Pricing

Open-source core. Pro dashboard.

The MCP server is free forever. Upgrade for team dashboards and cross-session analytics. USD only — not a security, not a token, not crypto.

Monthly
Annual save 20%
MCP Server
$0 / forever
Open source — Apache 2.0
  • 41 agent tools via MCP
  • Cheapest-lane routing across 26 providers
  • Side-by-side model compare
  • Run a node and earn kT credits
  • Works offline without an API key
  • Works with any MCP client
Install free
Most popular
Pro Dashboard
$9 / month
For power users and teams
  • Everything in MCP Server
  • Web dashboard with the savings ledger
  • Cross-session spend history
  • Team cost breakdowns
  • Export and reporting
  • Priority support
Start Pro trial
Enterprise
Custom
For organizations at scale
  • Everything in Pro
  • SSO and SAML
  • On-prem deployment
  • Custom routing policies
  • SLA and dedicated support
  • Audit logs and volume discounts
Contact sales

Run a node and earn kT credits against your usage — credits now; cash when MRR justifies. see the unit economics →

Live spot rates

Real-time pricing across 26+ providers.

InferLane routes your requests to the cheapest option that meets your quality requirements. Rates below are illustrative reference list prices, augmented live from the exchange spot API.

sample data · reference list rates
Providers tracked
23
Models indexed
80+
Local routing
$0.00
Gemma 4 via Ollama

Spot rates

Per 1M tokens · updated in real time
ModelProviderInputOutputContextTiervs Opus
Claude Sonnet 4.5Anthropic$3.00$15.00200KWorkhorse80%
GPT-4oOpenAI$2.50$10.00128KFrontier87%
Gemini 2.5 ProGoogle$1.25$10.001MFrontier87%
Gemini 2.0 FlashGoogle$0.10$0.401MSpeed99%
DeepSeek V3DeepSeek$0.27$1.1064KBudget99%
Gemma 4 27BDarkbloom$0.06$0.20128KDecentralized100%
Claude Haiku 4.5Anthropic$1.00$5.00200KSpeed93%
Llama 3.3 70BGroq$0.59$0.79128KBudget99%
Gemma 4 12BOllama (local)FreeFree128KFree / Local100%

How InferLane saves you money

Smart routing

Simple tasks (classification, extraction) route to budget models. Complex reasoning stays on frontier models. You get the right quality at the right price, automatically.

Local-first

One command installs Ollama + Gemma 4, auto-sized to your hardware. Simple workloads run free on your machine. Zero API cost, zero latency.

Spot exchange

Operators list spare capacity at competitive rates. Dynamic pricing means you benefit from supply competition — not flat-rate monopoly pricing.

No single provider lock-in

InferLane routes across 26 providers. If one raises prices, goes down, or changes terms — your workloads automatically shift. No vendor lock-in. No single point of failure.

AnthropicOpenAIGoogleMistralDeepSeekGroqTogetherFireworksCerebrasOllama (local)DarkbloomChutes (Bittensor)AkashNosana+12 more

Pricing API

Query live spot rates programmatically. Free, no auth required for read-only pricing data.

# Get spot rate for a model

curl "https://inferlane.dev/api/exchange/spot?model=gemma-4-27b&inputTokens=1000&outputTokens=500"