ChooseC API

统一的 AI 模型聚合网关，一站接入 Claude、GPT、Qwen、DeepSeek、Kimi、GLM 等 260+ 主流大模型，全面兼容 OpenAI / Claude / Gemini 接口。

DeepSeek V4 Flash Qwen2.5 Qwen3 VL GPT-OSS

ChooseC API offers 280 LLM API models.

API pricing per token ranges from $0.050 to $75.00/M (input).

Speed benchmark average: 143 tok/s.

ChooseC API is an API aggregator, offering models from multiple vendors.

Claim this provider

CVerified by C Choose

Avg Speed143.46 tok/s

Latency8.26 s

Updated6/2/2026

Created At12/10/2025

Recharge Rate¥1.00 per $1 quota

Features

TaskData ExportCheck-in

Login Methods

API Endpoints

Endpoint 1
https://ipv4-beta.kxcym.top:3001/v1
Endpoint 2
https://server.kxcym.top:3001/v1
Endpoint 3
https://api.choosec.cn/v1
Endpoint 4Historical / Unverified
https://api.choosec.cn
Endpoint 5Historical / Unverified
https://ipv4-beta.kxcym.top:11434

Supported Models

Model	Speed	Latency	Tests
deepseek-v4-flash	56.37 tok/s	3.93s	5
Qwen/qwen3.5-0.8b	241.83 tok/s	0.59s	5
huihui-ai/Huihui-Qwen3.5-0.8B-abliterated	181.27 tok/s	2.80s	10
qwen3.5-0.8b	354.52 tok/s	0.82s	10
qwen3.5	39.26 tok/s	24.04s	25
HauhauCS/qwen3.5-instruct	56.10 tok/s	1.15s	5
qwen3.5-instruct	55.78 tok/s	1.36s	10
unsloth/qwen3.5-instruct	33.20 tok/s	1.60s	5
huihui-qwen3.5-35b-a3b-abliterated-i1	142.42 tok/s	1.18s	5
huihui_ai/qwen3.5-abliterated:9b	92.02 tok/s	13.99s	5
qwen2.5:1.5b	387.70 tok/s	1.63s	5
huihui_ai/qwen3.5-abliterated:2B-fp16	174.08 tok/s	9.88s	5
qwen3-vl:latest	206.16 tok/s	6.63s	5
gpt-oss:20b	243.42 tok/s	2.62s	5

Available Models

266 models available (last updated: 5/30/2026)

MiniMax-M2minimaxMiniMax-M2.1aliMiniMax-M2.1-highspeedminimaxMiniMax-M2.5aliMiniMax-M2.5-highspeedminimaxMiniMax-M2.7minimaxMiniMax-M2.7-highspeedminimaxclaude-haiku-4-5-20251001claudeclaude-haiku-4-5-20251001-thinkingclaudeclaude-opus-4-5-20251101claudeclaude-opus-4-5-20251101-thinkingclaudeclaude-opus-4-6claudeclaude-opus-4-6-thinkingclaudeclaude-opus-4-7claudeclaude-opus-4-7-thinkingclaudeclaude-opus-4-8claudeclaude-opus-4-8-thinkingclaudeclaude-sonnet-4-5-20250929claudeclaude-sonnet-4-5-20250929-thinkingclaudeclaude-sonnet-4-6claude

Showing 20 of 266 models.

Model

Speed

Latency

Tests

deepseek-v4-flash

56.37 tok/s

3.93s

Qwen/qwen3.5-0.8b

241.83 tok/s

0.59s

huihui-ai/Huihui-Qwen3.5-0.8B-abliterated

181.27 tok/s

2.80s

qwen3.5-0.8b

354.52 tok/s

0.82s

qwen3.5

39.26 tok/s

24.04s

HauhauCS/qwen3.5-instruct

56.10 tok/s

1.15s

qwen3.5-instruct

55.78 tok/s

1.36s

unsloth/qwen3.5-instruct

33.20 tok/s

1.60s

huihui-qwen3.5-35b-a3b-abliterated-i1

142.42 tok/s

1.18s

huihui_ai/qwen3.5-abliterated:9b

92.02 tok/s

13.99s

qwen2.5:1.5b

387.70 tok/s

1.63s

huihui_ai/qwen3.5-abliterated:2B-fp16

174.08 tok/s

9.88s

qwen3-vl:latest

206.16 tok/s

6.63s

gpt-oss:20b

243.42 tok/s

2.62s

Available Models

266 models available (last updated: 5/30/2026)

Showing 20 of 266 models.