{"slug": "deepseek-api", "name": "DeepSeek API", "category": "ai", "category_name": "AI tools and apps", "description": "", "recommenders": 6, "commenters": 9, "warners": 1, "score": 4.994, "rising": 0.69, "first": "2026-04-23", "latest": "2026-10-18", "why": "with 2$ I was able to get around 120M tokens from deepseek easily", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 1, "compare": 1, "warn": 1}, "spark": [0, 0, 0, 0, 0, 2, 0, 2, 0, 1, 1, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "with 2$ I was able to get around 120M tokens from deepseek easily", "kind": "", "icon": true, "domain": "deepseek.com", "github_repo": null, "official_url": "https://www.deepseek.com", "pricing": "", "aliases": ["DeepSeek API"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 794031744, "item_id": 49626984, "url": "https://news.ycombinator.com/item?id=49626984", "by": "_aavaa_", "date": "2026-09-09", "version": null, "stance": "recommend", "quote": "Each one is now cheaper.", "excerpt": "Yes, and? This is their current off-peak pricing for their flash model [0]: $0.007 cache, $0.22 input, $0.66. 0.007 -> 0.003 0.22 -> 0.15 0.66 -> 0.60 Each one is now cheaper. [0]: https://api-docs.deepseek.com/quick_start/pricing/", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro"}, {"id": 788399521, "item_id": 49274970, "url": "https://news.ycombinator.com/item?id=49274970", "by": "vermaabhishek39", "date": "2026-08-12", "version": null, "stance": "recommend", "quote": "I've been heavily using Pane with Deepseek API and it costs me less than 10$ a month.", "excerpt": "How I use pane: - I use pane like a browser and a journal. - Since I do all my work in Pane, whenever I have something -> I just let it know by saying simple things like: \"applied to this\", \"got this response\", \"this guy reached out\"; without the need to give any additional context, because it already has the context. - I don't care about the response at this time. - Behind the scenes, Pane builds PI (Personalised In", "context": "", "use_case": "LLM backend for Pane", "switched_from": "", "story": "Show HN: Pane \u2013 An open-source browser that turns your work into living websites"}, {"id": 778711985, "item_id": 48669499, "url": "https://news.ycombinator.com/item?id=48669499", "by": "tacomagick", "date": "2026-06-24", "version": null, "stance": "recommend", "quote": "with 2$ I was able to get around 120M tokens from deepseek easily", "excerpt": "For my case Openrouter breaks Deepseek caching and charges me multiple times over what I pay for Deepseek's API, with 2$ I was able to get around 120M tokens from deepseek easily when Openrouter could only barely do 250k", "context": "", "use_case": "cheap LLM token usage", "switched_from": "", "story": "GLM-5.2 is the step change for open agents"}, {"id": 775150129, "item_id": 48446883, "url": "https://news.ycombinator.com/item?id=48446883", "by": "twotwotwo", "date": "2026-06-08", "version": null, "stance": "recommend", "quote": "They don't have the super-cheap cache reads deal that DeepSeek's own endpoint does", "excerpt": "If you worry about sending your data off for inference, Fireworks is one of the companies serving open models with solid performance and compliance/zero data retention sorted out. OpenCode supports them and many others. Cursor uses them. They don't have the super-cheap cache reads deal that DeepSeek's own endpoint does, but are still well below Anthropic API rates. (Though importantly, you're not paying API rates!) D", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek V4 Pro beats GPT-5.5 Pro on precision"}, {"id": 766180560, "item_id": 47886285, "url": "https://news.ycombinator.com/item?id=47886285", "by": "throwa356262", "date": "2026-04-23", "version": null, "stance": "recommend", "quote": "Seriously, why can't huge companies like OpenAI and Google produce documentation that is half this good??", "excerpt": "Seriously, why can't huge companies like OpenAI and Google produce documentation that is half this good?? https://api-docs.deepseek.com/guides/thinking_mode No BS, just a concise description of exactly what I need to write my own agent.", "context": "", "use_case": "Building an AI agent", "switched_from": "", "story": "DeepSeek v4"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 802249025, "item_id": 50140564, "url": "https://news.ycombinator.com/item?id=50140564", "by": "apwheele", "date": "2026-10-18", "version": null, "stance": "warn", "quote": "the fact DeepSeek API is not zero data retention I cannot get over", "excerpt": "I am currently using Perplexity for https://veruscite.com/. Verify citations actually exist -- so get in a list of 100, half I can check with crossref, but the other half I need to do a web search and fetch to make sure they exist. So I need higher rate limits to not make the tool come to a crawl. I probably will not consider DeepSeek API here (I have tried DeepSeek hosted at US providers, like Perplexity). The other", "context": "", "use_case": "web search and fetch", "switched_from": "", "story": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests"}]}], "who": [], "tags": [], "use_cases": ["web search and fetch", "llm backend for pane", "cheap llm token usage", "custom terminal coding agent", "building an ai agent"], "compared": [{"slug": "openrouter", "name": "OpenRouter", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 3, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=47884971", "title": "DeepSeek v4", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50138531", "title": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49624603", "title": "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49274936", "title": "Show HN: Pane \u2013 An open-source browser that turns your work into living websites", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49134297", "title": "DeepSeek's Plan for AGI Is the Costco Hot Dog", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48639840", "title": "GLM-5.2 is the step change for open agents", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 2}, "2026-05": {"neutral": 1}, "2026-06": {"recommend": 2}, "2026-07": {}, "2026-08": {"compare": 1, "recommend": 1}, "2026-09": {"recommend": 1}, "2026-10": {"warn": 1}}, "versions": [], "version_unnamed": 0, "family_ref": null, "runs_on": null, "lines": [], "quotes": [{"id": 802249025, "item_id": 50140564, "url": "https://news.ycombinator.com/item?id=50140564", "by": "apwheele", "date": "2026-10-18", "version": null, "stance": "warn", "quote": "the fact DeepSeek API is not zero data retention I cannot get over", "excerpt": "I am currently using Perplexity for https://veruscite.com/. Verify citations actually exist -- so get in a list of 100, half I can check with crossref, but the other half I need to do a web search and fetch to make sure they exist. So I need higher rate limits to not make the tool come to a crawl. I probably will not consider DeepSeek API here (I have tried DeepSeek hosted at US providers, like Perplexity). The other", "context": "", "use_case": "web search and fetch", "switched_from": "", "story": "DeepSeek search and fetch \u2013 $0.75 per 1000 successful requests"}, {"id": 794031744, "item_id": 49626984, "url": "https://news.ycombinator.com/item?id=49626984", "by": "_aavaa_", "date": "2026-09-09", "version": null, "stance": "recommend", "quote": "Each one is now cheaper.", "excerpt": "Yes, and? This is their current off-peak pricing for their flash model [0]: $0.007 cache, $0.22 input, $0.66. 0.007 -> 0.003 0.22 -> 0.15 0.66 -> 0.60 Each one is now cheaper. [0]: https://api-docs.deepseek.com/quick_start/pricing/", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro"}, {"id": 788399521, "item_id": 49274970, "url": "https://news.ycombinator.com/item?id=49274970", "by": "vermaabhishek39", "date": "2026-08-12", "version": null, "stance": "recommend", "quote": "I've been heavily using Pane with Deepseek API and it costs me less than 10$ a month.", "excerpt": "How I use pane: - I use pane like a browser and a journal. - Since I do all my work in Pane, whenever I have something -> I just let it know by saying simple things like: \"applied to this\", \"got this response\", \"this guy reached out\"; without the need to give any additional context, because it already has the context. - I don't care about the response at this time. - Behind the scenes, Pane builds PI (Personalised In", "context": "", "use_case": "LLM backend for Pane", "switched_from": "", "story": "Show HN: Pane \u2013 An open-source browser that turns your work into living websites"}, {"id": 786208272, "item_id": 49138017, "url": "https://news.ycombinator.com/item?id=49138017", "by": "VulgarExigency", "date": "2026-08-01", "version": null, "stance": "compare", "quote": "It's not as cheap as Deepseek's own API offering", "excerpt": "> The Chinese government has deep pockets. They can probably run at a loss for a long time and don't have to worry about it. It's not as cheap as Deepseek's own API offering, but there are multiple providers on Openrouter who are serving Flash V4 at an extremely low price. Is the Chinese government also subsidizing them? https://openrouter.ai/deepseek/deepseek-v4-flash-0731", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek's Plan for AGI Is the Costco Hot Dog"}, {"id": 778711985, "item_id": 48669499, "url": "https://news.ycombinator.com/item?id=48669499", "by": "tacomagick", "date": "2026-06-24", "version": null, "stance": "recommend", "quote": "with 2$ I was able to get around 120M tokens from deepseek easily", "excerpt": "For my case Openrouter breaks Deepseek caching and charges me multiple times over what I pay for Deepseek's API, with 2$ I was able to get around 120M tokens from deepseek easily when Openrouter could only barely do 250k", "context": "", "use_case": "cheap LLM token usage", "switched_from": "", "story": "GLM-5.2 is the step change for open agents"}, {"id": 775150129, "item_id": 48446883, "url": "https://news.ycombinator.com/item?id=48446883", "by": "twotwotwo", "date": "2026-06-08", "version": null, "stance": "recommend", "quote": "They don't have the super-cheap cache reads deal that DeepSeek's own endpoint does", "excerpt": "If you worry about sending your data off for inference, Fireworks is one of the companies serving open models with solid performance and compliance/zero data retention sorted out. OpenCode supports them and many others. Cursor uses them. They don't have the super-cheap cache reads deal that DeepSeek's own endpoint does, but are still well below Anthropic API rates. (Though importantly, you're not paying API rates!) D", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek V4 Pro beats GPT-5.5 Pro on precision"}, {"id": 773403504, "item_id": 48337719, "url": "https://news.ycombinator.com/item?id=48337719", "by": "Kuyawa", "date": "2026-05-30", "version": null, "stance": "neutral", "quote": "it connects to DeepSeek API", "excerpt": "I use a custom coding agent for terminal that uses file tools to read and write to my local file system and nothing else, it connects to DeepSeek API. I start with a prompt to build an app and I enjoy the show as it spits line by line its thought process and in a couple of minutes the final result.", "context": "", "use_case": "custom terminal coding agent", "switched_from": "", "story": "Ask HK: How are you building AI apps today?"}, {"id": 766191537, "item_id": 47886971, "url": "https://news.ycombinator.com/item?id=47886971", "by": "u_sama", "date": "2026-04-24", "version": null, "stance": "recommend", "quote": "", "excerpt": "I am very partial to Mistral's API docs https://docs.mistral.ai/api", "context": "", "use_case": "", "switched_from": "", "story": "DeepSeek v4"}, {"id": 766180560, "item_id": 47886285, "url": "https://news.ycombinator.com/item?id=47886285", "by": "throwa356262", "date": "2026-04-23", "version": null, "stance": "recommend", "quote": "Seriously, why can't huge companies like OpenAI and Google produce documentation that is half this good??", "excerpt": "Seriously, why can't huge companies like OpenAI and Google produce documentation that is half this good?? https://api-docs.deepseek.com/guides/thinking_mode No BS, just a concise description of exactly what I need to write my own agent.", "context": "", "use_case": "Building an AI agent", "switched_from": "", "story": "DeepSeek v4"}]}