{"slug": "deepinfra", "name": "DeepInfra", "category": "ai", "category_name": "AI models and assistants", "description": "Cloud inference platform serving open-weight AI models through a pay-per-token API.", "recommenders": 5, "commenters": 7, "warners": 0, "score": 5.238, "rising": 2.35, "first": "2026-01-21", "latest": "2026-10-09", "why": "Liked for low per-token prices on open models like DeepSeek and GLM, fast responses, and privacy terms that say prompts aren't used for training.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 5, "neutral": 2, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 2, 0], "listed": true, "loved": ["Low cost", "Privacy terms"], "caveat": "Model coverage", "short_quote": "I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast.", "icon": true, "domain": "deepinfra.com", "github_repo": null, "official_url": "https://deepinfra.com", "pricing": "paid", "aliases": ["DeepInfra", "Deepinfra"], "verdict": [{"text": "Liked for low per-token prices on open models like DeepSeek and GLM,", "cites": [{"id": 796706481, "item_id": 49794155, "url": "https://news.ycombinator.com/item?id=49794155", "by": "joshheitzman", "date": "2026-09-21", "stance": "recommend", "quote": "what it costs at deepinfra.com", "excerpt": "Absolutely! DeepSeek-V4-Flash-0731 has become my daily driver. It's pretty amazing what it can do for what it costs at deepinfra.com (I don't use deepseek as a provider since they train on your data [at least their honest about it]). GLM-5.1 was my daily driver before that and Kimi K2.5 before that.", "context": "", "use_case": "inference provider", "switched_from": "", "story": "MiMo v2.6"}, {"id": 747382129, "item_id": 46711383, "url": "https://news.ycombinator.com/item?id=46711383", "by": "wolttam", "date": "2026-01-21", "stance": "neutral", "quote": "pay literally less than $1/month for GLM-4.7 on deepinfra.", "excerpt": "I'm consistently amazed at how much some individuals spend on LLMs. I get a good amount of non-agentic use out of them, and pay literally less than $1/month for GLM-4.7 on deepinfra. I can imagine my costs might rise to $20-ish/month if I used that model for agentic tasks... still a very far cry from the $1000-$1500 some spend.", "context": "", "use_case": "hosted LLM inference", "switched_from": "", "story": "Without benchmarking LLMs, you're likely overpaying 5-10x"}, {"id": 800250994, "item_id": 50015687, "url": "https://news.ycombinator.com/item?id=50015687", "by": "yuhmahp", "date": "2026-10-09", "stance": "neutral", "quote": "DeepSeek 4.1 Flash (hosted on DeepInfra)", "excerpt": "We use Claude Fable to plan, and DeepSeek 4.1 Flash (hosted on DeepInfra) for everything else. Very cost effective.", "context": "", "use_case": "hosting DeepSeek", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}]}, {"text": " fast responses, and privacy terms that say prompts aren't used for training.", "cites": [{"id": 795154672, "item_id": 49697167, "url": "https://news.ycombinator.com/item?id=49697167", "by": "Roark66", "date": "2026-09-14", "stance": "recommend", "quote": "I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast.", "excerpt": "Openrouter is not ideal, because you don't know who they send your traffic to and there are rumours of vendors cheating by providing quantized models. I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast. However I have to caution you about one thing. No one will give you as many input tokens for so little money as Claude Max x5 (maybe x20 too, I use x5). I tend to use 1.1B to 1.4B a wee", "context": "", "use_case": "hosted model inference", "switched_from": "", "story": "Big AI sets out its terms for regulatory capture"}, {"id": 766311728, "item_id": 47894483, "url": "https://news.ycombinator.com/item?id=47894483", "by": "dryarzeg", "date": "2026-04-24", "stance": "recommend", "quote": "DeepInfra is usually being my go-to provider.", "excerpt": "> better privacy terms DeepInfra, as far as I'm aware, doesn't log your prompts and doesn't retain them in most cases, except \"debugging purposes\". As their per their privacy policy[1]: \"We understand that the inputs you provide to our API and the outputs it generates may contain your Personal Information. We will not store, sell, or train using this data unless we have your explicit consent. We might sometimes store", "context": "not a power user of LLMs, curious hobbyist", "use_case": "running large models too big for local hardware", "switched_from": "", "story": "DeepSeek v4"}, {"id": 796706481, "item_id": 49794155, "url": "https://news.ycombinator.com/item?id=49794155", "by": "joshheitzman", "date": "2026-09-21", "stance": "recommend", "quote": "what it costs at deepinfra.com", "excerpt": "Absolutely! DeepSeek-V4-Flash-0731 has become my daily driver. It's pretty amazing what it can do for what it costs at deepinfra.com (I don't use deepseek as a provider since they train on your data [at least their honest about it]). GLM-5.1 was my daily driver before that and Kimi K2.5 before that.", "context": "", "use_case": "inference provider", "switched_from": "", "story": "MiMo v2.6"}]}, {"text": " The main caveats are narrower model coverage than aggregators", "cites": [{"id": 795154672, "item_id": 49697167, "url": "https://news.ycombinator.com/item?id=49697167", "by": "Roark66", "date": "2026-09-14", "stance": "recommend", "quote": "I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast.", "excerpt": "Openrouter is not ideal, because you don't know who they send your traffic to and there are rumours of vendors cheating by providing quantized models. I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast. However I have to caution you about one thing. No one will give you as many input tokens for so little money as Claude Max x5 (maybe x20 too, I use x5). I tend to use 1.1B to 1.4B a wee", "context": "", "use_case": "hosted model inference", "switched_from": "", "story": "Big AI sets out its terms for regulatory capture"}]}, {"text": " and some models being served in quantized fp4 form.", "cites": [{"id": 787493649, "item_id": 49218353, "url": "https://news.ycombinator.com/item?id=49218353", "by": "johnnyApplePRNG", "date": "2026-08-07", "stance": "recommend", "quote": "I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet", "excerpt": "What quantization are you using? Which infra provider? Baseten.co's version got into a loop rather rapidly... I've since added loop detection and adjusted some other settings on the pi coding agent and have yet to notice it again. I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet and it's the top provider on openrouter.ai volume wise.", "context": "", "use_case": "hosting DeepSeek V4 Flash", "switched_from": "Baseten", "story": "DeepSeek V4 Flash 0731"}]}], "praise": [{"label": "Low cost", "summary": "Commenters call it very cost effective, with one paying under $1 a month for light use.", "quotes": [{"id": 747382129, "item_id": 46711383, "url": "https://news.ycombinator.com/item?id=46711383", "by": "wolttam", "date": "2026-01-21", "stance": "neutral", "quote": "pay literally less than $1/month for GLM-4.7 on deepinfra.", "excerpt": "I'm consistently amazed at how much some individuals spend on LLMs. I get a good amount of non-agentic use out of them, and pay literally less than $1/month for GLM-4.7 on deepinfra. I can imagine my costs might rise to $20-ish/month if I used that model for agentic tasks... still a very far cry from the $1000-$1500 some spend.", "context": "", "use_case": "hosted LLM inference", "switched_from": "", "story": "Without benchmarking LLMs, you're likely overpaying 5-10x"}, {"id": 800250994, "item_id": 50015687, "url": "https://news.ycombinator.com/item?id=50015687", "by": "yuhmahp", "date": "2026-10-09", "stance": "neutral", "quote": "DeepSeek 4.1 Flash (hosted on DeepInfra)", "excerpt": "We use Claude Fable to plan, and DeepSeek 4.1 Flash (hosted on DeepInfra) for everything else. Very cost effective.", "context": "", "use_case": "hosting DeepSeek", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 796706481, "item_id": 49794155, "url": "https://news.ycombinator.com/item?id=49794155", "by": "joshheitzman", "date": "2026-09-21", "stance": "recommend", "quote": "what it costs at deepinfra.com", "excerpt": "Absolutely! DeepSeek-V4-Flash-0731 has become my daily driver. It's pretty amazing what it can do for what it costs at deepinfra.com (I don't use deepseek as a provider since they train on your data [at least their honest about it]). GLM-5.1 was my daily driver before that and Kimi K2.5 before that.", "context": "", "use_case": "inference provider", "switched_from": "", "story": "MiMo v2.6"}]}, {"label": "Privacy terms", "summary": "Its policy says it does not store, sell or train on API data without consent, which some prefer to model makers' own APIs.", "quotes": [{"id": 766311728, "item_id": 47894483, "url": "https://news.ycombinator.com/item?id=47894483", "by": "dryarzeg", "date": "2026-04-24", "stance": "recommend", "quote": "DeepInfra is usually being my go-to provider.", "excerpt": "> better privacy terms DeepInfra, as far as I'm aware, doesn't log your prompts and doesn't retain them in most cases, except \"debugging purposes\". As their per their privacy policy[1]: \"We understand that the inputs you provide to our API and the outputs it generates may contain your Personal Information. We will not store, sell, or train using this data unless we have your explicit consent. We might sometimes store", "context": "not a power user of LLMs, curious hobbyist", "use_case": "running large models too big for local hardware", "switched_from": "", "story": "DeepSeek v4"}, {"id": 796706481, "item_id": 49794155, "url": "https://news.ycombinator.com/item?id=49794155", "by": "joshheitzman", "date": "2026-09-21", "stance": "recommend", "quote": "what it costs at deepinfra.com", "excerpt": "Absolutely! DeepSeek-V4-Flash-0731 has become my daily driver. It's pretty amazing what it can do for what it costs at deepinfra.com (I don't use deepseek as a provider since they train on your data [at least their honest about it]). GLM-5.1 was my daily driver before that and Kimi K2.5 before that.", "context": "", "use_case": "inference provider", "switched_from": "", "story": "MiMo v2.6"}, {"id": 772177968, "item_id": 48261123, "url": "https://news.ycombinator.com/item?id=48261123", "by": "h8hawk", "date": "2026-05-24", "stance": "recommend", "quote": "Deepinfra, Take a look at providers, there is special mark for Data Retention for each provider", "excerpt": "Deepinfra, Take a look at providers, there is special mark for Data Retention for each provider: https://openrouter.ai/deepseek/deepseek-v4-pro", "context": "", "use_case": "DeepSeek hosting without data retention", "switched_from": "", "story": "DeepSeek makes the V4 Pro price discount permanent"}]}, {"label": "Coding agents", "summary": "Used as a pay-as-you-go model backend for agents like Pi Coding Agent instead of capped subscriptions.", "quotes": [{"id": 790031745, "item_id": 49376984, "url": "https://news.ycombinator.com/item?id=49376984", "by": "johnnyApplePRNG", "date": "2026-08-20", "stance": "recommend", "quote": "picking and choosing your favorite model's API discounted on flex pricing on deepinfra.com", "excerpt": "Or just take full control of your agentic coding experience with Pi Coding Agent and picking and choosing your favorite model's API discounted on flex pricing on deepinfra.com instead. I highly recommend it. Claude and Codex usage limits cannot be trusted. Paying your own API bills in full is superior.", "context": "", "use_case": "cheap model API access", "switched_from": "", "story": "Clean up Claude 5's token vomit with a separate LLM"}, {"id": 787493649, "item_id": 49218353, "url": "https://news.ycombinator.com/item?id=49218353", "by": "johnnyApplePRNG", "date": "2026-08-07", "stance": "recommend", "quote": "I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet", "excerpt": "What quantization are you using? Which infra provider? Baseten.co's version got into a loop rather rapidly... I've since added loop detection and adjusted some other settings on the pi coding agent and have yet to notice it again. I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet and it's the top provider on openrouter.ai volume wise.", "context": "", "use_case": "hosting DeepSeek V4 Flash", "switched_from": "Baseten", "story": "DeepSeek V4 Flash 0731"}]}, {"label": "Speed", "summary": "Described as quite fast.", "quotes": [{"id": 795154672, "item_id": 49697167, "url": "https://news.ycombinator.com/item?id=49697167", "by": "Roark66", "date": "2026-09-14", "stance": "recommend", "quote": "I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast.", "excerpt": "Openrouter is not ideal, because you don't know who they send your traffic to and there are rumours of vendors cheating by providing quantized models. I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast. However I have to caution you about one thing. No one will give you as many input tokens for so little money as Claude Max x5 (maybe x20 too, I use x5). I tend to use 1.1B to 1.4B a wee", "context": "", "use_case": "hosted model inference", "switched_from": "", "story": "Big AI sets out its terms for regulatory capture"}]}, {"label": "Reliable output", "summary": "One user who switched from Baseten reported no problems so far, despite the fp4 serving.", "quotes": [{"id": 787493649, "item_id": 49218353, "url": "https://news.ycombinator.com/item?id=49218353", "by": "johnnyApplePRNG", "date": "2026-08-07", "stance": "recommend", "quote": "I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet", "excerpt": "What quantization are you using? Which infra provider? Baseten.co's version got into a loop rather rapidly... I've since added loop detection and adjusted some other settings on the pi coding agent and have yet to notice it again. I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet and it's the top provider on openrouter.ai volume wise.", "context": "", "use_case": "hosting DeepSeek V4 Flash", "switched_from": "Baseten", "story": "DeepSeek V4 Flash 0731"}]}], "caveats": [{"label": "Model coverage", "summary": "It offers fewer models than aggregators like OpenRouter.", "quotes": [{"id": 795154672, "item_id": 49697167, "url": "https://news.ycombinator.com/item?id=49697167", "by": "Roark66", "date": "2026-09-14", "stance": "recommend", "quote": "I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast.", "excerpt": "Openrouter is not ideal, because you don't know who they send your traffic to and there are rumours of vendors cheating by providing quantized models. I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast. However I have to caution you about one thing. No one will give you as many input tokens for so little money as Claude Max x5 (maybe x20 too, I use x5). I tend to use 1.1B to 1.4B a wee", "context": "", "use_case": "hosted model inference", "switched_from": "", "story": "Big AI sets out its terms for regulatory capture"}]}, {"label": "Quantized models", "summary": "Some models are served as fp4 quantizations.", "quotes": [{"id": 787493649, "item_id": 49218353, "url": "https://news.ycombinator.com/item?id=49218353", "by": "johnnyApplePRNG", "date": "2026-08-07", "stance": "recommend", "quote": "I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet", "excerpt": "What quantization are you using? Which infra provider? Baseten.co's version got into a loop rather rapidly... I've since added loop detection and adjusted some other settings on the pi coding agent and have yet to notice it again. I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet and it's the top provider on openrouter.ai volume wise.", "context": "", "use_case": "hosting DeepSeek V4 Flash", "switched_from": "Baseten", "story": "DeepSeek V4 Flash 0731"}]}, {"label": "Privacy limits", "summary": "It is not EU-based and may keep inputs and outputs for a limited time for debugging.", "quotes": [{"id": 766311728, "item_id": 47894483, "url": "https://news.ycombinator.com/item?id=47894483", "by": "dryarzeg", "date": "2026-04-24", "stance": "recommend", "quote": "DeepInfra is usually being my go-to provider.", "excerpt": "> better privacy terms DeepInfra, as far as I'm aware, doesn't log your prompts and doesn't retain them in most cases, except \"debugging purposes\". As their per their privacy policy[1]: \"We understand that the inputs you provide to our API and the outputs it generates may contain your Personal Information. We will not store, sell, or train using this data unless we have your explicit consent. We might sometimes store", "context": "not a power user of LLMs, curious hobbyist", "use_case": "running large models too big for local hardware", "switched_from": "", "story": "DeepSeek v4"}]}, {"label": "Heavy-use cost", "summary": "For very high token volumes, a Claude Max subscription can still be cheaper than API pricing.", "quotes": [{"id": 795154672, "item_id": 49697167, "url": "https://news.ycombinator.com/item?id=49697167", "by": "Roark66", "date": "2026-09-14", "stance": "recommend", "quote": "I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast.", "excerpt": "Openrouter is not ideal, because you don't know who they send your traffic to and there are rumours of vendors cheating by providing quantized models. I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast. However I have to caution you about one thing. No one will give you as many input tokens for so little money as Claude Max x5 (maybe x20 too, I use x5). I tend to use 1.1B to 1.4B a wee", "context": "", "use_case": "hosted model inference", "switched_from": "", "story": "Big AI sets out its terms for regulatory capture"}]}], "who": [{"by": "dryarzeg", "context": "not a power user of LLMs, curious hobbyist", "url": "https://news.ycombinator.com/item?id=47894483", "date": "2026-04-24"}], "tags": ["for agentic coding", "for open-weight models", "for privacy-conscious users", "for budget users", "for hobbyists"], "use_cases": ["hosting deepseek", "inference provider", "hosted model inference", "cheap model api access", "hosting deepseek v4 flash", "deepseek hosting without data retention"], "compared": [{"slug": "pi", "name": "Pi", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "baseten", "name": "Baseten", "co": 1, "switched_from": 1, "switched_to": 0}, {"slug": "deepseek-v4-flash", "name": "DeepSeek V4 Flash", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "openrouter", "name": "OpenRouter", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "glm", "name": "GLM", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=50000488", "title": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49792730", "title": "MiMo v2.6", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49694596", "title": "Big AI sets out its terms for regulatory capture", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49375996", "title": "Clean up Claude 5's token vomit with a separate LLM", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49214008", "title": "DeepSeek V4 Flash 0731", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48237663", "title": "DeepSeek makes the V4 Pro price discount permanent", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"neutral": 1}, "2026-02": {}, "2026-03": {}, "2026-04": {"recommend": 1}, "2026-05": {"recommend": 1}, "2026-06": {}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {"recommend": 2}, "2026-10": {"neutral": 1}}, "quotes": [{"id": 800250994, "item_id": 50015687, "url": "https://news.ycombinator.com/item?id=50015687", "by": "yuhmahp", "date": "2026-10-09", "stance": "neutral", "quote": "DeepSeek 4.1 Flash (hosted on DeepInfra)", "excerpt": "We use Claude Fable to plan, and DeepSeek 4.1 Flash (hosted on DeepInfra) for everything else. Very cost effective.", "context": "", "use_case": "hosting DeepSeek", "switched_from": "", "story": "Why isn't the industry freaking out about DeepSeek 4.1 Flash?"}, {"id": 796706481, "item_id": 49794155, "url": "https://news.ycombinator.com/item?id=49794155", "by": "joshheitzman", "date": "2026-09-21", "stance": "recommend", "quote": "what it costs at deepinfra.com", "excerpt": "Absolutely! DeepSeek-V4-Flash-0731 has become my daily driver. It's pretty amazing what it can do for what it costs at deepinfra.com (I don't use deepseek as a provider since they train on your data [at least their honest about it]). GLM-5.1 was my daily driver before that and Kimi K2.5 before that.", "context": "", "use_case": "inference provider", "switched_from": "", "story": "MiMo v2.6"}, {"id": 795154672, "item_id": 49697167, "url": "https://news.ycombinator.com/item?id=49697167", "by": "Roark66", "date": "2026-09-14", "stance": "recommend", "quote": "I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast.", "excerpt": "Openrouter is not ideal, because you don't know who they send your traffic to and there are rumours of vendors cheating by providing quantized models. I'm very happy with Deepinfra. Less model coverage, but good prices and quite fast. However I have to caution you about one thing. No one will give you as many input tokens for so little money as Claude Max x5 (maybe x20 too, I use x5). I tend to use 1.1B to 1.4B a wee", "context": "", "use_case": "hosted model inference", "switched_from": "", "story": "Big AI sets out its terms for regulatory capture"}, {"id": 790031745, "item_id": 49376984, "url": "https://news.ycombinator.com/item?id=49376984", "by": "johnnyApplePRNG", "date": "2026-08-20", "stance": "recommend", "quote": "picking and choosing your favorite model's API discounted on flex pricing on deepinfra.com", "excerpt": "Or just take full control of your agentic coding experience with Pi Coding Agent and picking and choosing your favorite model's API discounted on flex pricing on deepinfra.com instead. I highly recommend it. Claude and Codex usage limits cannot be trusted. Paying your own API bills in full is superior.", "context": "", "use_case": "cheap model API access", "switched_from": "", "story": "Clean up Claude 5's token vomit with a separate LLM"}, {"id": 787493649, "item_id": 49218353, "url": "https://news.ycombinator.com/item?id=49218353", "by": "johnnyApplePRNG", "date": "2026-08-07", "stance": "recommend", "quote": "I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet", "excerpt": "What quantization are you using? Which infra provider? Baseten.co's version got into a loop rather rapidly... I've since added loop detection and adjusted some other settings on the pi coding agent and have yet to notice it again. I also switched to DeepInfra ... who serves an fp4 version admittedly, but I've had no issues with it as of yet and it's the top provider on openrouter.ai volume wise.", "context": "", "use_case": "hosting DeepSeek V4 Flash", "switched_from": "Baseten", "story": "DeepSeek V4 Flash 0731"}, {"id": 772177968, "item_id": 48261123, "url": "https://news.ycombinator.com/item?id=48261123", "by": "h8hawk", "date": "2026-05-24", "stance": "recommend", "quote": "Deepinfra, Take a look at providers, there is special mark for Data Retention for each provider", "excerpt": "Deepinfra, Take a look at providers, there is special mark for Data Retention for each provider: https://openrouter.ai/deepseek/deepseek-v4-pro", "context": "", "use_case": "DeepSeek hosting without data retention", "switched_from": "", "story": "DeepSeek makes the V4 Pro price discount permanent"}, {"id": 766311728, "item_id": 47894483, "url": "https://news.ycombinator.com/item?id=47894483", "by": "dryarzeg", "date": "2026-04-24", "stance": "recommend", "quote": "DeepInfra is usually being my go-to provider.", "excerpt": "> better privacy terms DeepInfra, as far as I'm aware, doesn't log your prompts and doesn't retain them in most cases, except \"debugging purposes\". As their per their privacy policy[1]: \"We understand that the inputs you provide to our API and the outputs it generates may contain your Personal Information. We will not store, sell, or train using this data unless we have your explicit consent. We might sometimes store", "context": "not a power user of LLMs, curious hobbyist", "use_case": "running large models too big for local hardware", "switched_from": "", "story": "DeepSeek v4"}, {"id": 747382129, "item_id": 46711383, "url": "https://news.ycombinator.com/item?id=46711383", "by": "wolttam", "date": "2026-01-21", "stance": "neutral", "quote": "pay literally less than $1/month for GLM-4.7 on deepinfra.", "excerpt": "I'm consistently amazed at how much some individuals spend on LLMs. I get a good amount of non-agentic use out of them, and pay literally less than $1/month for GLM-4.7 on deepinfra. I can imagine my costs might rise to $20-ish/month if I used that model for agentic tasks... still a very far cry from the $1000-$1500 some spend.", "context": "", "use_case": "hosted LLM inference", "switched_from": "", "story": "Without benchmarking LLMs, you're likely overpaying 5-10x"}]}