`zai-org/glm-5.1`	202,800 tokens	FP8	$0.90 / M tokens	$0.27 / M tokens	$3.00 / M tokens
Gemma 4	`google/gemma-4-31b-it`	262,100 tokens	BF16	$0.11 / M tokens	—	$0.35 / M tokens
MiniMax M2.7	`minimaxai/minimax-m2.7`	204,800 tokens	FP8	$0.30 / M tokens	$0.055 / M tokens	$1.20 / M tokens

Cache read is the rate for repeated input tokens served from cache. It’s billed at a lower rate than standard input tokens on supported models. Models that don’t support cached input tokens are marked with —.

More models are coming soon. Request a model by emailing contact@getlilac.com.

Kimi K2.6

Moonshot AI’s flagship multimodal reasoning model. 1T total parameters (32B activated) with a Mixture-of-Experts architecture.

Kimi K2.6 on Hugging Face

Model card, benchmarks, and deployment guides.

Capabilities

Capability	Status	Details
Text input	Supported	Chat, instructions, system prompts
Image input	Supported	Native multimodal — pass images via `image_url` in messages
Text output	Supported	Completions, structured JSON, tool calls
Reasoning (thinking)	On by default	Chain-of-thought returned in `reasoning` field. Kimi K2.6’s Moonshot chat template honors `chat_template_kwargs: {"thinking": false}` (the `enable_thinking` key is ignored here). For forward compatibility across models, see the Reasoning section.
Tool calling	Supported	Function definitions with automatic argument extraction
Structured output	Supported	`response_format` with `json_object` or `json_schema`

Recommended Parameters

From the Kimi K2.6 model card:

Mode	Temperature	Top P
Thinking (default)	`1.0`	`0.95`
Instant (thinking off)	`0.6`	`0.95`

Vision

Kimi K2.6 natively supports image inputs. Pass images as base64 data URIs or URLs in the content array:

Python
cURL

response = client.chat.completions.create(
    model="moonshotai/kimi-k2.6",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this image."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg",
                        "detail": "auto"
                    }
                }
            ]
        }
    ],
)

curl https://api.getlilac.com/v1/chat/completions \
  -H "Authorization: Bearer your-lilac-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2.6",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe this image."},
          {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg", "detail": "auto"}}
        ]
      }
    ]
  }'

You can also pass base64-encoded images:

import base64

with open("image.png", "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="moonshotai/kimi-k2.6",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What's in this image?"},
                {
                    "type": "image_url",
                    "image_url": {"url": f"data:image/png;base64,{image_b64}"}
                }
            ]
        }
    ],
)

GLM 5.1

Z.ai’s next-generation flagship model for agentic engineering. 754B total parameters in a Mixture-of-Experts architecture, with state-of-the-art coding capabilities — it holds up over long-horizon tasks, handles ambiguous problems well, and sustains hundreds of tool calls per run. 202.8K context window, 131.1K max output. MIT licensed.

GLM 5.1 on Hugging Face

Model card, benchmarks, and deployment guides.

Capabilities

Capability	Status	Details
Text input	Supported	Chat, instructions, system prompts
Text output	Supported	Completions, structured JSON, tool calls
Image input	Not supported	GLM 5.1 is text-only
Reasoning (thinking)	On by default	Chain-of-thought returned in `reasoning` field. GLM 5.1’s chat template honors `chat_template_kwargs: {"enable_thinking": false}` (the `thinking` key is ignored here, and leaving it set alone will cause the chain-of-thought to leak into `content` terminated by a `</think>` marker — see the Reasoning section for details and the forward-compatible form).
Tool calling	Supported	Function definitions with automatic argument extraction — strong performance on agentic tasks
Structured output	Supported	`response_format` with `json_object`

Recommended Parameters

From the Z.ai platform docs:

Mode	Temperature	Top P
Thinking (default)	`1.0`	`0.95`
Instant (thinking off)	`0.6`	`0.95`

Example request

Python
JavaScript
cURL

response = client.chat.completions.create(
    model="zai-org/glm-5.1",
    messages=[
        {"role": "user", "content": "Write a haiku about idle GPUs."}
    ],
)

const response = await client.chat.completions.create({
  model: "zai-org/glm-5.1",
  messages: [
    { role: "user", content: "Write a haiku about idle GPUs." }
  ],
});

curl https://api.getlilac.com/v1/chat/completions \
  -H "Authorization: Bearer your-lilac-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/glm-5.1",
    "messages": [
      {"role": "user", "content": "Write a haiku about idle GPUs."}
    ]
  }'

Gemma 4

Google’s open-weight multimodal model. 31B parameters with native support for text, image, and video inputs. 262K context window with BF16 precision. Released under the Gemma license.

Gemma 4 on Hugging Face

Model card, benchmarks, and deployment guides.

Capabilities

Capability	Status	Details
Text input	Supported	Chat, instructions, system prompts
Image input	Supported	Native multimodal — pass images via `image_url` in messages
Video input	Supported	Pass video frames as a sequence of images
Text output	Supported	Completions, structured JSON
Reasoning (thinking)	Off by default	Chain-of-thought returned in `reasoning` field when enabled. Gemma 4’s chat template honors `chat_template_kwargs: {"enable_thinking": true}` (the `thinking` key is ignored here). Unlike Kimi K2.6 and GLM 5.1, thinking is off by default — you must opt in. See the Reasoning section for the forward-compatible form.
Tool calling	Supported	Function definitions with automatic argument extraction
Structured output	Supported	`response_format` with `json_object` or `json_schema`

Gemma 4 chain-of-thought may leak into content. vLLM’s Gemma 4 reasoning parser can fail to populate the reasoning field when special tokens are stripped before the parser runs — see vllm-project/vllm#38855. When reasoning is enabled, clients that require a clean split should post-process by treating text inside <|channel|>thought ... <|channel|> markers as reasoning.

Structured output caveat. On current vLLM builds, combining --reasoning-parser gemma4 with enable_thinking: false can silently disable xgrammar-backed structured output — see vllm-project/vllm#39130. If you rely on response_format: json_schema with Gemma 4, leave thinking enabled or validate output client-side.

Enabling reasoning

Gemma 4 is the only model in the catalog where reasoning is off by default. To turn it on, use the forward-compatible form recommended in the Reasoning section:

Python
cURL

response = client.chat.completions.create(
    model="google/gemma-4-31b-it",
    messages=[{"role": "user", "content": "Prove there are infinitely many primes."}],
    extra_body={
        "chat_template_kwargs": {
            "thinking": True,
            "enable_thinking": True,
        }
    },
)

curl https://api.getlilac.com/v1/chat/completions \
  -H "Authorization: Bearer your-lilac-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31b-it",
    "messages": [
      {"role": "user", "content": "Prove there are infinitely many primes."}
    ],
    "chat_template_kwargs": {
      "thinking": true,
      "enable_thinking": true
    }
  }'

Vision

Gemma 4 natively supports image inputs. Pass images as base64 data URIs or URLs in the content array:

Python
cURL

response = client.chat.completions.create(
    model="google/gemma-4-31b-it",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this image."},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/image.jpg",
                        "detail": "auto"
                    }
                }
            ]
        }
    ],
)

curl https://api.getlilac.com/v1/chat/completions \
  -H "Authorization: Bearer your-lilac-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31b-it",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe this image."},
          {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg", "detail": "auto"}}
        ]
      }
    ]
  }'

Video

Gemma 4 can process video by accepting a sequence of frames as images. Extract frames from your video and pass them as multiple image_url entries:

Python
cURL

import base64
import cv2

# Extract frames from video
video = cv2.VideoCapture("video.mp4")
frames = []
while video.isOpened():
    ret, frame = video.read()
    if not ret:
        break
    _, buffer = cv2.imencode(".jpg", frame)
    frames.append(base64.b64encode(buffer).decode())
video.release()

# Sample frames to fit context window
sampled = frames[::len(frames) // 8][:8]

response = client.chat.completions.create(
    model="google/gemma-4-31b-it",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe what happens in this video."},
                *[
                    {
                        "type": "image_url",
                        "image_url": {"url": f"data:image/jpeg;base64,{frame}"}
                    }
                    for frame in sampled
                ]
            ]
        }
    ],
)

curl https://api.getlilac.com/v1/chat/completions \
  -H "Authorization: Bearer your-lilac-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31b-it",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe what happens in this video."},
          {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,FRAME_1_BASE64"}},
          {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,FRAME_2_BASE64"}}
        ]
      }
    ]
  }'

MiniMax M2.7

MiniMax’s text-only language model. 204.8K context window with reasoning, tool calling, and structured output support over an OpenAI-compatible API.

MiniMax M2.7 on Hugging Face

Model card, benchmarks, and deployment guides.

Capabilities

Capability	Status	Details
Text input	Supported	Chat, instructions, system prompts
Text output	Supported	Completions, structured JSON, tool calls
Image input	Not supported	MiniMax M2.7 is text-only
Reasoning (thinking)	Supported	Chain-of-thought returned in the `reasoning` field. See the Reasoning section for forward-compatible toggles.
Tool calling	Supported	Function definitions with automatic argument extraction
Structured output	Supported	`response_format` with `json_object` or `json_schema`

Limits

Limit	Value
Context length	204,800 tokens
Max completion tokens	204,800 tokens

Supported parameters

MiniMax M2.7 accepts the following sampling and request parameters via the OpenAI-compatible API: temperature, top_p, top_k, max_tokens, stop, frequency_penalty, presence_penalty, repetition_penalty, seed, min_p, logit_bias, logprobs, top_logprobs, response_format, structured_outputs, tools, tool_choice.

Example request

Python
JavaScript
cURL

response = client.chat.completions.create(
    model="minimaxai/minimax-m2.7",
    messages=[
        {"role": "user", "content": "Write a haiku about idle GPUs."}
    ],
)

const response = await client.chat.completions.create({
  model: "minimaxai/minimax-m2.7",
  messages: [
    { role: "user", content: "Write a haiku about idle GPUs." }
  ],
});

curl https://api.getlilac.com/v1/chat/completions \
  -H "Authorization: Bearer your-lilac-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimaxai/minimax-m2.7",
    "messages": [
      {"role": "user", "content": "Write a haiku about idle GPUs."}
    ]
  }'

Listing Models via API

Python
JavaScript
cURL

from openai import OpenAI

client = OpenAI(
    base_url="https://api.getlilac.com/v1",
    api_key="your-lilac-api-key",
)

models = client.models.list()
for model in models:
    print(model.id)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.getlilac.com/v1",
  apiKey: "your-lilac-api-key",
});

const models = await client.models.list();
for await (const model of models) {
  console.log(model.id);
}

curl https://api.getlilac.com/v1/models \
  -H "Authorization: Bearer your-lilac-api-key"

Documentation Index

​Available Models

​Kimi K2.6

Kimi K2.6 on Hugging Face

​Capabilities

​Recommended Parameters

​Vision

​GLM 5.1

GLM 5.1 on Hugging Face

​Capabilities

​Recommended Parameters

​Example request

​Gemma 4

Gemma 4 on Hugging Face

​Capabilities

​Enabling reasoning

​Vision

​Video

​MiniMax M2.7

MiniMax M2.7 on Hugging Face

​Capabilities

​Limits

​Supported parameters

​Example request

​Listing Models via API

Available Models

Kimi K2.6

Capabilities

Recommended Parameters

Vision

GLM 5.1

Capabilities

Recommended Parameters

Example request

Gemma 4

Capabilities

Enabling reasoning

Vision

Video

MiniMax M2.7

Capabilities

Limits

Supported parameters

Example request

Listing Models via API