ComputePrices API

Cloud GPU and LLM inference pricing, catalog, daily trends, and weekly movers — all under /api/v1/* as stable JSON.

Quickstart

No signup, no key. Paste this:

curl https://computeprices.com/api/v1/gpu-prices

That's the whole API for the public tier. You get 60 requests/hour per IP. A free key lifts the limit to 5,000/hour and extends historical trend windows from 7 to 30 days.

Three things if you're running an agent or automated tool:

• Send a descriptive User-Agent header.
• Respect Retry-After on 429 responses.
• Read meta.upgrade_hint — it names the next-tier features, not just throughput.

A raw markdown copy of this page is at /docs/api.md — curl it directly. For broader site discovery, see llms.txt.

Tiers

What you get at each tier:

v1.1 = coming in the next release. roadmap = planned, no date.

Rate-limit ratios mirror GitHub's REST API (60/hr unauth → 5,000/hr authed). Feature gates start at pro.

Authentication

Public-tier requests need nothing — just hit the endpoint:

curl https://computeprices.com/api/v1/gpu-prices

Authenticated requests use a Bearer token:

curl -H "Authorization: Bearer cp_live_..." \
  https://computeprices.com/api/v1/gpu-prices

Getting a free key

Self-serve is on the roadmap. Until then, email api@computeprices.com with your use case and we'll get you a key. There's no approval hurdle for reasonable use.

Endpoints

All endpoints return { data, meta }. meta always includes version, generated_at, tier, and (when auth or rate-limiting is in play) rate_limit and upgrade_hint.

Pricing

GET /api/v1/gpu-prices · public+

Latest GPU prices across every tracked provider. One row per (provider, GPU, pricing_type, node size).

Query parameters:

Example:

curl "https://computeprices.com/api/v1/gpu-prices?gpu=h100&pricing_type=on_demand"

Response:

{
  "data": [
    {
      "provider": "Lambda",
      "provider_slug": "lambda",
      "provider_url": "https://lambdalabs.com",
      "gpu": "H100 80GB",
      "gpu_slug": "h100",
      "vram_gb": 80,
      "architecture": "Hopper",
      "gpu_count": 1,
      "max_gpus_per_node": 8,
      "price_per_hour_usd": 2.49,
      "total_hourly_usd": 2.49,
      "pricing_type": "on_demand",
      "commitment_months": null,
      "currency": "USD",
      "exchange_rate_to_usd": 1,
      "source_url": "https://lambdalabs.com/pricing",
      "last_updated": "2026-04-20T10:15:30Z"
    }
  ],
  "meta": {
    "count": 1,
    "generated_at": "2026-04-20T12:00:00Z",
    "version": "v1",
    "tier": "public",
    "rate_limit": { "limit": 60, "remaining": 58, "reset": 1714827060, "window_seconds": 3600 },
    "upgrade_hint": "A free API key lifts your limit..."
  }
}

GET /api/v1/llm-prices · public+

Latest LLM inference prices. Per-1M-token input/output pricing, modalities, knowledge cutoff.

Query parameters:

Example:

curl "https://computeprices.com/api/v1/llm-prices?model=claude-3-5-sonnet"

Catalog

GET /api/v1/gpus · public+

List of every GPU model we track, with specs (VRAM, architecture, TFLOPs, memory bandwidth).

curl https://computeprices.com/api/v1/gpus

GET /api/v1/gpus/{slug} · public+

Single GPU model with full specs.

curl https://computeprices.com/api/v1/gpus/h100

GET /api/v1/llm-models · public+

List of tracked LLM models with creator, context window, modalities, and knowledge cutoff.

curl https://computeprices.com/api/v1/llm-models

GET /api/v1/llm-models/{slug} · public+

Single LLM model detail.

curl https://computeprices.com/api/v1/llm-models/claude-3-5-sonnet

GET /api/v1/providers · public+

List of tracked cloud and inference-API providers (archived providers excluded).

curl https://computeprices.com/api/v1/providers

GET /api/v1/providers/{slug} · public+

Single provider detail.

curl https://computeprices.com/api/v1/providers/lambda

Trends & movers

GET /api/v1/trends/gpu/{slug} · public+

Daily average price for a GPU across providers. days is capped by tier (7/30/90/365).

Query parameters:

Example:

curl "https://computeprices.com/api/v1/trends/gpu/h100?days=90"

GET /api/v1/trends/llm/{slug} · public+

Daily average input/output token price for an LLM across providers.

Query parameters:

Example:

curl "https://computeprices.com/api/v1/trends/llm/claude-3-5-sonnet?days=30"

GET /api/v1/movers · public+

Biggest week-over-week price changes (up or down) for a (provider, GPU/LLM) pair.

Query parameters:

Example:

curl "https://computeprices.com/api/v1/movers?scope=gpu&limit=10"

Pro — coming in v1.1

• GET /api/v1/indexes — weekly compute price index, 100-baseline, separate series per GPU / LLM.
• GET /api/v1/compare — side-by-side provider comparison with price differences and shared-GPU coverage.
• GET /api/v1/cheapest — cheapest provider per LLM model for input and output tokens.
• GET /api/v1/gpu-prices/history — raw GPU price history with date-range filters (beyond the 30-day public window).
• GET /api/v1/llm-prices/history — raw LLM price history.

Enterprise — coming in v1.2

• GET /api/v1/llm-benchmarks — LLM throughput, time-to-first-token, p95 latency from Artificial Analysis.
• GET /api/v1/providers/{slug}/health — per-provider scrape health, staleness, and price confidence metrics.

Rate limits

Every response carries X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset (Unix epoch seconds). 429 Too Many Requests additionally sets Retry-After in seconds.

Public tier is keyed by IP; authenticated tiers are keyed by API key. Windows are per-hour with a sliding window — short bursts are allowed, sustained throughput is not.

Errors

Standard HTTP status codes. Error bodies share a small envelope.

401 Unauthorized

Malformed Authorization header, invalid/revoked/expired key, or the endpoint requires free tier and you sent no key.

402 Payment Required

Endpoint requires a paid tier. Body includes required_tier, current_tier, and upgrade_hint.

{
  "error": "tier_required",
  "message": "Provider comparison requires the pro tier.",
  "required_tier": "pro",
  "current_tier": "free",
  "upgrade_hint": "Pro adds price indices, provider comparison...",
  "meta": { "version": "v1" }
}

404 Not Found

Unknown slug or resource.

429 Too Many Requests

Over your tier's rate budget. Wait Retry-After seconds.

500 Internal Server Error

Upstream failure. Try again; if persistent, ping us.

Versioning & stability

All endpoints live under /api/v1/* and guarantee additive, non-breaking changes at this version. Breaking changes will ship under a new version prefix and the old version will stay available for at least 6 months.

Fields added to response bodies are non-breaking. Fields are never renamed or removed at the same version. meta.version is always "v1".

Roadmap

Near-term (explicit target):

• v1.1: price indices, provider comparison, cheapest-per-model, historical prices with date ranges, CSV & NDJSON export.
• v1.2: LLM benchmarks (throughput, TTFT, p95), per-provider scrape-health and data-confidence metrics.

No-date items:

• Webhooks on price change.
• Per-key scopes (restrict a key to specific endpoints).
• Self-serve API key dashboard.
• Public SLA page.

Next steps

• Start with /api/v1/providers to see what's tracked.
• Grab raw markdown for your agent: /docs/api.md (text/markdown).
• Site-wide resource map: llms.txt.
• Feedback or a free key: api@computeprices.com.