Jina Search Foundation API
10M tokens for new accounts; it does not recur.
https://api.jina.ai/v1Models mentioned
The offer covers a dynamic catalog, provider-selected route, or model class without stable model IDs in this snapshot.
Equivalent paid value
How this was valued: The 10M shared signup tokens are valued against the live first-party model catalog. Most captured models cost $0.05 per 1M input tokens, while the two nano models cost $0.02 per 1M; rows are alternative maxima for the same balance and are not additive. No period normalization is shown because Jina does not document the signup-token expiry.
Limits and terms
- Signup Tokens
- 10,000,000
- Recurrence
- No
- Free Token Expiry
- not documented
- Conservative Embedding And Rerank Requests Per Minute
- 100
- Conservative Embedding And Rerank Tokens Per Minute
- 100,000
- Caveat
- The product table gives the conservative limits above while the versioned OpenAPI page publishes higher Free-tier limits; use the lower figures until response headers or the dashboard resolve the conflict.
What happens to your prompts?
Jina excludes model training on request content, but retention and broader support or improvement handling remain imprecise.
- Plan Scope
- Jina AI Search Foundation APIs after Elastic's October 2025 acquisition; current Elastic data terms supersede portions of Jina's legacy legal page.
- Prompt Retention
- Request data, inputs, prompts, and uploaded content are processed to provide the APIs; no current public per-request retention period was found.
- Response Retention
- not documented
- Ordinary Logging
- Operational, diagnostic, and usage metadata may be retained and used in aggregated, anonymized form to operate, secure, and improve the services.
- Model Training
- Jina's published terms state customer request data, inputs, prompts, and uploaded content are not used to train its models.
- Product Improvement
- Aggregated and anonymized metadata can be used for service improvement; the terms exclude request content from model training but do not promise that all content is excluded from every support or product-development activity.
- Human Or Operator Access
- Access is governed by confidentiality, service delivery, security, support, and current Elastic data-processing controls; no operator-blind statement is published.
- Subprocessors And Routing
- Jina AI is owned by Elastic, and current processing is governed by Elastic's DPA and privacy statement with their subprocessors.
- Deletion Controls
- Contract termination requires deletion or return of confidential information and data under Jina's published terms, subject to mandatory retention; current self-service per-request deletion is not documented.
- Caveat
- The acquisition creates a policy-transition risk, and neither legacy Jina terms nor linked Elastic terms publish a Search Foundation request-content retention duration.
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
- Yes
- Payment Method Required
- No
- Signup Token Use
- noncommercial only
- Signup Token License
- CC-BY-NC
Primary sources
Before you build with Jina Search Foundation API
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
No stable model ID is recorded. The offer may use a dynamic catalog, a provider-selected route, or a model class, so resolve the current machine-readable ID before writing a fixed production configuration. The recorded base endpoint is https://api.jina.ai/v1, but the provider's current API reference remains authoritative for paths, authentication, and request shape.
Confirm account and billing boundaries
An account is required, so public catalog evidence cannot by itself prove the limits, balance, or billing behavior attached to your workspace. 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 on request content, but retention and broader support or improvement handling remain imprecise. 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.