The Global Price Benchmark
for AI Inference

Pricing intelligence for developers, analysts, and infrastructure buyers

--Datapoints --SKUs --Models --Vendors --Modalities --Countries
Inference Market Coverage
Key Price Movements and Structural Shifts
Loading Timeline
Inference Price Volatility
Live Price Movement Across All Tracked Models
🔒 Unlock Full Intelligence See Plans
🔒 Unlock Full Intelligence See Plans
Input Price Volatility
--
YTD Average
--
Cached Input Price Volatility
--
YTD Average
--
Output Price Volatility
--
YTD Average
--
Input
Cached Input
Output
Loading Live Data
Inference Price Benchmarks
15 Indexes Across Modality, Channel, Tier, and Licensing
🔒 Unlock Full Intelligence See Plans
🔒 Unlock Full Intelligence See Plans
Loading Live Data
Inference Market KPIs
9 Cost and Structure Metrics Derived from Live Pricing Data
🔒 Unlock Full Intelligence See Plans
🔒 Unlock Full Intelligence See Plans
Loading market intelligence...
Global Inference Supply
Live Tracking Across Key Markets
Loading Coverage Data
For Developers
& AI Agents
For Analysts
& FinOps Teams
For Engineering
& Quant Teams
ATOM | MCP

4 tools free. 4 more with MCP PRO. -- SKUs across -- vendors.
Native to Claude, Cursor, Windsurf, and any MCP-compatible client.

8 tools — 4 free with MCP · 4 unlocked with MCP PRO
list_vendors get_kpis get_index_benchmarks get_market_stats search_models get_model_detail compare_prices get_vendor_catalog
MCP Tool  ·  search_models  ·  atom-mcp-server-production.up.railway.app
Agent Query
Find text models with 100K+ context window and tool calling support. Rank by input price, cheapest last.
ATOM MCP  ·  search_models  ·  10 results returned
#ModelVendorVendor TypeContextToolInput /1Mvs. Priciest
1Claude Sonnet 4.5AnthropicModel Developer200K$3.00— anchor
2GPT-4oOpenAIModel Developer128K$2.5017% cheaper
3Mistral LargeMistralModel Developer128K$2.0033% cheaper
4Gemini 1.5 ProGoogleModel Developer1M$1.2558% cheaper
5Llama 3.3 70BGroqInference Platform128K$0.5980% cheaper
6Llama 3.3 70BTogether AICloud Marketplace128K$0.3588% cheaper
7DeepSeek V3DeepSeekModel Developer128K$0.2791% cheaper
8Llama 3.3 70BFireworks AIInference Platform128K$0.2293% cheaper
9Gemini 2.0 FlashGoogleModel Developer1M$0.1097% cheaper
10Gemini 2.0 FlashOpenRouterCloud Marketplace1M$0.1097% cheaper
LIVE  ·  200 OK  ·  18ms
MCP/SSE  ·  -- SKUs  ·  -- vendors
Explore MCP
ATOM | TERMINAL

Full market intelligence for analysts and FinOps teams.
Dynamic dashboards across every modality, channel, and tier.

Dynamic dashboards — full market intelligence across every modality, channel, and tier
Regional Indexes Custom Indexes Model-Level Data Vendor-Level Data Vendor Benchmarking Competitiveness Rankings Rank Movement Tracking Supply Share Metrics Complete Time Series Daily Alerts
ATOM Terminal Dashboard
Explore Terminal
ATOM | FEED

-- SKUs across -- vendors.
Query by 32 parameters. Direct to your systems.

32 fields per SKU. Full schema access.
sku_id vendor vendor_type model_name modality model_family region
context_window tool_calling open_source direction normalized_price billing_method delivery_method
GET  api.a7om.com/v1/prices?model=llama-4-maverick&vendor=together-ai
{
  // ── Identity ────────────────────────────────────
  "sku_id": "together-llama-4-maverick-text-input",
  "vendor_id": "together",
  "vendor_name": "Together AI",
  "vendor_type": "Inference Platform",
  "model_id": "meta-llama/llama-4-maverick",
  "model_name": "Llama 4 Maverick",
  "sku_plan_name": "Llama 4 Maverick — Text Input",
  // ── Model Intelligence ───────────────────────────
  "modality": "Text",
  "modality_subtype": "Chat Completion",
  "model_family": "Llama 4",
  "context_window": 1048576,
  "tool_calling": true,
  "open_source": true,
  // ── Pricing ──────────────────────────────────────
  "direction": "Input",
  "original_price": "$0.27 / 1M tokens",
  "billing_method": "Token-based",
  "normalized_price": 0.00027,
  "normalized_unit": "per 1,000 tokens",
  "normalization_formula": "price / 1000",
  "normalization_method": "Standard Token",
  // ── Delivery & Geography ─────────────────────────
  "delivery_method": "Real-Time",
  "deployment_method": "Cloud API (Shared)",
  "contracting_method": "Self-serve",
  "region": "North America",
  "country": "United States",
  "vendor_url": "https://together.ai",
  "pricing_url": "https://together.ai/pricing",
  "verification_date": "2026-03-01",
  "run_id": "20260301-103843-875"
}
LIVE  ·  200 OK  ·  12ms
application/json  ·  -- SKUs  ·  -- vendors
Explore FEED
Data Integrity

Why Institutional Buyers
Trust ATOM

Every price point collected, timestamped, and verified.
Built by information economists with 25+ years advising C-suite teams on pricing strategy.

Deterministic Methodology
Full Audit Trail
Analyst-Verified Accuracy
View Our Methodology
Inference KPIs
Loading Inference KPIs...