Jina Reader and anonymous utility APIs
A recurring no-cost API allowance covering 2 cataloged models.
https://r.jina.aiModels mentioned
ReaderLM-v2jina-vlmEquivalent paid value
How this was valued: Modeled request envelope for the anonymous Reader tier: the documented keyless limit of 20 requests/minute per IP (28,800/day) is multiplied by a modeled 10,000 tokens per request and priced at Jina's current $0.05 per 1M token API rate, the rate the live first-party catalog lists for ReaderLM-v2 and all standard models and the rate keyed Reader calls pay when Jina counts the tokens of the output response. The per-request size is modeled, not documented: r.jina.ai publishes no per-request or per-minute token cap at any tier, so the assumption borrows Jina's only published per-request token quantity for web-content retrieval, the adjacent s.jina.ai charge of "a fixed number of tokens, starting from 10000 tokens" per request; individual Reader responses can be larger or smaller. Assumes uninterrupted single-IP saturation with no latency or availability loss. The anonymous Segmenter charges zero tokens even when keyed, so it adds no paid-equivalent value at Jina's own rates, and s.jina.ai is blocked without a key; the separate 10M-token keyed signup balance is valued in the jina_ai_search_foundation record and is not double counted here.
Limits and terms
- Reader Anonymous Requests Per Minute Per Ip
- 20
- Segmenter Anonymous Requests Per Minute Per Ip
- 20
- Segmenter Tokens Charged
- 0
- Reader With Free Key Requests Per Minute
- 500
- Caveat
- Supplying a key to Reader charges its token balance; anonymous basic Reader calls remain free.
What happens to your prompts?
Jina excludes model training, but anonymous Reader retention and non-training content handling remain unclear.
- Plan Scope
- Jina Reader and anonymous utility endpoints after Elastic's October 2025 acquisition; legacy Jina statements and current Elastic processing terms both matter.
- Prompt Retention
- URLs, fetched pages, prompts, and transformed content are request data; the public legal documents do not state a Reader-specific retention period or whether anonymous requests receive different storage.
- Response Retention
- not documented
- Ordinary Logging
- Operational, diagnostic, usage, IP, and security metadata may be retained and used in aggregated and anonymized form.
- Model Training
- Jina's terms say customer request data, inputs, prompts, and uploaded content are not used to train its models.
- Product Improvement
- Aggregated anonymized metadata can improve services; request-content use outside model training is not described with Reader-specific precision.
- Human Or Operator Access
- Content can be accessed as necessary for service delivery, security, support, and legal compliance under Elastic/Jina controls; no operator-blind promise is published.
- Subprocessors And Routing
- Reader fetches third-party URLs and operates under Elastic's current DPA and subprocessor framework, creating both destination-site and service-side data flows.
- Deletion Controls
- No anonymous per-request deletion mechanism or content TTL was found; contractual deletion at termination does not directly help anonymous users.
- Caveat
- Anonymous access should not be mistaken for anonymous processing. IP and usage logs plus an undocumented content TTL make Reader unsuitable for confidential URLs or query material.
Governing documents
- Terms And Conditions
- https://jina.ai/legal/
- Privacy Policy
- https://www.elastic.co/legal/privacy-statement
- Data Processing Agreement
- https://www.elastic.co/legal/customer-dpa
Eligibility
- Account Required
- No
- Payment Method Required
- No
Primary sources
Before you build with Jina Reader and anonymous utility APIs
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 2 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. The recorded base endpoint is https://r.jina.ai, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
The recorded offer does not require an account, but published limits and abuse controls can still change without notice. The reviewed evidence explicitly says no payment card is required. Re-check the signup flow because eligibility and billing controls can change after the snapshot. 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”: Jina excludes model training, but anonymous Reader retention and non-training content handling remain unclear. 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 7 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.