Operated by Sourcelane✓ verified
Run one prompt across many language models at once and get every response side by side, with token counts, cost, and latency per model in a single results.
A tool that sends a single user prompt to many large language models in parallel and aggregates per-model outputs for side-by-side comparison. It supports hundreds of models across multiple providers (examples include GPT, Claude, Gemini, Llama, DeepSeek, Kimi, Qwen, GLM) and returns each model’s full text response along with token usage breakdown (prompt/completion/total), measured latency, provider metadata, completion reason and status, and any error messages. Designed for comparative evaluation and selection, it captures quality, speed, and cost-related metrics per model, measures per-model latency and completion behavior, and presents one record per model to enable benchmarking, A/B testing of prompts, and construction of evaluation results for prompt engineering.
Verified Sep 28, 3:55 AM
$0.001
per model response
Up to 100 per call. Only pay for results returned; failed calls are refunded.
Pick the best and cheapest model for a task before committing to it in production
Benchmark answer quality, speed, and price across providers on custom prompts
A/B test a system prompt across multiple models
Build evaluation results for prompt engineering
The question or instruction to send to every model.
Optional system instruction applied to every model, for example 'You are a concise expert assistant.'
Optional settings
| Window | Uptime | Success rate | p50 | p95 | Calls |
|---|---|---|---|---|---|
| 24h | — | — | — | — | 0 |
| 7d | — | — | — | — | 0 |
| 30d | — | — | — | — | 0 |
Call it through Sourcelane's gateway or MCP server. We run the connector, apply your agent's spend guardrails, and bill only the results returned.
Call it via Sourcelane
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"multi-model-llm-compare","params":{"prompt":"Explain quantum entanglement to a 10 year old in 3 sentences."},"maxResults":10}'Request params
| Field | Type | Required | Description |
|---|---|---|---|
prompt | string | required | The question or instruction to send to every model. |
models | array | optional | Pick the models to compare. Leave empty to use a default cross-provider set (Gemini, GPT, Claude, Llama). |
systemPrompt | string | optional | Optional system instruction applied to every model, for example 'You are a concise expert assistant.' |
temperature | number | optional | Optional sampling temperature from 0 to 2. Leave empty to use each model's default. |
maxTokens | integer | optional | Maximum tokens each model may generate. Lower values cap cost per response. Defaults to 1024. |
Each result contains
| Field | Type | Description |
|---|---|---|
prompt | string | Prompt |
model | string | Model |
provider | string | Provider |
response | string | Response |
promptTokens | integer | Prompt Tokens |
completionTokens | integer | Completion Tokens |
totalTokens | integer | Total Tokens |
latencyMs | integer | Latency Ms |
finishReason | string | Finish Reason |
status | string | Status |
error | null | — |
Pick your tool and connect in under a minute. Then just ask — for example: “Transcribe this video and give me timestamps for every product mention: <url>”
Connect Claude
Web, desktop and mobile. One click, then confirm.
Adds the Sourcelane MCP server with your key as a header.
claude mcp add --transport http sourcelane https://api.usesourcelane.com/mcp \
--header "Authorization: Bearer sl_live_your_agent_key"Alternative to the connector URL: add to claude_desktop_config.json, then restart Claude.
{
"mcpServers": {
"sourcelane": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://api.usesourcelane.com/mcp",
"--header",
"Authorization:${AUTH_HEADER}"
],
"env": {
"AUTH_HEADER": "Bearer sl_live_your_agent_key"
}
}
}
}Add to ~/.cursor/mcp.json (or Windsurf's mcp_config.json).
{
"mcpServers": {
"sourcelane": {
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer sl_live_your_agent_key"
}
}
}
}Save as .vscode/mcp.json. VS Code prompts for your key once.
{
"servers": {
"sourcelane": {
"type": "http",
"url": "https://api.usesourcelane.com/mcp",
"headers": {
"Authorization": "Bearer ${input:sourcelane-key}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "sourcelane-key",
"description": "Sourcelane agent key",
"password": true
}
]
}Create a GPT → Actions → Import from URL, then Authentication: API Key, Bearer.
https://usesourcelane.com/openapi.jsonOne POST. Pass maxResults to cap cost.
curl -X POST https://api.usesourcelane.com/v1/call \
-H "Authorization: Bearer sl_live_your_agent_key" \
-H "Content-Type: application/json" \
-d '{"listing":"multi-model-llm-compare","params":{"prompt":"Explain quantum entanglement to a 10 year old in 3 sentences."},"maxResults":10}'Wrap the REST call as a tool, or point an MCP client at the endpoint.
import requests
res = requests.post(
"https://api.usesourcelane.com/v1/call",
headers={"Authorization": "Bearer sl_live_your_agent_key"},
json={
"listing": "multi-model-llm-compare",
"params": {"prompt":"Explain quantum entanglement to a 10 year old in 3 sentences."},
"maxResults": 10,
},
timeout=300,
)
body = res.json()
print(body["receipt"]["chargedMicros"], "micro-USD for", body["receipt"]["results"], "results")
print(body["data"])—
0 reviews
Leave a review
Loading reviews…