Pick the cheapest LLM that passes your task and constraints
Pick the cheapest LLM that passes your task and constraints. Give a task class and optional constraints such as minimum context, required tool-use, vision or reasoning, maximum input and output price per million tokens, a minimum coding benchmark and a provider filter, and get a ranked cheapest-first list of models that pass, plus a recommended pick and a deterministic rationale. Fused from open keyless catalogs LiteLLM, models dev and Aider with a citation on every model.
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
GET https://api.agentstools.dev/model/route
| Category | Market data |
|---|---|
| Provider host | api.agentstools.dev |
| Networks | eip155:8453 |
| Payment schemes | exact |
| Self-reported calls, 30 days | 1 from 1 payers (the provider's figure, not ours) |
Our checks, last 30 days
| Day | Result | HTTP | Asked | Time |
|---|---|---|---|---|
| 2026-09-24 | valid payment request | 402 | $0.02 | 1016 ms |
Example input (from the provider)
{
"method": "GET",
"queryParams": {
"max_output_price": 10,
"min_context": 200000,
"needs_tools": true,
"task": "coding"
},
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"method": {
"enum": [
"GET",
"HEAD",
"DELETE"
],
"type": "string"
},
"queryParams": {
"properties": {
"max_input_price": {
"description": "Maximum input price in USD per million tokens.",
"minimum": 0,
"type": "number"
},
"max_output_price": {
"description": "Maximum output price in USD per million tokens.",
"minimum": 0,
"type": "number"
},
"min_benchmark": {
"description": "Minimum Aider coding pass rate percent.",
"maximum": 100,
"minimum": 0,
"type": "number"
},
"min_context": {
"description": "Minimum context window in tokens.",
"minimum": 0,
"type": "integer"
},
"needs_reasoning": {
"description": "Require extended reasoning support.",
"type": "boolean"
},
"needs_tools": {
"description": "Require function or tool calling support.",
"type": "boolean"
},
"needs_vision": {
"description": "Require image or vision input support.",
"type": "boolean"
},
"provider": {
"description": "Optional provider filter such as anthropic or openai.",
"type": "string"
},
"task": {
"description": "The workload class to route for. Each class implies required capabilities and a sensible context floor that your explicit constraints override.",
"enum": [
"coding",
"reasoning",
"vision",
"tool-use",
"long-context",
"cheap-chat",
"general"
],
"type": "string"
}
},
"required": [
"task"
],
"type": "object"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}