--- title: MiniMax M3.1 Flash is cheap, free this week, and everywhere description: MiniMax M3.1 Flash launched on OpenRouter under the stealth name 'Space Bunny' with aggressive distribution: day-0 serving support from vLLM (native NVFP4 KV... canonical: https://daily.dev/posts/minimax-m3-1-flash-is-cheap-free-this-week-and-everywhere-7uccejy7e twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: MiniMax M3.1 Flash is cheap, free this week, and everywhere | daily.dev og:description: MiniMax M3.1 Flash launched on OpenRouter under the stealth name 'Space Bunny' with aggressive distribution: day-0 serving support from vLLM (native NVFP4 KV... og:url: https://daily.dev/posts/minimax-m3-1-flash-is-cheap-free-this-week-and-everywhere-7uccejy7e og:image: https://api.daily.dev/og/posts/7UCceJy7E.png og:image:alt: MiniMax M3.1 Flash is cheap, free this week, and everywhere og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # MiniMax M3.1 Flash is cheap, free this week, and everywhere **[Trends](https://daily.dev/sources/trends)** · 3 min read · 1 upvotes · 0 comments ## Summary MiniMax M3.1 Flash launched on OpenRouter under the stealth name 'Space Bunny' with aggressive distribution: day-0 serving support from vLLM (native NVFP4 KV cache, NVFP4 MoE weights, DSpark speculative decoding), a free tier on Vercel's AI Gateway through October 20 (when routed to MiniMax), and pricing of $0.15/$0.60 per million input/output tokens with a 1M-token context window. It reportedly scores 74% on DeepSWE and supports tunable thinking depth. It can be used with Claude Code, Codex, and Cursor via Vercel's CLI. Open weights and a Pro variant are expected October 23, at which point independent testing can verify the benchmark claims and serving performance outside the launch-day demo. ## Content The sharpest divide on MiniMax M3.1 Flash isn't about quality. It's about which discount number you believe. MiniMax's launch pitch: a 70% cut in agent costs versus M3, nearly 3x faster inference, output above 200 tokens per second, and flat pricing of $0.15/M input, $0.60/M output and $0.015/M cached input. Artificial Analysis ran its own numbers and landed on a 57% cost reduction per task. It also notes the two figures come from different workloads, so neither is exactly wrong. Your bill depends on your agent. ## The hype side @nutlope is the loudest voice: "This model is insane at design. And 88x cheaper than Claude Opus 5.5 on my test!" He had M3.1 Flash and Opus 5.5 each build a hardware launch landing page. MiniMax cost $0.014 versus $1.22 for Opus, and it was 4x faster and more token efficient. That's one prompt, one test, but it's the kind of screenshot that travels. On coding benchmarks, Artificial Analysis has M3.1 Flash roughly tied with Claude Opus 5 and GPT-5.6 Sol. MiniMax's own numbers include 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2 and 82% on CyberGym. Computer-use scores still trail the top Anthropic and OpenAI models. ## The catch On AA-Omniscience, the factual benchmark, the model got 56% right but attempted nearly every question. That means a high hallucination rate. The recommendation for knowledge-heavy work is verification and guardrails, not blind trust. There's also a pricing fight. DeepSeek's V4.1 Flash matches MiniMax off-peak but doubles during peak UTC hours. Its cache rate is five times cheaper, which matters a lot for agents that re-read context constantly. ## The ecosystem piled in fast vLLM shipped Day-0 support, with native NVFP4 KV, NVFP4 MoE weights and DSpark speculative decoding. Vercel's AI Gateway is serving it free until October 20 (route to MiniMax via provider order), and it works inside Claude Code, Codex and Cursor through the Vercel CLI. Before launch it had been testing on OpenRouter as "Space Bunny". ## Still open Weights are due October 23, but the license is unpublished. That matters for anyone eyeing self-hosting. A stronger Pro model is planned with no date. The model has a 1M context window and tunable thinking depth, which is new to the 3.1 family. My read: the price is real, the speed is real, and the headline savings figure is a best case. Run your own workload before rewriting your budget. ## Questions this post answers ### How much does MiniMax M3.1 Flash cost per million tokens? MiniMax M3.1 Flash costs $0.15 per million input tokens and $0.60 per million output tokens. It has a 1M-token context window and is positioned as a frontier multimodal coding model with a tunable thinking-depth setting. MiniMax reports a 74% score on the DeepSWE benchmark, though that figure comes from MiniMax itself ahead of the open-weights release. _Comparing coding model pricing before switching providers is easier with daily.dev tracking these launches._ ### Is MiniMax M3.1 Flash free to use right now? Vercel's AI Gateway serves MiniMax M3.1 Flash free until October 20, but only when requests are explicitly routed to the MiniMax provider, so the provider order must be pinned manually. After that date, standard MiniMax pricing applies. Open model weights are expected October 23, alongside a separate Pro variant. _Developers testing new coding models against a deadline can follow these windows on daily.dev._ ### Can I use MiniMax M3.1 Flash with Cursor or Claude Code? Yes, MiniMax M3.1 Flash can be accessed through Claude Code, Codex, and Cursor by routing through Vercel's CLI and AI Gateway. The API supports multiple formats including AI SDK, Chat Completions, Responses, and Anthropic Messages, and vLLM added day-0 serving support with native NVFP4 KV cache and MoE weights plus DSpark speculative decoding. _Developers wiring new models into existing coding agents can track integration details via daily.dev._ ## Community take How the wider developer community reacted, aggregated from 7 discussions and 149 comments across hackernews (as of 2026-10-19). **TL;DR:** Discussion is heavily skeptical, with many pointing out the model (previously tested as a 'stealth' release called Space Bunny) underperformed relative to its benchmark scores, and the broader conversation drifts into general distrust of AI labs' cherry-picked benchmarks and comparisons to outdated competitor models. **Sentiment:** 10% positive · 35% mixed · 55% skeptical **The case for** - Some found it 'OK' for basic coding tasks when coaxed through mistakes. - Pricing and speed claims look competitive on paper compared to the previous MiniMax generation. - It successfully completed a Pac-Man coding demo, albeit slowly, at effectively zero cost. **The pushback** - People who used it under its stealth codename found it unimpressive and inferior to DeepSeek and GLM Flash alternatives. - Benchmark comparisons are seen as cherry-picked, pitting the model against outdated competitor versions (Opus 5, GPT-5.6) rather than current SOTA. - Many feel benchmarks are increasingly 'benchmaxed' and disconnected from real-world coding performance. - MiniMax's language models are viewed as weaker than its video generation products. - The announcement's claimed 70% cost cut still doesn't beat DeepSeek's pricing, especially on cache costs. **By community** - hackernews (skeptical): Commenters who tried the model under its stealth name found it underwhelming compared to DeepSeek and GLM Flash, and much of the thread is broader skepticism toward AI benchmark marketing rather than enthusiasm for this specific release. **Hottest debate:** Whether benchmark-topping claims translate to real-world usefulness, with several commenters recounting disappointing hands-on experience with the model's earlier stealth release versus its glossy benchmark numbers. **Open questions** - How will the model perform once independently benchmarked by third parties rather than the vendor's own charts? - Will the eventual open-weight release confirm the claimed parameter/efficiency tradeoffs? - Will pricing stay competitive once more providers host the model, similar to dynamics seen with other open models? **Highlights** > This model seems to be pretty benchmaxed. In actual use, it doesn't survive the comparison to models in the benchmark. This model was released as a "stealth model" in OpenCode Go for a while as "Space Bunny" (they mention this in the blog). So people have been using without knowing what the model was exactly, but it failed to impress anyone as far as I can tell. This is despite the model being served for free (with some asterisks). GLM 5.3 Flash and DeepSeek V4.1 Flash, even before last week's update, seemed to be much preferred. Stealth releases happen often with OpenCode subscriptions, and GLM 5.3 Flash (stealth name "Ox Alpha") impressed a lot for example. The perverse incentives around benchmarks are now so bad that benchmark scores are effectively meaningless. Models can score highly and still be crap to use. It doesn't matter whether it's Minimax or Google, or anyone really. > — [DCKing on hackernews · 7 comments](https://news.ycombinator.com/item?id=50157109) > I used Space Bunny from some providers that offered it for free and it was a very much a "you get what you pay for" experience. If the release is comparable, I'll be sticking with Deepseek v4 for sure. > — [Rebelgecko on hackernews · 1 comments](https://news.ycombinator.com/item?id=50157192) > I’m one of the unimpressed. I tested SpaceBunny intensely on a research project for a week. The model wasn’t horrible at coding, it just made a ton of initial mistakes—but then would catch most of them later on. It can get work done if coaxed, but its peers are just cheaper and/or easier to work with. > — [adinb on hackernews · 2 comments](https://news.ycombinator.com/item?id=50157653) > Because they selectively choose which benchmarks to highlight and which competing models to compare against; they don't always compare against the SOTA or the Pareto frontier of performance/price, a lot of times you'll see them compare against the last generation of competing models, or the like, so that they look better if you don't carefully consider what they're comparing against. For example, here you see they are comparing against Opus 5 and GPT-5.6 Sol, when Opus 5.5, Sonnet 5.5, GPT-6 Astra, and GPT-6.1 Sol would be the latest SOTA models from those labs to compare against. Also because a lab's own benchmarks tend to run about 6.4% better than third party runs of the same benchmark. Source: https://whatmodel.sh/claims This can happen due to a number of factors, and doesn't necessarily indicate anything nefarious. It could just be that they run multiple times while fixing issues that aren't related to the model, and have a selection bias towards stopping when the score is on the higher side. But since you see that sometimes their own scores are lower than the independent runs, some of the variation is explained just by variance in the model solving problems, since LLMs are nondeterministic there can be variation from run to run and you don't see labs always cheating, just potentially a bit of selection bias about when they stop tweaking their benchmark setup and publish the results. And yes, there are independent third party runs of benchmarks for just this reason. The most popular with broad coverage of a range of benchmarks is https://artificialanalysis.ai/ but there are a number of others as well. > — [lambda on hackernews · 1 comments](https://news.ycombinator.com/item?id=50156938) > Yeah, I think of MiniMax as a good video generation model provider. Their languages models, by comparison, are not as impressive. > — [arcanemachiner on hackernews](https://news.ycombinator.com/item?id=50158870) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50154540) · 324 points · 149 comments - [hackernews](https://news.ycombinator.com/item?id=50154561) · 1 points · 0 comments - [hackernews](https://news.ycombinator.com/item?id=50153725) · 1 points · 0 comments - [hackernews](https://news.ycombinator.com/item?id=50153612) · 1 points · 0 comments - [hackernews](https://news.ycombinator.com/item?id=50153196) · 1 points · 0 comments - [hackernews](https://news.ycombinator.com/item?id=50151576) · 1 points · 0 comments - [hackernews](https://news.ycombinator.com/item?id=50151561) · 1 points · 0 comments ## Similar posts on daily.dev - [Google's Gemini 3.5 Flash costs 3x the model it replaced, and the era of cheap AI is ending](https://daily.dev/posts/google-s-gemini-3-5-flash-costs-3x-the-model-it-replaced-and-the-era-of-cheap-ai-is-ending-ochkeykzb) · XDA Developers · 2 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#vllm](https://daily.dev/tags/vllm), [#openrouter](https://daily.dev/tags/openrouter) [View this post on daily.dev](https://daily.dev/posts/minimax-m3-1-flash-is-cheap-free-this-week-and-everywhere-7uccejy7e) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"MiniMax M3.1 Flash is cheap, free this week, and everywhere","url":"https://daily.dev/posts/minimax-m3-1-flash-is-cheap-free-this-week-and-everywhere-7uccejy7e","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/minimax-m3-1-flash-is-cheap-free-this-week-and-everywhere-7uccejy7e"},"datePublished":"2026-10-19T12:16:21.377Z","dateModified":"2026-10-19T23:23:14.844Z","description":"MiniMax M3.1 Flash launched on OpenRouter under the stealth name 'Space Bunny' with aggressive distribution: day-0 serving support from vLLM (native NVFP4 KV...","image":"https://pbs.twimg.com/media/HU_iad5WcAAx2IN.jpg","thumbnailUrl":"https://pbs.twimg.com/media/HU_iad5WcAAx2IN.jpg","isAccessibleForFree":true,"articleSection":"Trends","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Trends","logo":"https://media.daily.dev/image/upload/s--ZfSp3asX--/f_auto,q_auto/v1780996004/logos/trends?_a=BAMAMiWQ0","url":"https://daily.dev/sources/trends"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/minimax-m3-1-flash-is-cheap-free-this-week-and-everywhere-7uccejy7e","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,ai-agents,vllm,openrouter","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Trends","item":"https://daily.dev/sources/trends"},{"@type":"ListItem","position":3,"name":"MiniMax M3.1 Flash is cheap, free this week, and everywhere"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/minimax-m3-1-flash-is-cheap-free-this-week-and-everywhere-7uccejy7e#faq","mainEntity":[{"@type":"Question","name":"How much does MiniMax M3.1 Flash cost per million tokens?","acceptedAnswer":{"@type":"Answer","text":"MiniMax M3.1 Flash costs $0.15 per million input tokens and $0.60 per million output tokens. It has a 1M-token context window and is positioned as a frontier multimodal coding model with a tunable thinking-depth setting. MiniMax reports a 74% score on the DeepSWE benchmark, though that figure comes from MiniMax itself ahead of the open-weights release. Comparing coding model pricing before switching providers is easier with daily.dev tracking these launches."}},{"@type":"Question","name":"Is MiniMax M3.1 Flash free to use right now?","acceptedAnswer":{"@type":"Answer","text":"Vercel's AI Gateway serves MiniMax M3.1 Flash free until October 20, but only when requests are explicitly routed to the MiniMax provider, so the provider order must be pinned manually. After that date, standard MiniMax pricing applies. Open model weights are expected October 23, alongside a separate Pro variant. Developers testing new coding models against a deadline can follow these windows on daily.dev."}},{"@type":"Question","name":"Can I use MiniMax M3.1 Flash with Cursor or Claude Code?","acceptedAnswer":{"@type":"Answer","text":"Yes, MiniMax M3.1 Flash can be accessed through Claude Code, Codex, and Cursor by routing through Vercel's CLI and AI Gateway. The API supports multiple formats including AI SDK, Chat Completions, Responses, and Anthropic Messages, and vLLM added day-0 serving support with native NVFP4 KV cache and MoE weights plus DSpark speculative decoding. Developers wiring new models into existing coding agents can track integration details via daily.dev."}}]} ```