deepseek-v4-flash
DeepSeek
Faster, lower-cost variant of DeepSeek V4, optimized for coding assistants, high-throughput chat, and latency-sensitive Agent workflows.
- 上下文
- 1M
- 输入 / 1M tokens
- $0.22
- 输出 / 1M tokens
- $0.66
- 缓存读 / 1M
- $0.007
- 缓存写 / 1M
- $0
apiex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 12文本 12图像 0音频 0视频 0
gpt-4o-mini
OpenAI
A lightweight model tuned for low-cost, low-latency text tasks like chatbots, summarization, and bulk classification.
- 上下文
- 128K
- 输入 / 1M tokens
- $0.15
- 输出 / 1M tokens
- $0.6
- 缓存读 / 1M
- $0.075
- 缓存写 / 1M
- $0
qwen3-vl-8b-instruct
qwen
Lightweight multimodal model with balanced performance.
- 上下文
- 128K
- 输入 / 1M tokens
- $0.25
- 输出 / 1M tokens
- $0.75
- 缓存读 / 1M
- $0.12
- 缓存写 / 1M
- $0
qwen3.5-122b-a10b
qwen
Open-weight mid-tier MoE text model with long chain-of-thought reasoning, strong on function-calling and multi-step planning benchmarks for self-hosted agentic workflows.
- 上下文
- 262K
- 输入 / 1M tokens
- $0.115
- 输出 / 1M tokens
- $0.917
- 缓存读 / 1M
- $0
- 缓存写 / 1M
- $0
qwen3.5-27b
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
qwen3.5-plus
qwen
Multimodal model from the Qwen3.5 line with toggleable thinking mode, tuned for image and video understanding, document parsing, and multimodal agents.
- 上下文
- 1M
- 输入 / 1M tokens
- $0.115
- 输出 / 1M tokens
- $0.688
- 缓存读 / 1M
- $0.057
- 缓存写 / 1M
- $0.717
qwen3.6-flash
qwen
Qwen 3.6 lightweight tier with text, image, and video input. Low latency and low cost, well-suited for high-volume classification, extraction, summarization, and simple agent workflows.
- 上下文
- 1M
- 输入 / 1M tokens
- $0.165
- 输出 / 1M tokens
- $0.99
- 缓存读 / 1M
- $0
- 缓存写 / 1M
- $0
hy3
tencent
A 295B MoE reasoning model from Tencent with 21B active parameters, configurable reasoning effort, and a 262K context window. It is designed for agentic workflows, long-horizon tasks, coding, document processing, and financial analysis, with an emphasis on reliable tool use and reduced hallucinations.
- 上下文
- 262K
- 输入 / 1M tokens
- $0.132
- 输出 / 1M tokens
- $0.528
- 缓存读 / 1M
- $0.033
- 缓存写 / 1M
- $0
hy3-preview
tencent
Hy3 preview in high-reasoning mode, built for complex problem solving and multi-step agent workflows that need dependable execution.
- 上下文
- 262K
- 输入 / 1M tokens
- $0.18
- 输出 / 1M tokens
- $0.6
- 缓存读 / 1M
- $0.06
- 缓存写 / 1M
- $0
mimo-v2.5-pro
xiaomi
Flagship coding and agent model that sustains thousand-tool-call autonomous workflows for complex software engineering.
- 上下文
- 1M
- 输入 / 1M tokens
- $0.435
- 输出 / 1M tokens
- $0.87
- 缓存读 / 1M
- $0.0036
- 缓存写 / 1M
- $0
glm-4.6v
Z.ai
Multimodal model with strong image + text understanding.
- 上下文
- 128K
- 输入 / 1M tokens
- $0.3
- 输出 / 1M tokens
- $0.9
- 缓存读 / 1M
- $0.055
- 缓存写 / 1M
- $0
glm-5.3-flash
Z.ai
Flash tier of GLM-5.3: native multimodal inputs, suited for efficient coding and long-horizon agents with stable long-context behavior in production.
- 上下文
- 1M
- 输入 / 1M tokens
- $0.15
- 输出 / 1M tokens
- $0.5
- 缓存读 / 1M
- $0.03
- 缓存写 / 1M
- $0
需要完整模型清单或企业接入方案？进入控制台