ModCon
Token Relay Station (中转站)Public directory profile, technical parameters, and available model price breakdown.
Pricing Multiplier
0.15x
~82.8% off official list Gateway Architecture
OpenAI / Claude API Compatible
Protocol compatible endpoint Hosting Origin / Edge
Tokyo Direct Gateway
Reported server gateway region Probe Telemetry
100% Online
0.69s TTFT • 100% Genuine ModCon PRICE DYNAMICS
PRICE: $3.000 / 1M DISPERSION: ±0.00% FEED: ● 100% CLEAN NATIVE
DRAWING TOOLS:
30 DAYS AGO 21 DAYS AGO 14 DAYS AGO 7 DAYS AGO TODAY (LIVE)
⚡ AVAILABLE MODELS & PRICING BREAKDOWN (ModCon)
8 MONITORED ASSETS
| MODEL / SLOT NAME | REASONING GRADE | CONTEXT / MAX OUT | EFFECTIVE INPUT (1M) | EFFECTIVE OUTPUT (1M) | PROMPT CACHE READ | BATCH MODE (50%) | CAPABILITIES |
|---|---|---|---|---|---|---|---|
| Claude 3.7 Sonnet (Thinking) (Relayed)
MMLU 92.4%
| SOTA Frontier | 200k / 8k | $0.450 | $2.250 | $0.045 -85% | $0.225 / $1.125 | 🧠 👁 |
| Claude 3.5 Sonnet (Relayed)
MMLU 88.5%
| Coding Specialist | 200k / 8k | $0.450 | $2.250 | $0.045 -85% | $0.225 / $1.125 | 👁 |
| Claude 3.5 Haiku (Relayed)
MMLU 88.5%
| Coding Specialist | 200k / 8k | $0.102 | $0.512 | $0.010 -87.2% | $0.051 / $0.256 | 👁 |
| Claude 3 Opus (Relayed)
MMLU 88.5%
| Coding Specialist | 200k / 8k | $2.580 | $12.900 | $0.26 -82.8% | $1.290 / $6.450 | 👁 |
| GPT-4o (Omni) (Relayed)
MMLU 88.5%
| Coding Specialist | 128k / 8k | $0.375 | $1.500 | $0.038 -85% | $0.188 / $0.750 | 👁 |
| GPT-4o mini (Relayed)
MMLU 88.5%
| Fast Economy | 128k / 8k | $0.019 | $0.077 | $0.002 -87.2% | $0.010 / $0.038 | 👁 |
| o3-mini (High Effort) (Relayed)
MMLU 88.5%
| Fast Economy | 128k / 8k | $0.165 | $0.660 | $0.017 -85% | $0.083 / $0.330 | 👁 |
| OpenAI o1 Reasoning (Relayed)
MMLU 88.5%
| SOTA Frontier | 128k / 8k | $2.580 | $10.320 | $0.26 -82.8% | $1.290 / $5.160 | 🧠 👁 |
Public Service Parameters VERIFIED 2026-08-20
Provider Name: ModCon
Market Category: Token Relay Station (中转站)
Supported Payment Methods: Alipay (支付宝), WeChat Pay (微信)
Reported Pooled Channels: 355 Channels
Protocol Architecture: OpenAI / Claude API Compatible
TTFT Latency Probe: 0.69s (±26ms jitter)
24h Probe Online Rate: 100%
100% Genuine Output
SDK Configuration & Connection Endpoint
Standard Gateway SDK Integration:
// OpenAI Compatible Gateway Endpoint import OpenAI from 'openai';
const client = new OpenAI({
apiKey: 'sk-your-provider-key',
baseURL: 'https://api.example-gateway.com/v1',
});
Public Directory Notice: TokTick provides aggregated technical directory specifications and publicly available information for market transparency. TokTick is an independent analytics screener and does not endorse, broker, or operate third-party endpoints.
← Back to Exchange