模型广场

选择模型后可复制配置给 AI，也可以快速测试当前连接延迟。

重置筛选

全部 7文本 7图像 0音频 0视频 0

gemma-3n-e4b-it:free

文本图像视频音频文本

Google

Fast and cost-efficient.

上下文: 33K
输入 / 1M tokens: $0.06
输出 / 1M tokens: $0.12
缓存读 / 1M: $0
缓存写 / 1M: $0

ChatReal-time ResponseClassification

lfm-2.5-1.2b-instruct:free

文本文本

liquid

Instruction-tuned optimization for precise execution.

上下文: 8K
输入 / 1M tokens: $0
输出 / 1M tokens: $0
缓存读 / 1M: -
缓存写 / 1M: -

Instruction FollowingTask AutomationStructured Output

nemotron-3-nano-30b-a3b:free

文本文本

nvidia

Balanced powerful model.

上下文: 131K
输入 / 1M tokens: $0
输出 / 1M tokens: $0
缓存读 / 1M: $0
缓存写 / 1M: -

High-Quality GenerationReasoningBalanced Performance

gpt-5-nano

文本图像文本

OpenAI

Cheapest GPT. Built for high-volume simple jobs.

上下文: 400K
输入 / 1M tokens: $0.05
输出 / 1M tokens: $0.4
缓存读 / 1M: $0.01
缓存写 / 1M: $0

Cost Effective

qwen3.5-27b

文本图像视频文本

qwen

Mid-tier Qwen model tuned for multi-step reasoning and agent workflows, compact enough for private and on-prem deployment.

上下文: 262K
输入 / 1M tokens: $0.086
输出 / 1M tokens: $0.688
缓存读 / 1M: $0
缓存写 / 1M: $0

ReasoningCodingChain of ThoughtLocal Deployment

qwen3.5-flash

文本图像视频文本

qwen

Lightweight mid-tier variant tuned for low-latency agent workflows with coding and tool-calling support.

上下文: 1M
输入 / 1M tokens: $0.029
输出 / 1M tokens: $0.287
缓存读 / 1M: $0.003
缓存写 / 1M: $0.036

CodingLong Text ProcessingReal-time ResponseLightweight

qwen3.7-flash

文本图像视频文本

qwen

Qwen3.7 Flash is the lightweight tier in the series, a vision-language reasoning model with strengths in object recognition, spatial understanding, and real-world visual perception. Suited for multimodal agents, visual coding, search, and computer interaction.

上下文: 1M
输入 / 1M tokens: $0.03
输出 / 1M tokens: $0.13
缓存读 / 1M: $0.006
缓存写 / 1M: $0.038

ReasoningVisionCost EffectiveLong Text Processing

需要完整模型清单或企业接入方案？进入控制台