Puter.js AI
Free to the developer; each end user signs in and consumes their own allowance.
Models mentioned
google:google/gemma-4-26b-a4b-itgoogle:google/gemma-4-31b-ittogetherai:prism-ml/ternary-bonsai-27binfron:deepseek/deepseek-v4-flash:freeinfron:deepseek/deepseek-v4-flash-0731:freeinfron:motif/motif-3infron:qwen/qwen3.8-27b:freeopenrouter:deepseek/deepseek-v4-flash-0731:freeopenrouter:qwen/qwen3.8-27b:freeopenrouter:z-ai/glm-5.2:freeopenrouter:inclusionai/ling-3.0-flash-vl:freeopenrouter:nex-agi/nex-n2.5-mini:freeopenrouter:nex-agi/nex-n2.5-pro:freeopenrouter:inclusionai/ling-3.0-flash-sante:freeopenrouter:inclusionai/ling-3.0-flash-fin:freeopenrouter:dots-studio/dots-3-note-preview:freeopenrouter:liquid/lfm-2.5-2.6b:freeopenrouter:nvidia/nemotron-3.5-lightning:freeopenrouter:thinkingmachines/inkling-small:freeopenrouter:poolside/laguna-s-2.1:freeopenrouter:thinkingmachines/inkling:freeopenrouter:poolside/laguna-xs-2.1:freeopenrouter:cohere/north-mini-code:freeopenrouter:nvidia/nemotron-3.5-content-safety:freeopenrouter:nvidia/nemotron-3-ultra-550b-a55b:freeopenrouter:nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freeopenrouter:google/gemma-4-26b-a4b-it:freeopenrouter:google/gemma-4-31b-it:freeopenrouter:google/lyria-3-pro-previewopenrouter:google/lyria-3-clip-previewopenrouter:nvidia/nemotron-3-super-120b-a12b:freeopenrouter:openrouter/freeEquivalent paid value
How this was valued: The published allowance or a defensible paid comparison is not precise enough to calculate.
The end user's monthly allowance is not documented and model prices are paid by that user rather than the developer.
Limits and terms
- Free Monthly End User Allowance
- amount not documented
- Exhausted Behavior
- End user is prompted to upgrade.
What happens to your prompts?
Puter and the selected upstream both process requests, while AI-specific TTL and training protections are unresolved.
- Plan Scope
- Puter platform and Puter.js user-pays AI integrations; selected upstream model providers also apply.
- Prompt Retention
- Puter's general terms permit platform processing, scanning, monitoring, and deletion of User Data, but do not give an AI-request TTL.
- Response Retention
- not documented
- Ordinary Logging
- Account, activity, device, cookie, and usage data is collected; AI content logging is not isolated in the public policy.
- Model Training
- No universal no-training commitment was found for Puter.js AI requests or all selected upstream providers.
- Product Improvement
- Service providers may assist Puter with operation and improvement; content scope remains unclear.
- Human Or Operator Access
- Terms permit Puter to monitor and review User Data, including private messages, while upstream AI providers necessarily receive routed content.
- Subprocessors And Routing
- Puter.js routes to third-party AI providers and charges the end user's account; both Puter and the chosen upstream are relevant processors.
- Deletion Controls
- Users can delete accounts and stored User Data, subject to the terms; no per-inference upstream deletion control is documented.
- Caveat
- The privacy policy says Puter does not collect personal information contained in User Data, while the terms permit operational processing and review. Neither document establishes a model-route-specific privacy guarantee.
Governing documents
- Terms Of Service
- https://puter.com/terms
- Privacy Policy
- https://puter.com/privacy
Eligibility
- Developer Provider Key Required
- No
- End User Account Required
- Yes
Primary sources
Before you build with Puter.js AI
Read the classification narrowly
This record has current first-party evidence for some zero-cost hosted inference. The label describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every region.
Resolve the live model route
This snapshot records 32 model IDs. Match the exact ID against the provider's live catalog before using it in code; zero-price routes and aliases can rotate while an older documentation page remains online. No stable base endpoint is published in this record, so use the linked provider documentation to identify the current request URL and protocol.
Confirm account and billing boundaries
The public evidence does not settle whether an account is required. Confirm the signed-in flow before treating anonymous or credential-free access as available. The payment-card requirement is conditional or not clearly documented. Treat signup friction and billing exposure as unresolved until the account flow confirms them. The equivalent paid value shown here prices a documented allowance where possible; it is not cash, guaranteed savings, or protection from overage.
Re-read the prompt policy for your plan
This record classifies the reviewed handling as “Partially private”: Puter and the selected upstream both process requests, while AI-specific TTL and training protections are unresolved. Provider policies can distinguish free, paid, enterprise, opted-in, and feature-specific traffic, so verify the governing terms for the exact account and route that will receive your data.
Follow the evidence, then re-check it
The record links 8 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest governing document or live catalog when sources disagree, and submit a correction when a provider changes a material term.
Match the quota to the workload shape
Translate the published allowance into the traffic pattern you actually expect instead of comparing headline totals alone. A daily token pool can look generous while a low requests-per-minute or concurrency ceiling blocks interactive bursts; a high request limit can still fail a long-context job when input, output, or per-request tokens are capped. Separate prompt tokens from generated tokens, include retries and tool calls, and test the largest realistic payload. If the provider documents more than one limit window, the tightest window at your peak load is the practical ceiling. Research, experimental, and community access can also carry eligibility or fair-use constraints that cannot be modeled as a simple number.
Plan fallback without changing the rules
A fallback should preserve more than API syntax. Confirm that the substitute route supports the required modality, context length, streaming behavior, structured output, tools, and safety controls, then compare its prompt-retention and training terms. An OpenAI-compatible request shape does not make providers operationally or contractually equivalent. Decide which errors may trigger a retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. If deterministic output matters, record the model revision and sampling settings; rotating aliases and free-model pools can change behavior even when the endpoint remains available.
Monitor the offer as a dependency
Capture the model ID, response model field, rate-limit headers, usage fields, latency, HTTP status, and any provider request identifier for each test. Watch for authorization failures, quota exhaustion, catalog removal, policy revisions, and dashboard balance changes as separate failure modes. Re-check the provider’s live catalog and governing pages on a schedule proportionate to the workload’s importance, and keep the dated sources that supported your decision. Free capacity is especially suitable for prototypes, evaluations, fallbacks, and bounded workloads when the application can tolerate change; a production dependency still needs observability, an exit path, and an owner responsible for re-verification.
Test one complete request before scaling
Start with the smallest permitted request using the exact credential, model ID, endpoint, and account type you intend to deploy. Record the HTTP status, response headers, usage fields, latency, and any dashboard balance change. Then exercise the failure path: an invalid model, an exhausted quota, or a rate-limit response should fail clearly without silently switching to a paid route. If the provider supports streaming or tool calls, validate those features separately because a free model can expose a narrower capability set than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and avoid sending sensitive data until the observed route matches the reviewed data agreement.