Serverless API
Models
Serverless API
Models
Anthropic
Supported Models
Index supports several powerful large language models with vision capabilities:
Gemini
Gemini 2.5 Pro
- Status: High performance and fast execution
- Usage: Best choice for complex reasoning tasks that require fast execution
- How to use:
import { LaminarClient } from '@lmnr-ai/lmnr';
const client = new LaminarClient({
projectApiKey: 'lmnr-project-api-key',
});
const main = async () => {
const result = await client.agent.run({
prompt: 'Go to www.lmnr.ai and summarize their homepage.',
modelProvider: 'gemini',
model: 'gemini-2.5-pro-preview-03-25',
});
console.log(result);
};
main().then(() => {
console.log('Done');
});
import { LaminarClient } from '@lmnr-ai/lmnr';
const client = new LaminarClient({
projectApiKey: 'lmnr-project-api-key',
});
const main = async () => {
const result = await client.agent.run({
prompt: 'Go to www.lmnr.ai and summarize their homepage.',
modelProvider: 'gemini',
model: 'gemini-2.5-pro-preview-03-25',
});
console.log(result);
};
main().then(() => {
console.log('Done');
});
from lmnr import LaminarClient
client = LaminarClient(project_api_key='lmnr-project-api-key')
result = client.agent.run(
prompt='Go to www.lmnr.ai and summarize their homepage.',
model_provider='gemini',
model='gemini-2.5-pro-preview-03-25',
)
print(result)
from lmnr import AsyncLaminarClient
client = AsyncLaminarClient(project_api_key='lmnr-project-api-key')
async def main():
result = await client.agent.run(
prompt='Go to www.lmnr.ai and summarize their homepage.',
model_provider='gemini',
model='gemini-2.5-pro-preview-03-25',
)
print(result)
asyncio.run(main())
Gemini 2.5 Flash
- Status: Good performance and fast execution, very cost effective
- Usage: Best choice for simpler tasks that require fast execution and low cost
- How to use:
import { LaminarClient } from '@lmnr-ai/lmnr';
const client = new LaminarClient({
projectApiKey: 'lmnr-project-api-key',
});
const main = async () => {
const result = await client.agent.run({
prompt: 'Go to www.lmnr.ai and summarize their homepage.',
modelProvider: 'gemini',
model: 'gemini-2.5-flash-preview-04-17',
});
console.log(result);
};
main().then(() => {
console.log('Done');
});
import { LaminarClient } from '@lmnr-ai/lmnr';
const client = new LaminarClient({
projectApiKey: 'lmnr-project-api-key',
});
const main = async () => {
const result = await client.agent.run({
prompt: 'Go to www.lmnr.ai and summarize their homepage.',
modelProvider: 'gemini',
model: 'gemini-2.5-flash-preview-04-17',
});
console.log(result);
};
main().then(() => {
console.log('Done');
});
from lmnr import LaminarClient
client = LaminarClient(project_api_key='lmnr-project-api-key')
result = client.agent.run(
prompt='Go to www.lmnr.ai and summarize their homepage.',
model_provider='gemini',
model='gemini-2.5-flash-preview-04-17',
)
print(result)
from lmnr import AsyncLaminarClient
client = AsyncLaminarClient(project_api_key='lmnr-project-api-key')
async def main():
result = await client.agent.run(
prompt='Go to www.lmnr.ai and summarize their homepage.',
model_provider='gemini',
model='gemini-2.5-flash-preview-04-17',
)
print(result)
asyncio.run(main())
Anthropic
Claude 3.7 Sonnet
- Status: High performance
- Usage: Best choice for complex reasoning tasks
- How to use:
import { LaminarClient } from '@lmnr-ai/lmnr';
const client = new LaminarClient({
projectApiKey: 'lmnr-project-api-key',
});
const main = async () => {
const result = await client.agent.run({
prompt: 'Go to www.lmnr.ai and summarize their homepage.',
modelProvider: 'anthropic',
model: 'claude-3-7-sonnet-20250219',
});
console.log(result);
};
main().then(() => {
console.log('Done');
});
import { LaminarClient } from '@lmnr-ai/lmnr';
const client = new LaminarClient({
projectApiKey: 'lmnr-project-api-key',
});
const main = async () => {
const result = await client.agent.run({
prompt: 'Go to www.lmnr.ai and summarize their homepage.',
modelProvider: 'anthropic',
model: 'claude-3-7-sonnet-20250219',
});
console.log(result);
};
main().then(() => {
console.log('Done');
});
from lmnr import LaminarClient
client = LaminarClient(project_api_key='lmnr-project-api-key')
result = client.agent.run(
prompt='Go to www.lmnr.ai and summarize their homepage.',
model_provider='anthropic',
model='claude-3-7-sonnet-20250219',
)
print(result)
from lmnr import AsyncLaminarClient
client = AsyncLaminarClient(project_api_key='lmnr-project-api-key')
async def main():
result = await client.agent.run(
prompt='Go to www.lmnr.ai and summarize their homepage.',
model_provider='anthropic',
model='claude-3-7-sonnet-20250219',
)
print(result)
asyncio.run(main())
OpenAI
o4-mini
- Status: Good performance
- Usage: Various difficulty tasks, depends on
reasoning_effortparameter - How to use:
import { LaminarClient } from '@lmnr-ai/lmnr';
const client = new LaminarClient({
projectApiKey: 'lmnr-project-api-key',
});
const main = async () => {
const result = await client.agent.run({
prompt: 'Go to www.lmnr.ai and summarize their homepage.',
modelProvider: 'openai',
model: 'o4-mini',
});
console.log(result);
};
main().then(() => {
console.log('Done');
});
import { LaminarClient } from '@lmnr-ai/lmnr';
const client = new LaminarClient({
projectApiKey: 'lmnr-project-api-key',
});
const main = async () => {
const result = await client.agent.run({
prompt: 'Go to www.lmnr.ai and summarize their homepage.',
modelProvider: 'openai',
model: 'o4-mini',
});
console.log(result);
};
main().then(() => {
console.log('Done');
});
from lmnr import LaminarClient
client = LaminarClient(project_api_key='lmnr-project-api-key')
result = client.agent.run(
prompt='Go to www.lmnr.ai and summarize their homepage.',
model_provider='openai',
model='o4-mini',
)
print(result)
from lmnr import AsyncLaminarClient
client = AsyncLaminarClient(project_api_key='lmnr-project-api-key')
async def main():
result = await client.agent.run(
prompt='Go to www.lmnr.ai and summarize their homepage.',
model_provider='openai',
model='o4-mini',
)
print(result)
asyncio.run(main())