⌘
01One compatible API
Use OpenAI clients and switch models with one parameter. Streaming, usage, and errors follow familiar shapes.
● TAIWAN-BUILT · GLOBAL COMPUTE NETWORK
One API.
Every available GPU.
Route AI inference across sovereign Taiwan infrastructure, official model APIs, and a worldwide community of idle GPUs.
Turn GPU time into tokens. Earn Indigo. Use compute across the network.
✓ No credit card required✓ 500 Indigo per verified node✓ OpenAI compatible
RECIPROCAL COMPUTENETWORK LIVE
01
Provide computeGenerate AI tokens on your GPU
GPU
Ollama connected
INDIGO+95
VALUE STAYS IN THE NETWORK
02
Use what you earnSpend Indigo on another community GPU
INDIGO95
Community Ollama
OUTPUT1,248tokens
Service credit · not transferablePROVIDE → EARN → USE
api.tokens2tokens.com/v1LIVEREQUESTqwen/qwen3-8b
SMART ROUTERTW · 22ms · verified
COMPUTECommunity GPU
from openai import OpenAI
client = OpenAI({
base_url="https://api.tokens2tokens.com/v1",
api_key="t2t_••••••••"
)
response = client.chat.completions.create({
model="qwen/qwen3-8b",
messages=[{"role": "user", "content": "Hello Taiwan!"}]
)GoldOfficial compute
IndigoEarned compute
How credits work →✦ EVERYTHING YOU NEED
Compute that moves where demand is.
Open-source nodes, real-time model discovery, and an accountable ledger make idle hardware useful without changing your AI SDK.
⑂
02Smart marketplace routing
Filter by price, latency, country, verified entity, privacy tier, and quantization.
◫
03Live model discovery
Ollama, LM Studio, llama.cpp, and vLLM catalogs appear automatically when nodes connect.
◇
04Sovereign when it matters
Gold routes sensitive workloads to contracted official infrastructure in Taiwan.
↗
05Earn where you spend
Providers retain 95% in Indigo and can immediately use it for community inference.
⎋
06Open provider client
Transparent Rust and Tauri software for Windows, Ubuntu, and macOS.
⌁ OPEN MARKETPLACE
Compute has a market now.
Every live endpoint competes on price, latency, uptime, location, and trust. Token2Token finds the right route for each request.
Browse the model marketplace →LIVE ROUTE CANDIDATES3 ONLINE
1
Taiwan OfficialTaiwan · verified
officialGold only18 ms2
Formosa LabTaiwan · community
communityAll credits31 ms3
Indigo Node 7Japan · community
communityAll credits47 msBalanced routing
price × latency × uptimeGPU
HAVE AN IDLE GPU?
Your next inference can pay for itself.
Install the open-source client, connect your existing engine, choose prices and an earnings cap, then join the network.
TOKEN2TOKEN BETA
Put every GPU within reach.
Share GPU. Earn Indigo. Run any model.