inferroute

Pay only for what you use.

No subscription. The open frontier — Kimi, GLM, MiniMax — sits well under market on every bucket: input, cache, and output. Claude (Anthropic) is pass-through on your own key, never marked up.

Open models, per token

vs OpenRouter

Kimi K3

Economy
$0.49/ M effective

−64% vs OpenRouter $1.36/M

Economy · per token
Input$0.90 $3.00−70%Cached$0.19 $0.30−37%Output$5.40 $15.00−64%
On-demand
Input$2.40Cached$0.49Output$9.00

GLM 5.2

Economy
$0.22/ M effective

−20% vs OpenRouter $0.27/M

Economy · per token
Input$0.44 $0.50−12%Cached$0.089 $0.10−11%Output$1.40 $3.15−56%
On-demand
Input$0.89Cached$0.19Output$2.90

MiniMax M3

Economy
$0.048/ M effective

−69% vs OpenRouter $0.15/M

Economy · per token
Input$0.090 $0.30−70%Cached$0.019 $0.060−68%Output$0.44 $1.20−63%
On-demand
Input$0.24Cached$0.049Output$0.84

DeepSeek V4 Flash

Economy
$0.023/ M effective

−65% vs OpenRouter $0.066/M

Economy · per token
Input$0.049 $0.14−65%Cached$0.010 $0.028−65%Output$0.090 $0.28−68%
On-demand
Input$0.090Cached$0.019Output$0.19

Kimi K2.6

Economy
$0.11/ M effective

−77% vs OpenRouter $0.46/M

Economy · per token
Input$0.19 $0.95−80%Cached$0.039 $0.16−76%Output$1.40 $4.00−65%
On-demand
Input$0.44Cached$0.089Output$2.40

GLM 5.1

Economy
$0.16/ M effective

−76% vs OpenRouter $0.67/M

Economy · per token
Input$0.34 $1.40−76%Cached$0.069 $0.26−73%Output$0.90 $4.40−80%
On-demand
Input$0.69Cached$0.14Output$2.40

MiniMax M2.7

Economy
$0.048/ M effective

−69% vs OpenRouter $0.15/M

Economy · per token
Input$0.090 $0.30−70%Cached$0.019 $0.060−68%Output$0.44 $1.20−63%
On-demand
Input$0.24Cached$0.049Output$0.84

The big figure is the effective $/M — the three buckets blended on real agent traffic (30.3% input / 68% cached / 1.7% output). Per-token rates below in $/M. Economy is the deferred, best-effort lane (ideal for agents that can wait); on-demand is real-time. Strikethrough is OpenRouter — use the arrows, dots, or swipe to browse models. * imputed cache rate where the provider doesn't publish one.

Works with the Claude you already pay for. Sonnet & Opus pass through your own Anthropic subscription — never marked up, never touched. InferRoute just adds the cheaper open models on top.

Two ways to pay

Most people

One account, no subscription

Top up a balance and pay only for what you route — no monthly bill, stop anytime.

  • No usage-cap anxiety — never ration prompts or get throttled
  • Prepaid credits that never expire
  • Top up by card or USDC — 0% fees in USDC
Request access
x402 enabled

Pay-as-you-go in USDC

Approve once via the open x402 standard. Usage is metered per request and topped up in $1 USDC increments — batched on purpose, so you pay 0 network fees.

  • $1 gasless top-ups, drawn down per request — 0% fees
  • Non-custodial: you approve, funds stay yours until used
  • Built for agents and machine-to-machine spend
Learn about x402

Pay only for what you use. No subscription, no commitment.