LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Back to Tools

API · MCP

The normalized pricing, capability and leaderboard data behind this site is published as plain static JSON, free to fetch and without an API key. Point your code or an agent straight at it.

Endpoints

GETmodels.jsonhttps://llmpricing.dev/api/models.json

All models: canonical entry, official + cheapest channel price, blended prices, context, capabilities, Artificial Analysis scores and 30-day usage.

GETproviders.jsonhttps://llmpricing.dev/api/providers.json

All providers: name, tier (first-party / cloud / gateway), model count, SDK, API base and docs.

GETllms.txthttps://llmpricing.dev/llms.txt

Plain-text site summary for AI crawlers (llms.txt convention).

Served as static files from a CDN. The site applies no per-client quota, but the host's general traffic limits still apply, so please cache responses rather than refetching on every request. Data refreshes on each build.

Key fields (models.json)

id, name, lab, kindCanonical id, display name, lab and model kind.
official / blendedOfficialPrice from the lab's own API (provider, modelId, input/output/cache-read per 1M) and its blended unit price; null when no official API price is listed. In that case reference falls back to a third-party channel, flagged by reference.official = false.
reference / cheapestReference (official/list) and cheapest paid channel, each with input/output/cache-read per 1M tokens.
outputModalities / generationPricesPrices use each vendor's billing unit. The billed media and listed conditions determine the charge; these values do not enter text-token price comparisons.
blendedRef / blendedMin / blendedTrustedBlended unit price (input×0.75 + output×0.25) for the reference, lowest and lowest-trusted (gateways excluded) channels.
context, outputLimit, capabilitiesContext window, max output, and tri-state capability flags (true/false/null).
aa (idx, coding, agentic, indices, speed, taskCost, evals)Artificial Analysis intelligence, coding and agentic indices, other indices such as the domain sub-indices (indices), output speed, cost per task, and per-benchmark scores (evals, with key names in meta.aaEvals). Coding and agentic are currently null for every model. A field is null when Artificial Analysis publishes no value for the model.
usage (rank, tokens, share)OpenRouter 30-day usage rank, total tokens and share (null when untracked).
hostCount, spreadHow many providers host the model and the cross-platform price spread.
status, openWeights, releaseDate, lastUpdated, urlLifecycle status, open-weights flag, release and last-update dates, and the model page URL.

Examples

Five cheapest models by blended price, with curl and jq:

curl -s https://llmpricing.dev/api/models.json \
  | jq '.models
        | map(select(.blendedMin != null))
        | sort_by(.blendedMin)[:5]
        | .[] | {name, blendedMin, cheapest: .cheapest.provider}'

JavaScript (fetch):

const res = await fetch("https://llmpricing.dev/api/models.json");
const { meta, models } = await res.json();

// 5 cheapest by blended price (input x0.75 + output x0.25)
const cheapest = models
  .filter((m) => m.blendedMin != null)
  .sort((a, b) => a.blendedMin - b.blendedMin)
  .slice(0, 5);

console.log(meta.syncedAt, cheapest);

Python (requests):

import requests

data = requests.get("https://llmpricing.dev/api/models.json").json()
models = data["models"]

# highest Artificial Analysis intelligence with a public price
ranked = sorted(
    (m for m in models if m["aa"] and m["aa"]["idx"] is not None),
    key=lambda m: m["aa"]["idx"],
    reverse=True,
)
for m in ranked[:5]:
    print(m["name"], m["aa"]["idx"], m["blendedMin"])

Endpoints send Access-Control-Allow-Origin: *, so they work from the browser too.

MCP server

Because the data is clean JSON over HTTPS, any fetch-capable MCP server can expose it to an agent. For example, the reference fetch server:

{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    }
  }
}

Then ask the agent to read https://llmpricing.dev/api/models.json. The fetch tool returns 5,000 characters per call by default and continues from start_index, and models.json is over 1 MB, so use it for targeted lookups. For bulk questions such as the cheapest model within a budget, run the examples above in an agent with code execution, or start from llms.txt, a smaller plain-text summary.

A first-party MCP server with typed tools (search_models, cheapest, compare) is on the roadmap. Until then the JSON endpoints above are the stable interface.

License & attribution

Data is aggregated from models.dev (MIT), Artificial Analysis and OpenRouter. You may reuse it under CC BY 4.0, keeping attribution to LLM Pricing and the upstream sources.