command-a-reasoning-08-2025command-a
Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows
256,000 tokens→MODEL PRICE INDEX
模型比价
先确定模型版本，再查看各服务商的渠道、输入输出价格和核验状态。
command-a-translate-08-2025command-a
Translation model for multilingual conversion, localization, and cross-language workflows
8,000 tokens→command-a-vision-07-2025command-a
Cohere vision model for multilingual document analysis, OCR, and image understanding
128,000 tokens→command-r-08-2024command-r
Cohere retrieval model for long-context chat and enterprise RAG workflows
128,000 tokens→command-r7b-12-2024command-r
Cohere retrieval model for long-context chat and enterprise RAG workflows
128,000 tokens→command-r7b-arabic-02-2025command-r
Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge
128,000 tokens→command-r-plus-08-2024command-r
Cohere's RAG workhorse for long-context enterprise search and tool use
128,000 tokens→north-mini-code-1-0north
Cohere coding model for practical software engineering and agentic edits
256,000 tokens→Open-weight translation model for more than 50 languages and locale variants
32,768 tokens→Open multilingual model optimized for generation across 23 languages
128,000 tokens→Open multilingual vision model for OCR, visual reasoning, and image question answering
16,000 tokens→tiny-aya-earth其他模型
Compact multilingual model specialized for West Asian and African languages
8,000 tokens→tiny-aya-fire其他模型
Compact multilingual model specialized for South Asian languages
8,000 tokens→tiny-aya-global其他模型
Compact multilingual model balanced across 70 languages and regions
8,000 tokens→tiny-aya-water其他模型
Compact multilingual model specialized for European and Asia-Pacific languages
8,000 tokens→deepseek-flashdeepseek-flash
October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
1,048,576 tokens→deepseek-v4-flashdeepseek-flash
October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
1,048,576 tokens→deepseek-v4-flash-vision-expdeepseek-flash
October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding
1,048,576 tokens→deepseek-v4-prodeepseek-thinking
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
1,048,576 tokens→gemini-4-argongemini
Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents
1,048,576 tokens→