# Wally by RunAnywhere Aiolum story: https://aiolum.com/story/wally-by-runanywhere/ · added 2026-11-11 · updated 2026-11-11 **In short.** Wally by RunAnywhere (Hosted inference API for open models, United States): Paid API with ten open models, October 2026. Evidence grade E: no revenue figure was checked. Team: 2 founders in 2025; 5 people on the Y Combinator page, November 2026. Launched 21 September 2026; still running. Hosted inference API for open models · United States · AI-native · team of 2 to 10 · still running · group: Developer tools and coding agents - Outcome: Paid API with ten open models, October 2026 (evidence grade of the headline number: E; no revenue figure) - Launch: 21 September 2026; months from launch to the outcome: 1 - Team: 2 founders in 2025; 5 people on the Y Combinator page, November 2026 - Outside funding: Y Combinator, Winter 2026 batch; amount not found - Main factor: Product - Meters, 1 to 4: evidence strength 1, copyable pattern 1, capital needed 3 - Tags: AI-native, Small team, Funded, Running, B2B, Developer tools Links: - Visit runwally.com: https://runwally.com/ **The product.** Wally is a hosted service that runs open AI models, such as Kimi K3, GLM-5.3 and DeepSeek V4.1, behind one API key. The API follows the OpenAI format, so existing code works after a change of base URL. A command-line tool connects coding agents such as Claude Code, Codex and OpenCode to a chosen model. The company also publishes an open-source on-device SDK. **Why it worked.** Wally sells speed on open models, and the company reuses engine work from its earlier on-device products. The founders claim in their launch post that Wally is faster than other hosts of the same model. Customers pay per token from prepaid credits. No source gives a revenue figure. Evidence grades: A = disclosed by a public company, a filing or a payment processor, or verified by one; B = two or more independent reports agree, or a journalist confirmed it; C = a founder claim that no one else verified; D = reported, not verified: one founder claim or a third-party estimate with no second source; E = no revenue figure found, so the headline is a non-money fact and the other facts carry their own grades; calc = computed on this page from graded facts. ## Summary Wally is a hosted inference service, and inference means running a trained AI model to produce an answer. Wally runs open-weight models, whose trained parameters anyone can download, on its own servers. A developer calls them through an OpenAI-compatible API, a web interface that programs use to send requests and read replies. RunAnywhere, Inc. makes Wally and also publishes open-source SDKs for running models on phones and laptops. Sanchit Monga and Shubham Malhotra started RunAnywhere in 2025, according to the company's About page. The company went through Y Combinator in the Winter 2026 batch, and its first products ran models on devices. The company's blog says it launched Wally on 21 September 2026, and its Y Combinator launch post is dated 29 September 2026. On 22 October 2026 the company published a catalog of ten models, and customers buy prepaid credits through Stripe. No source gives a revenue, customer or user count for Wally, so this story has grade E. Prices, dates and the launch claims come from the company's own pages. The Y Combinator page gives a team of 5 people. The page does not say how many customers pay. ## Why did Wally by RunAnywhere work? ### The founders claim Wally serves the same models faster than other hosts In the launch post, the two founders claim that Wally serves GLM-5.3 Flash at 380 tokens per second with a 274 ms first token. They cite Artificial Analysis, a benchmark site, for 28 September 2026. These are the founders' claims, not independent checks. Speed matters in loops such as coding agents, where each tool call waits for the first token. ### It reuses engine work from the on-device products The founders write that they spent nine months on engines for Apple and Qualcomm chips. They also write that none of that work was specific to phones, and that they pointed it at data-center GPUs. The company's blog says an agent pipeline writes the kernels, which are the low-level programs that run a model on a chip. The company says its engineers direct and check that work. ### Customers pay per token from prepaid credits The pricing page lists a rate per million tokens for each model. Customers buy credits through Stripe in a console, and each request debits the balance at the listed price. A request fails once the balance runs out. The terms add that the credits of a new account start with a US$5 grant. ## How it was built These details come from the company's own pages and blog. They are grade C. - The API follows the OpenAI chat-completions format at inference.runanywhere.ai/v1, so existing OpenAI client code works after a change of base URL. - A command-line tool, wally, connects coding agents such as OpenCode, Claude Code and Codex to a model. Sign-in is in the browser with Google or GitHub. - Payments use Stripe. The privacy policy names PropelAuth for sign-in, Resend for transactional email and Vercel for the marketing site. - The company says AI agents write the kernels and the serving stack, and its engineers direct and verify their work. Sources: [2, 6, 12] ## Who tried this before Wally by RunAnywhere, and why did they fail? Four companies in our database of failed startups sold developer infrastructure or AI inference to other builders. The values below are from that database and are not independently verified. The failed startups come from our database of dead startups, retold here in our own words; Its entries are AI-assisted summaries of public sources, so they carry no evidence grade. ### Parse (2011 to 2017; funding US$7.0M; cause: Acquired, then shut down) - Promise: A backend service for mobile developers, with sign-in, push messages and storage in hours instead of weeks. - Why it died: Facebook bought it in 2013 for about US$85M and shut it down in 2017. The page names weak unit economics under freemium pricing. - Record: ### DotCloud (2008 to 2012; funding US$18.0M; cause: Pivot) - Promise: A platform that hides the work of running cloud servers, so developers focus on code. - Why it died: The company pivoted to Docker, its own container technology. The page says the original service was overshadowed by it. - Record: ### Surge Cloud (2018 to 2023; funding US$1.0M; cause: Capital intensity) - Promise: A Polish cloud provider with lower latency, GDPR-native compliance and lower prices than the large US clouds. - Why it died: The page says it underestimated the capital and the competitive moat needed to challenge the large cloud providers. - Record: ### Rain AI (2017 to 2025; funding US$118.0M; cause: Hardware without a software base) - Promise: Neuromorphic chips for AI inference with far lower energy use than GPUs. - Why it died: The page says the company burned US$118M on a hardware platform before it had a software ecosystem that developers could use. - Record: ## What changed Each of the four sold the infrastructure under other people's products. Each met a larger provider or a cost that small revenue could not carry. Facebook bought Parse and later shut it down. DotCloud moved to Docker, its own container technology. Surge Cloud and Rain AI needed more capital than they had. Wally differs in what it owns. The launch post says Wally serves open models on the company's own GPUs. It does not build chips or a whole cloud. Its risk is also different. The launch post says Artificial Analysis lists 19 providers serving the same GLM-5.3 Flash weights, and the terms say prices can change. ## Can one person copy Wally by RunAnywhere now? **Verdict: Possibly, but only with funding and engine skill.** Hosting open models fast needs GPU capacity and kernel engineering, so a solo founder with no capital would struggle to copy it. A reader can study the sequence instead. Build open-source tools first, find what users still lack, and add a paid service for it. 1. Publish open-source tools for a narrow job and watch which requests the tools cannot meet. 2. Add a paid hosted service with a public price per unit of use. 3. Connect to the tools your customers already use, such as coding agents, with one command. **What is still open.** New open-weight models that other hosts serve slowly or not at all, and customers that need the same speed on their own GPUs. ## How much revenue does Wally by RunAnywhere make? The numbers, graded A paid hosted API launched in September 2026, with prices and no revenue figure. Most rows are company statements | Fact | Value | Grade | Note | Sources | |---|---|---|---|---| | Launch of Wally | 21 September 2026 | C | The company's blog post of 22 October 2026 says Wally launched on 21 September. RuntimeWire published its launch article on 21 September 2026. | [6, 11] | | Start of the company | 2025 | C | The About page lists 2025 as the year the founders started RunAnywhere. The Y Combinator page also says founded in 2025. The terms name RunAnywhere, Inc. | [1, 4, 8] | | Team | 5 people | C | The Y Combinator company page gives Team Size 5. The About page names two founders and adds that a small team of engineers works with them. | [4, 1] | | Funding | Y Combinator, Winter 2026 batch; amount not found | C | The About page says the company went through Y Combinator in Winter 2026. No source read gives an amount. | [1, 4] | | Models in the catalog | ten, on 22 October 2026 | C | The company's blog post of that date lists ten models, with fast versions that have their own model ids. | [5] | | Price range, input | US$0.042 to US$2.925 per million tokens | C | Pricing page. Eve has the lowest input rate and Kimi K3 the highest. The highest output rate is US$15.00 for Kimi K3. | [3] | | Free credit for a new account | US$5 | C | The terms call it a promotional welcome grant. The launch post says US$5 free on signup, no card. | [8, 4] | | How customers pay | prepaid credits through Stripe | C | The refund policy of 19 September 2026 says purchased credits are non-refundable except for a billing error, a duplicate charge or an outage. | [7] | | Service status | preview, with no uptime commitment | C | The terms effective 26 October 2026 say the service is a preview with no uptime or support-response commitment. | [8] | | Data retention | zero by default | C | The product page says Wally does not store prompts or replies. The console playground keeps recent conversations. | [2] | | GitHub stars of the on-device SDK repository | 10.3k stars, 416 forks | C | Read on the repository page on 11 November 2026. The repository holds the open-source SDKs, not the hosted service. | [10] | | Time from launch to the October 2026 fact | 1 month | calc | Calculated: 21 September 2026 to 22 October 2026. | [6, 5] | How to read this table. Most values are statements on the company's own pages or on the Y Combinator page, so they have grade C. The star count was read on GitHub. The "calc" value is computed on this page. No value has grade A or B. ## Pricing Wally prices per million tokens, read from the pricing page of runwally.com on 11 November 2026 (grade C) | Plan | Per month, billed yearly (US$) | Per month, billed monthly (US$) | Limit | |---|---|---|---| | DeepSeek V4 Flash 0731 | | | input 0.293, output 0.88, cached 0.0093 per million tokens | | DeepSeek V4 Pro (Fast) | | | input 1.68, output 3.38, cached 0.14 per million tokens | | DeepSeek V4.1 Flash | | | input 0.275, output 1.20, cached 0.006 per million tokens | | DeepSeek V4.1 Flash 1017 | | | input 0.195, output 1.00, cached 0.006 per million tokens | | DeepSeek V4.1 Flash (Fast) | | | input 0.275, output 1.20, cached 0.006 per million tokens | | Eve (decision model) | | | input 0.042 per million tokens; no output or cached rate | | GLM-5.3 (Fast) | | | input 1.40, output 4.40, cached 0.26 per million tokens | | GLM-5.3 Flash | | | input 0.15, output 0.50, cached 0.03 per million tokens | | Kimi K3 | | | input 2.925, output 15.00, cached 0.30 per million tokens | | MiniMax M3 | | | input 0.30, output 1.20, cached 0.06 per million tokens | The pricing page says that Wally uses prepaid credits, spent per million tokens. The table shows the input rate, the output rate and the cached input rate in US dollars. There is no monthly plan. The terms say that new accounts receive a US$5 welcome grant and that the service is a preview. ## When did Wally by RunAnywhere launch, and how did it grow? Timeline From a founders' company in 2025 to a paid hosted API in September 2026. Each entry carries its grade. - **2025** (grade C [1]): The two founders start RunAnywhere to run AI models on devices that people already own. - **Winter 2026** (grade C [1]): The company goes through Y Combinator and open-sources its on-device SDKs. - **21 September 2026** (grade C [6, 11]): The company's blog says Wally launched on this day, and RuntimeWire published an article about it. - **29 September 2026** (grade C [4]): The founders post a launch announcement on the Y Combinator site. It says sign up and get US$5 in free credits. - **22 October 2026** (grade C [5]): The company publishes the Wally catalog of ten open models. Fast versions have their own model ids. - **27 October 2026** (grade C [9]): A company blog post says DeepSeek V4.1 Flash Uncensored is coming to Wally, with reviewed access for authorized security work. ## What could go wrong for Wally by RunAnywhere? - **What is not verified.** No revenue figure was found. The pages read give prices and terms but no revenue, customer count or named paying customer. A reader could look for a payment-processor profile, a founder interview or a later press piece with figures. - **A preview service with a short history.** The terms effective 26 October 2026 say the service is a preview, and that the catalog and pricing can change. Wally launched about seven weeks before this page was written. - **Logo wall, counter and badges.** The "Works with" lists on the home pages name nine coding agents and twelve platforms with links. They do not say that any of them pays. The 10.3K counter on the site counts GitHub stars of the on-device SDK repository. "Backed by Y Combinator" matches the Y Combinator page, and "SOC 2 Type II Audit in progress" is the company's own line. The About page lists press pieces from early 2026, mostly about on-device work, which were not read. - **Security model with reviewed access.** A company blog post of 27 October 2026 announces DeepSeek V4.1 Flash Uncensored on Wally for authorized security work. The Security programme page of runwally.com says a person at RunAnywhere approves each account. The acceptable use policy allows tests only on systems the user owns or has written permission to test. The terms say approved accounts pay 50% of the published price from 26 October to 30 November 2026. The model is not on the pricing page of 11 November 2026. The post calls the access review KYC, and the founder writes that he is not a security expert. ## Sources 1. RunAnywhere, About page (runanywhere.ai/about) — https://runanywhere.ai/about (grade C). Read in full on 11 November 2026. Company page. Source for the start in 2025, the founders, the Y Combinator batch and the press list. 2. Wally by RunAnywhere, home page (runwally.com) — https://runwally.com/ (grade C). Read in full on 11 November 2026. Source for the product description, the data retention claim and the Works with lists. 3. Wally, pricing page (runwally.com/pricing) — https://runwally.com/pricing (grade C). Read in full on 11 November 2026. It loads as plain HTML. Source for the rate table. 4. Y Combinator company page: RunAnywhere, with the Wally launch post — https://www.ycombinator.com/companies/runanywhere (grade C). Read in full on 11 November 2026. Source for founded 2025, team size 5, the launch post of 29 September 2026 and its claims. 5. RunAnywhere blog, 22 October 2026: Wally now serves ten open models — https://runanywhere.ai/blog/wally-catalog-ten-open-models (grade C). Read in full. Written by Sanchit Monga. Source for the ten-model catalog. 6. RunAnywhere blog, 22 October 2026: Why we build inference for everyone — https://runanywhere.ai/blog/why-we-build-inference-for-open-models (grade C). Read in full. Written by Sanchit Monga. Source for the launch date of 21 September and the move from on-device to hosted models. 7. RunAnywhere refund policy, effective 19 September 2026 — https://runanywhere.ai/legal/refunds (grade C). Read in full. Source for prepaid credits through Stripe and the US$5 welcome grant. 8. RunAnywhere terms of service, effective 26 October 2026 — https://runanywhere.ai/legal/terms (grade C). Read in full. Source for the legal entity, the preview status and the welcome grant. 9. RunAnywhere blog, 27 October 2026: Cheap Tokens Don't Matter Without Access — https://runanywhere.ai/blog/cheap-tokens-dont-matter-without-access (grade C). Read in full. Written by Sanchit Monga. Source for the security model with reviewed access. 10. GitHub: RunanywhereAI/runanywhere-sdks — https://github.com/RunanywhereAI/runanywhere-sdks (grade C). Read the repository page on 11 November 2026. Source for the star and fork counts of the on-device SDK. 11. RuntimeWire, 21 September 2026: RunAnywhere launches Wally, says its open-model inference outruns larger providers — https://runtimewire.com/article/runanywhere-launches-wally-open-model-inference (grade C). Read the headline, the subtitle and the date. The article body loads by script and was not read, so only the date is used. 12. RunAnywhere privacy policy, effective 26 October 2026 — https://runanywhere.ai/legal/privacy (grade C). Read in full. Source for the subprocessors Stripe, PropelAuth, Resend and Vercel. 13. Database of failed startups, local export — /method/#dead (grade C). Record pages read on the website on 11 November 2026. AI-written summaries, not independently verified. Source for the failed predecessors. 14. Wally, Security programme page (runwally.com/security) — https://runwally.com/security (grade C). Read in full on 11 November 2026. Source for the gated security model and the review of each access request by a person. 15. RunAnywhere acceptable use policy, effective 26 October 2026 — https://runanywhere.ai/legal/acceptable-use (grade C). Read in full on 11 November 2026. Source for the rule that security tests need ownership or written permission. Contact: aiolum@livyden.com. Run Wally by RunAnywhere? Send corrections or a verified figure to aiolum@livyden.com (subject: Correction: Wally by RunAnywhere).