GLOBAL INFERENCE MARKET LIVE
The market for
inference.
Buy, sell, and route inference across models and infrastructure
at the best available price.
Every model. Every provider. One market.
LIQUID INFERENCE INDEX LIX 100
$1.82 ↘ 3.80% 24H−27.4% YoY
Cost / 1M quality-adjusted tokens
$185.3M↗ 12.8%
67.25TModel-specific contracts
6.39T11 active regions
99.999%8 connected providers
THE GLOBAL ORDER BOOK
All markets Live markets
| 24H change | Price / 24H | Available | |||||
|---|---|---|---|---|---|---|---|
GPT-5.6 SolOpenAI · US East | $10.48/ 1M output | -2.31% | $34.2M | 241B tokens | 164 ms | ||
Claude SonnetAnthropic · US West | $13.92/ 1M output | -4.70% | $28.4M | 184B tokens | 182 ms | ||
Gemini ProGoogle · US West | $9.84/ 1M output | -3.12% | $19.8M | 318B tokens | 146 ms | ||
DeepSeek V4DeepSeek · US East | $1.62/ 1M output | +1.84% | $16.7M | 420B tokens | 218 ms | ||
Liquid AutoRouteLiquid · Global | $2.18/ 1M output | -5.24% | $14.2M | 1240B tokens | 118 ms | ||
Llama 4Meta · US West | $0.780/ 1M output | -1.42% | $12.1M | 682B tokens | 94 ms | ||
Claude OpusAnthropic · US East | $23.76/ 1M output | -1.67% | $9.6M | 96B tokens | 242 ms |
Continuous price discoveryModel-specific contracts Output and input tokens Spot, reserved, and forward delivery
PRECISION AT EVERY LAYER
Open terminal A real contract. A transparent market.
US West · OUTPUT · <250ms · SPOT
Order book
USD / 1M outputBid size (M)BidAskAsk size (M)
34.013.87013.92038.0
57.913.86013.93048.9
76.413.84913.94155.3
89.013.83913.95165.1
100.713.82813.96283.1
117.313.81813.972106.6
140.013.80713.983127.6
164.613.79713.993140.8
Inference forward curve
Claude Sonnet · OutputSpot$13.92
Oct 2026$13.52
Nov 2026$12.95
Dec 2026$12.42
Q1 2027$11.80
Lock future inference capacity at transparent market prices. Fixed model, region, and service level.
ONE ENDPOINT. OPTIMAL EXECUTION.
Best execution
for every token.
One API for the best available price, latency, and reliability. Your workload takes the right path through the market.
Explore the routerYOUR PRICE$4.20 / M
LIQUID MARKET$3.11 / M
26.0%illustrative savingsProvider competition, batching, and capacity utilization improve pricing. Actual savings vary by workload.
Your application requests / responses
Liquid Router PRICE × LATENCY × QUALITY
Fireworks$2.21 · 180msBEST EXECUTION
Together$1.98 · 242ms
Cerebras$2.44 · 91ms
Groq$2.36 · 114ms
Best price within the 200 ms latency target
TypeScript · Integration specification
const response = await liquid.responses.create({
model: "liquid/auto",
objective: {
quality: 0.90,
max_ttft: 200,
optimize: "price"
}
});SECONDARY CAPACITY MARKET
Your unused capacity
has value.
Turn idle inference commitments into available supply. The original model, region, SLA, and expiry travel with the contract.
Claude SonnetAnthropic · US West
Original commitment1B tokens
Available for resale380M tokens
Executable bid / 1M$13.870
Estimated resale value$5,270.60
One market. Global reach.
11 ACTIVE REGIONSLIQUID AGENT RUNTIME
Built for agents
that think a lot.
Reasoning loops, parallel rollouts, and long-running tasks. Keep inference and environment execution close.
01Reason
02Search
03Call tool
04Evaluate
05Simulate
06Verify
07Answer
Inference 81%Environment 14%Network 5%
Seven steps. One execution layer.
A MARKET THAT GETS BETTER WITH EVERY REQUEST
More demandMore suppliersDeeper liquidityTighter spreadsBetter execution
Better execution brings more demand back to the market.
THE ECONOMIC LAYER FOR MACHINE INTELLIGENCE
Intelligence should have
a market price.
Every model. Every provider. One market.
Enter the market