紫脑喵

Provides API access to AI models including Claude, GPT, and Gemini, with support for chat, image generation, and coding tools.

紫脑喵 offers 214 LLM API models.

API pricing per token ranges from $0.010 to $75.00/M (input).

Speed benchmark average: 157 tok/s.

Avg Speed157.45 tok/s

Latency5.65 s

Total Tests20

Models4

Updated4/17/2026

Created At3/10/2026

Model Pricing

Pricing for 214 models (group: default, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)
qwen3-coder-nextFixed	$0.010	$0.010
gemini-2.5-flash-preview-09-2025-thinkingFixed	$0.010	$0.010
kimi-k2.5Fixed	$0.010	$0.010
gemini-2.5-flash-preview-09-2025-searchFixed	$0.010	$0.010
deepseek-v3.2Fixed	$0.010	$0.010
minimax-m2.1Fixed	$0.010	$0.010
gpt-5.1-codex-miniFixed	$0.010	$0.010
deepseek-v3.1Fixed	$0.010	$0.010
deepseek-v3.1-thinkingFixed	$0.010	$0.010
qwen3-maxFixed	$0.010	$0.010
deepseek-v3.1-terminusFixed	$0.010	$0.010
kimi-k2-0711-previewFixed	$0.010	$0.010
gemini-2.5-flash-lite-preview-09-2025-thinkingFixed	$0.010	$0.010
glm-4.7-flashFixed	$0.010	$0.010
MiMo-V2-FlashFixed	$0.010	$0.010
glm-4.5-airFixed	$0.010	$0.010
gemini-2.5-flash-preview-09-2025Fixed	$0.010	$0.010
deepseek-v3.2-expFixed	$0.010	$0.010
Qwen3.5-397BFixed	$0.010	$0.010
deepseek-r1-0528Fixed	$0.010	$0.010

Showing 20 of 214 models.