https://modelsite.ai/en/blog/ Practical guides to calling and pricing LLM APIs: DeepSeek, Qwen, GLM and more through one key. en Fri, 06 Nov 2026 20:49:21 +0800 https://modelsite.ai/en/blog/deepseek-v41-flash-1017-review/ https://modelsite.ai/en/blog/deepseek-v41-flash-1017-review/ Fri, 06 Nov 2026 20:49:21 +0800 OpenRouter's weekly data shows DeepSeek V4.1 Flash 1017 as the most-used LLM at 56.5T tokens. What the numbers do and do not say, plus live prices. https://modelsite.ai/en/blog/prompt-caching-cache-hit-pricing-explained/ https://modelsite.ai/en/blog/prompt-caching-cache-hit-pricing-explained/ Thu, 22 Oct 2026 18:22:26 +0800 Cache read tokens cost a fraction of normal input tokens, and the fraction differs a lot by model. Live prices, a worked example and how to get more hits. https://modelsite.ai/en/blog/who-pays-for-ai-spend-concentration/ https://modelsite.ai/en/blog/who-pays-for-ai-spend-concentration/ Thu, 22 Oct 2026 13:59:10 +0800 a16z's October 2026 data shows consumer AI spend concentrated in a few heavy users. What that means when choosing between plans and pay-per-token. https://modelsite.ai/en/blog/llm-api-vs-chat-subscription/ https://modelsite.ai/en/blog/llm-api-vs-chat-subscription/ Thu, 22 Oct 2026 09:48:56 +0800 A flat monthly plan and a per-token API solve different problems. How to tell which is cheaper for you, with a break-even check and sourced data. https://modelsite.ai/en/blog/deepseek-qwen-glm-api-pricing-compared/ https://modelsite.ai/en/blog/deepseek-qwen-glm-api-pricing-compared/ Thu, 22 Oct 2026 09:24:10 +0800 Per-million-token prices for DeepSeek V4.1 Flash 1017, Qwen3.7 and Qwen3.8 Max, GLM-5.3 and MiniMax-M3, read live from the ModelSite catalog. https://modelsite.ai/en/blog/one-api-key-deepseek-qwen-glm/ https://modelsite.ai/en/blog/one-api-key-deepseek-qwen-glm/ Thu, 22 Oct 2026 09:24:10 +0800 Use one API key and the OpenAI SDK to call DeepSeek, Qwen and GLM. Change the model name, keep your code. Includes curl, Python and live prices.