Danh sách Model
DeepSeek V4 Flash
DeepSeek fast and cost-efficient model with 1M context window. Supports function calling, prompt caching, and reasoning.
- Context
- 1M
- In / 1M
- 11.532₫
- Out / 1M
- 34.597₫
GPT-5.6 Luna
OpenAI's fastest and most affordable GPT-5.6 tier with 1.05M context window. Optimized for cost-sensitive, high-volume workloads with function calling, vision, and prompt caching.
- Context
- 1.1M
- In / 1M
- 5.242₫
- Out / 1M
- 31.452₫
Qwen3.8 27B
Self-hosted Qwen 3.8 27B dense multimodal model with hybrid attention (Gated DeltaNet + GQA). 262K native context extensible to 1M. Accepts text, image, and video input with reasoning, function calling, and agentic capabilities.
- Context
- 262K
- In / 1M
- 11.795₫
- Out / 1M
- 83.872₫
MiniMax M3
MiniMax flagship model with 1M context window, supporting vision, reasoning, and prompt caching with tiered pricing above 512K tokens.
- Context
- 1M
- In / 1M
- 7.863₫
- Out / 1M
- 31.452₫
Claude Sonnet 4.6
Anthropic's balanced model with 1M context window. Fast, capable, and cost-efficient with adaptive thinking, computer use, and vision support.
- Context
- 1M
- In / 1M
- 78.630₫
- Out / 1M
- 393.150₫
Grok 4.3
xAI's flagship reasoning model with 1M context window. Well-suited for long-document analysis, deep research, and multi-step agentic tasks.
- Context
- 1M
- In / 1M
- 32.763₫
- Out / 1M
- 65.525₫
Qwen3.8 Flash
Alibaba's fast and cost-efficient Qwen 3.8 model via DashScope. 1M context with vision, reasoning, and function calling.
- Context
- 1M
- In / 1M
- 3.932₫
- Out / 1M
- 12.319₫
GPT-4o
OpenAI's versatile multimodal model with 128K context window. Accepts text and image inputs with function calling, structured outputs, and vision support.
- Context
- 128K
- In / 1M
- 65.525₫
- Out / 1M
- 262.100₫
Kimi K2.6
Moonshot AI's flagship model with 262K context window. Supports vision, video input, reasoning, and function calling. $0.95/1M input, $4/1M output.
- Context
- 262K
- In / 1M
- 24.900₫
- Out / 1M
- 104.840₫
Gemini 3.5 Flash
Google's latest fast and capable model from the Gemini 3.5 family. 1M context, multimodal inputs, reasoning, and function calling.
- Context
- 1.0M
- In / 1M
- 39.315₫
- Out / 1M
- 235.890₫
Gemini 3.1 Flash Image Preview
Google's fast image generation model from the Gemini 3.1 family. $0.067 per output image. Preview.
- Context
- 66K
- Giá / ảnh
- 1.761₫
Claude Opus 4.8
Anthropic's frontier model with 1M context, adaptive thinking, computer use, and extended thinking capabilities for complex professional workloads.
- Context
- 1M
- In / 1M
- 131.050₫
- Out / 1M
- 655.250₫
Jina Reranker v2
Jina AI's multilingual reranking model with 1024 token context and automatic chunking for longer documents. 10M free tokens per API key.
- Context
- 1K
- Giá / truy vấn
- 0,52₫
Cohere Rerank v3.5
Cohere's reranking model for improved search relevance. Supports multi-aspect and semi-structured data reranking over 100+ languages. $0.002 per search.
- Context
- 4K
- Giá / truy vấn
- 52₫
ElevenLabs Scribe v1
ElevenLabs' speech recognition model with 99 language support. $0.22 per hour of audio.
- Context
- —
- Giá / phút
- 96₫