Bankr Chat (Venice AI)

LIVE ON-CHAINBase

OpenAI-compatible LLM chat completions via Venice AI: Llama 3.3 70B, Qwen3 235B, Kimi K2, DeepSeek, Grok, uncensored models. Streaming (SSE), tool/function calling. POST {messages, model?, temperature?, max_tokens?, stream?, tools?}.

Window	Trust	Uptime	Success	p50	p95	Price	Data
Last hour	93	100%	—	—	—	$0.003	Low
Last 24h	94	100%	—	—	—	$0.003	Low
Last 7 days	93	100%	—	—	—	$0.003	Low

Endpoint	Uptime	Latency	Price / call
GET`/{address}/image-pro` Dellbot Image Pro (Bankr)	—	—	$0.15
GET`/{address}/tts-pro` Dellbot TTS Pro (Bankr)	—	—	$0.08
GET`/{address}/image-nano` Dellbot Image Nano (Bankr)	—	—	$0.02
GET`/{address}/chat-pro` Bankr Chat-Pro (Kimi K2 Thinking / Qwen3 Coder 480B)	—	—	$0.01
GET`/{address}/tts-nano` Dellbot TTS Nano (Bankr)	—	—	$0.005
GET`/{address}/chat` Bankr Chat (Venice AI)	—	—	$0.0008
GET`/{address}/chat-nano` Bankr Chat-Nano (Llama 3.3 70B)	—	—	$0.0008

Bankr Chat (Venice AI)

Overview

Health

Metrics by window

Endpoints (7)

Equivalent APIs