InferIndex

InferIndex

InferIndex finds the cheapest provider for a given LLM, across more than 60 tracked pricing sources — direct provider APIs and aggregators/routers — with price history and promotion detection.

Live API: https://api.inferindex.dev

Service status: https://status.inferindex.dev (external uptime monitoring)

This repository holds the public documentation, examples and (eventually) a client SDK for that API. The backend itself — collection, parsers, data model — lives in a separate private repository.

curl "https://api.inferindex.dev/cheapest?model=deepseek/deepseek-v3.2"

_Example response as of 2026-10-07 — prices, providers and statuses change._

{

"query": "deepseek/deepseek-v3.2", "model": { "id": "deepseek/deepseek-v3.2", "name": "DeepSeek: DeepSeek V3.2" }, "other_matches": [], "sort": "blended", "cheapest": { "provider": "GMICloud", "via": "openrouter", "via_name": "OpenRouter", "offer_url": "https://openrouter.ai/models", "offer_url_kind": "pricing", "tier": "standard", "input_per_1M": 0.2088, "output_per_1M": 0.3096, "cache_read_per_1M": 0.0216, "blended_per_1M": 0.234, "currency": "USD", "quantization": "fp8", "quantization_source": "declared", "context_length": 163840, "promo": true, "also_via": [ "kilo" ], "unverified": [] }, "offers": [ { "provider": "GMICloud", "via": "openrouter", "via_name": "OpenRouter", "blended_per_1M": 0.234, "…": "…" }, { "provider": "Nous Portal", "via": "nous", "via_name": "Nous Portal", "blended_per_1M": 0.234, "…": "…" } ], "hidden_tiers": { "flex": 1 }, "filters_unknown": {}, "strict": false }

Prices are in USD per million tokens, converted at the day's ECB rate when the source publishes another currency. blended_per_1M is (3 × input + output) / 4, a rough proxy for a typical chat workload. Each offer appears once, at its cheapest source: via is "direct" or the aggregator it comes from, and also_via lists other sources selling the same offer. promo is false unless a promotion was detected, in which case confidence and price_before_promo are filled in.

Status

Early / actively developed. The API is public and free to use, without authentication, but there is no uptime guarantee, no versioned API contract yet, and endpoints or response shapes may change. If you build something on it, expect to adjust when they do. Feedback and issues are welcome.

Service status: https://status.inferindex.dev (external uptime monitoring). It shows current and past availability; it is not an uptime guarantee.

Why

Provider pricing pages disagree, change without notice, and rarely show what resellers actually charge for the same model. InferIndex collects prices from more than 60 sources, each read from its own listing on its own schedule (from hourly to daily depending on the source), stores every change, and answers "who is cheapest for model X right now" from that history — client requests never trigger a live call to a provider.

Data freshness and limits

• Cache: successful responses carry Cache-Control: public, max-age=300 (5 minutes) (except /health/ready, never cached). On the custom domain, responses are additionally held in Cloudflare's edge cache for the same 5 minutes.
• Collection frequency: most sources are polled hourly; a few (exchange rates, model catalog) once a day.
• Rate limits: 60 requests per minute per IP on /cheapest, /history, /resellers, /self-host, /gpus and /gpu-rentals, counting only requests not answered from cache. An optional API key (x-api-key header) raises this to 300 requests per minute per key; free keys will be offered, self-service sign-up isn't available yet. An invalid key returns

1. Over the limit, requests get 429. The MCP server has its own limits, see Use with AI assistants.

• Cost estimate: add prompt_tokens, output_tokens, cached_ratio and requests_per_day to /cheapest or /resellers to get an estimated cost per request and per month for each offer, and sort=estimated_cost to rank by it. See docs/api.md.
• Hidden tiers by default: degraded service tiers (flex, batch — lower priority, variable latency, in exchange for a lower price) are excluded from /cheapest and /resellers unless you ask for them with include_tiers=flex,batch. The number hidden is reported in hidden_tiers.

Reliability of the prices — read this before trusting a number

Data corrections are listed in the changelog.

InferIndex is a comparison tool, not a source of truth. Treat every price as "what our collector last saw", not as a guarantee of what you will be billed:

• Prices come from public APIs and, for some sources, HTML pages parsed with source-specific code — a page redesign can silently break a parser until it's caught.
• A price that looks unusually low may be a promotion, a misparsed unit, or a provider that hasn't updated its page yet. InferIndex applies guard rails (rejecting implausible prices, quarantining sudden jumps, flagging outliers against a second reference source) and reports detected promotions with a confidence level, but these are heuristics, not certainties.
• Reseller aggregators can add their own margin. When a source's pricing model isn't fully understood, it is either excluded or flagged.
• Always confirm the price on the provider's own page or dashboard before committing to real spend.

Endpoints

/cheapest filters

• sort=blended\|input\|output — sort order (default blended)
• min_context=100000 — minimum context window
• quantization=fp8,bf16 — accepted quantizations
• min_uptime=95 — minimum 30-minute uptime (%), as observed by an aggregator (not measured by InferIndex)
• tools=true, json=true, vision=true — only offers declared to support tool calling, JSON output, image input
• region=eu — only offers processed in that region (eu, us, cn, uk, ch, sg, id, my, vn, kr, jp, in, ca, au), per the providers' official documents
• no_training=true — only offers whose providers state they don't train on prompts
• no_waitlist=true — only providers whose signup is open to everyone
• strict=true — also drop offers for which the filtered data is unknown (by default they're kept and flagged in unverified, counted in filters_unknown)
• include_tiers=flex,batch — include degraded service tiers (excluded by default, see above)
• explain=true — list every excluded offer with its reason codes (an explanation summary is always included)

Offers also carry conditions (data region, retention, training on prompts, and what it takes to open an account — each with its official source link), quantization_source (whether the compute precision is declared by the source or inferred), and, on /resellers, reliability from the providers' official status pages. See docs/api.md.

/history

granularity=raw returns one row per price change; day / week (weeks start Monday) return one point per period and per offer (provider, quantization, variant) with min, max and last price. Use days or from/to for a period, or at=2026-09-15 for the prices in force at a given moment. Prices are converted to USD at the ECB rate of the day of the price.

Model search (/models):

curl "https://api.inferindex.dev/models?search=deepseek"

_Example response as of 2026-09-15 — prices, providers and statuses change._

{

"count": 19, "models": [ { "id": "deepseek/deepseek-v3.2", "name": "DeepSeek: DeepSeek V3.2" }, { "id": "deepseek/deepseek-v4.1-flash", "name": "DeepSeek: DeepSeek V4.1 Flash" } ] }

/health/ready

_Example response as of 2026-09-15 — prices, providers and statuses change._

{

"ready": true, "status": "ok", "failures": [], "degraded": [], "warnings": ["2 price source(s) in error", "1 announcement source(s) in error"], "prices": { "current_offers": 5664, "latest_check_at": "2026-09-15T05:01:05.639Z", "latest_check_age_minutes": 1.5 }, "watcher": { "active_sources": 84, "errors": 1, "persistent_errors": 0, "latest_check_at": "2026-09-15T05:02:08.890Z", "latest_check_age_minutes": 0.4 }, "schedulers": { "active": 62, "ok": 62, "starting": 0, "late": 0, "not_started": 0 }, "source_errors": { "count": 1, "persistent": 0 }, "version": { "id": "…", "tag": "", "deployed_at": "…" }, "checked_at": "2026-09-15T05:02:34.383Z" }

status is ok, degraded (a non-critical part is having trouble — see the degraded array for which) or unavailable (no usable price data). HTTP 200 for ok/degraded, 503 for unavailable. Useful as an uptime-monitor target if you depend on this API.

Full route and parameter reference: docs/api.md.

Use with AI assistants (MCP)

InferIndex is also available as a remote MCP server, so an AI assistant can look up prices for you:

• Endpoint: https://mcp.inferindex.dev/mcp (Streamable HTTP) (https://api.inferindex.dev/mcp also works, as an alias)
• Listed in the official MCP Registry as io.github.InferIndex/inferindex.
• Read-only, no authentication. An API key can be passed in the x-api-key header.
• Limits: 120 requests per minute per IP on /mcp, at most 10 JSON-RPC messages per batch and 64 KB per request (otherwise 400 or 413 with JSON-RPC error -32600). Over the rate limit: 429 with JSON-RPC error -32000. Each tool call also counts toward the limit of the API route it uses (/cheapest, /resellers, /history, /self-host, /gpus, /gpu-rentals).

| `price_history(model, days \| from +