Contact sales

Chatsax currently provides hosted API access. For Jina cloud marketplace deployments and model-weight licenses, consult the original provider. Jina AI ↗

Chatsax is independently operated. Jina supplies the current underlying APIs; model names and source links identify that provider.

The active request limit depends on your key and the upstream service. Check the rate-limit page for the limit assigned to your key, and use the retry information returned by a rate-limited response.

Reader normally counts tokens in the returned content. Options such as ReaderLM or web search can use a different rate; review the active pricing and recorded usage.

The service loads the supplied URL, extracts the relevant page content, and returns Markdown, text, HTML, or a screenshot according to your request.

Jina publishes its Reader implementation. The source link explains the extraction pipeline; Chatsax adds its own access and gateway layer.

Latency depends on the target site, cache state, browser engine, and readiness settings. A simple cached page and an interactive application have very different loading costs.

Clean document text reduces navigation, scripts, and markup in the context you send to a model. Raw HTML remains available when structure is useful.

Reader preserves the language of the source. Browser locale controls can help request the localized version a website serves.

A URL does not grant access to restricted content. Use authorized access, and supply supported cookies or proxy settings only when you have permission.

Use a public PDF URL or upload a local PDF in the playground. Scanned and image-heavy pages may need visual extraction; inspect the response before indexing it.

Images can remain as Markdown references, be removed, or receive generated captions. Choose the output that suits the model consuming the document.

Upload the file and provide a reference URL so that relative resources and links have a meaningful base.

Set cache tolerance to accept recent content, or bypass the cache when freshness matters. Requests with custom authentication may not be cacheable.

Reader supports forwarding cookies for authorized sessions. Some applications still require interactions that a single extraction request cannot reproduce.

Yes. Supply the PDF URL rather than an abstract page when you need the paper itself. Rate limits on the source website can still affect access.

Enable generated alt text to add a visual description to image references. Captions are model output and should be checked for important details.

Use a managed key, inspect errors and latency, control concurrency, and choose cache settings according to how quickly your sources change.

It is useful when document structure makes rule-based HTML conversion difficult. Enable ReaderLM in the playground and compare the resulting content and usage.

Use ReaderLM with an extraction instruction and JSON schema, then validate the returned fields in your application.

No access result is guaranteed. Target websites may reject automated traffic regardless of the available browser settings or account tier.

A higher service tier changes service limits; it does not confer authorization on third-party websites.

The public Reader repository is a useful starting point. Review its license, dependencies, browser requirements, and the parts you need to operate yourself.

Consult the limit assigned to your key and the selected model’s batch-size limits. Control request concurrency and use backoff when the service returns a rate-limit response.

Training methods differ by generation. The linked papers explain the data mixtures, task adapters, distillation, and multimodal alignment used for each model.

v5-omni accepts text, images, audio, video, and PDF input. Other models support a narrower set; the playground only offers input types published for the selected model.

Support varies by model. Use the model card for the published language coverage and evaluate representative queries from your own corpus.

The catalog displays each model’s context window. Hosted API limits can be lower and may also depend on input modality and batch size.

The active API schema and service limits determine the batch size. Split large collections or use the asynchronous batch API when available.

Select a model that supports the modality, choose the input type, and provide the supported URL or data representation. The generated request shows the exact structure.

Evaluate retrieval on your queries and documents. Published benchmarks provide context, but latency, storage, language, and domain fit also affect the decision.

Re-embed the documents and rebuild the index when the embedding space changes. Vectors from different models are not generally comparable.

Image, audio, and video tokenization depends on the model and preprocessing. Review the response usage fields and the current provider pricing.

Use v5-omni for several media types, v4 for its multimodal and multi-vector capabilities, or a CLIP model for text–image tasks. Compare performance on your data.

Classifier training is available through the classification workflow. Updating the underlying embedding weights is a separate model-training task.

Check the model card for available weights, supported runtimes, and licensing. A hosted API subscription does not automatically grant a commercial weight license.

It selects a representation suited to a workflow. For retrieval, encode the query and the document with their corresponding retrieval tasks.

Instead of one vector per document, token-level vectors preserve more detail. A scoring step then matches the query tokens against the document tokens.

The model processes wider document context before pooling smaller chunks. This helps a chunk retain information that appears outside its own text span.

Serving capacity, latency, and modality preprocessing affect the limits of a shared API even when the model architecture supports a longer sequence.

A model or processing path may need to warm up. Compare sustained latency separately from the first request and handle timeouts in your application.

Smaller vectors reduce storage and transfer costs. For models supporting Matryoshka dimensions, evaluate how much retrieval quality is retained at your chosen size.

Limits differ by input format and hosted model. Prefer accessible URLs for large files and consult the selected model’s schema before uploading.

Usage depends on the selected model and the query–document inputs. Review the response usage and current pricing before estimating a large workload.

v3.5 and v3 compare documents listwise; m0 supports visual candidates; v2 and earlier models offer other size, language, and architecture trade-offs.

Open the model card for its published license. API access and permission to run downloaded weights commercially are separate arrangements.

Multilingual rerankers support cross-language relevance matching. Test the language pairs and document styles important to your application.

Limits vary by model. The v3 family also exposes a document-length setting; reduce long candidates or segment them before reranking.

Use the published API limits and account for the total context of a listwise request. Reducing the candidate set also helps latency.

Measure representative queries with the model, candidate count, and document lengths used in production. A fixed document count alone is not enough.

Available weights and cloud marketplace listings provide deployment paths. Review the model license and the environment’s memory and runtime requirements.

This playground runs published rerankers. Training or adapting the underlying reranker requires a separate training workflow and licensed model assets.

Choose m0 for image candidates and provide readable source images. Very small text or heavily compressed pages can lose information before ranking.

A listwise model sees the query and candidate documents together, allowing the score to reflect relationships among the candidates.

The serving system balances total request size, throughput, and latency. Follow the API schema rather than assuming the model’s theoretical maximum.

Both request frequency and input volume can matter. Queue bursts, limit concurrency, and retry transient rate errors with backoff.

For text, evaluate v3.5 first. For visual documents, evaluate m0. Use a smaller or older model when its license, runtime, or latency better fits the task.

Some hosted models may need to load or initialize before serving a request. Latency also depends on the input size and current service load. Keep a timeout suited to the workload and inspect errors before retrying.

A key can access the services assigned to its scopes. Review the key in the dashboard before sharing it with an application.

Open the key manager to inspect recorded requests, status, latency, and available usage data for the selected key.

Sign in to manage your keys. If a key may be exposed, revoke it and update the applications that use it.

Access follows the expiry and status configured for the key. A key that is revoked or expired cannot be used for new requests.

Use only the transfer options available in your account. Do not assume that provider balances and Chatsax balances are interchangeable.

Use the key manager. Revocation stops future access, so update any dependent applications before retiring a key.

Check the platform privacy terms and the selected provider’s policy. Avoid sending material your organization has not approved for that service.

Use the status and retry information returned by the API. Add backoff and control concurrency instead of continuously retrying the same request.

The batch workflow supports submitting a job, checking its status, and downloading its output when the selected provider completes it.

Chatsax is independently operated. The current model APIs are provided by Jina, whose papers and model cards are linked for reference.

Each service has its own metering rules. Reading, search, embedding, and generation can count different units; review the active pricing before use.

Open the dashboard to receive a visitor key automatically. Sign in when you need account management or token purchases. The account screen shows your available balance and access.

The provider may have processed work before the connection ended. Review the recorded usage and billing status rather than inferring them from a closed browser tab.

The checkout screen displays payment methods available for your region, currency, and account.

Use the billing portal linked from your account, and retain the payment confirmation associated with the purchase.

No. API credit pays for hosted usage. Downloading and commercially running model weights follows the model’s separate license.

Use the contact page to describe the services, traffic, latency, and deployment requirements you need.

Check the selected account and key, the payment status, and the latest usage records. Keep the payment reference when contacting support.

Use the billing controls provided in the account or payment portal. Check the confirmation after changing an automatic payment setting.