Quality Control
reasoning_effortChoose the amount of research effort. Higher effort can perform more searches and take longer.
Configure in the playgroundDeepSearch API
Explore the API. Make a real request. Use the code in your application.
Stream response
streamReceive reasoning and answers as they are generated.
Reasoning effort
reasoning_effortBalance research depth and response time.
Maximum output tokens
max_tokensLimit the length of the answer.
Research token budget
budget_tokensMaximum reasoning budget for this request.
Always search
no_direct_answerRequire research instead of answering from model memory.
Maximum attempts
max_attemptsLeave empty to use the service default.
Research team size
team_sizeLeave empty to use the service default.
Maximum returned URLs
max_returned_urlsLeave empty to use the service default.
arXiv optimized search
search_providerSearch academic papers using arXiv.
JSON schema
response_formatRequest a structured answer.
Search language
search_language_codeUse a language code.
Answer language
language_codeUse a language code.
Preferred hostnames
boost_hostnamesSeparate hostnames with commas.
Excluded hostnames
bad_hostnamesSeparate hostnames with commas.
Restrict hostnames
only_hostnamesSeparate hostnames with commas.
curl 'https://chatsax.com/v1/deepsearch' \
-X 'POST' \
-H 'Content-Type: application/json' \
-H 'Accept: text/event-stream' \
-H "Authorization: Bearer $CHATSAX_API_KEY" \
--data-binary '{
"model": "jina-deepsearch-v1",
"messages": [
{
"role": "user",
"content": "Hi!"
},
{
"role": "assistant",
"content": "Hi, how can I help you?"
},
{
"role": "user",
"content": "what'\''s the latest blog post from jina ai?"
}
],
"stream": true,
"reasoning_effort": "medium",
"max_tokens": 1000
}'Your response will appear here.
Your API key
Use this key right away. Sign in to manage your account.
DeepSearch Parameters Guide
Budget Tokens
budget_tokensSet a token budget for the research process. Use a budget appropriate for the complexity of your question.
Configure in the playgroundMax Attempts
max_attemptsLimit how many times the researcher may revise its answer after evaluating the evidence.
Configure in the playgroundTeam Size
team_sizeSet the number of collaborating research agents. More parallel work can use more resources.
Configure in the playgroundSource Control
no_direct_answerDecide whether the model may answer from existing knowledge or should perform an explicit search.
Configure in the playgroundNo Direct Answer
no_direct_answerEnable this option when a current source is required. It requests research before the final answer.
Configure in the playgroundHostname Controls
boost_hostnames / bad_hostnames / only_hostnamesPrefer useful domains, exclude unsuitable sources, or restrict research to a domain allowlist.
Configure in the playgroundSpecial Case: Academic Research
only_hostnamesUse scholarly sources for research questions and inspect the original papers behind the answer.
Configure in the playgroundSearch Language Code
search_language_codeChoose the language used for search independently of the language of the final answer.
Configure in the playgroundUse Cases for Language Control
Research a local topic with native-language sources, then write the answer in the language your audience reads. Verify translations of technical terms against the sources.
Chat with DeepSearch
API Integrations
Connect DeepSearch to your preferred chat client using its OpenAI-compatible API settings.
6 integrations
What is DeepSearch?
DeepSearch alternates between research, source reading, and reasoning to build an answer with evidence. The process can revise a search when the available information is incomplete.
Standard LLMs
A language model answers primarily from its learned knowledge and the context supplied in the prompt.
RAG and grounded LLMs
Retrieval adds selected documents to the prompt so an answer can use evidence beyond the model’s training data.
DeepSearch
An iterative researcher can plan follow-up searches, inspect sources, and revise its answer as new information arrives.
API pricing
Your API key
Use this key right away. Sign in to manage your account.
Toy Experiment
10Million
FreeNo login required
- Search Foundation
- Shared token balance
- Usage tracking
Production
1Billion
$50.00one-time purchase
- All Chatsax APIs
- Shared token balance
- Usage tracking
Scale Up
11Billion
$500.00one-time purchase
- All Chatsax APIs
- Shared token balance
- Usage tracking
Log in to manage your balance, keys and billing history.
Rate limits & token usage
Default application keys allow 60 requests per minute and 10,000 requests per day. All keys in an account share its prepaid balance. Usage is settled from provider-reported tokens.
View rate limit detailsRate limits
Your key’s assigned limits apply alongside the provider’s service capacity. Check the dashboard for the limits currently active on your account.
| Service | Method | Usage basis |
|---|---|---|
| Reader | GET / POST | Output tokens |
| Search | GET / POST | Search request and content |
| Embeddings | POST | Input tokens and modalities |
| Reranker | POST | Query and candidate documents |
Frequently asked questions
API questions
Why is the first request for some models slow?
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.
Can one Chatsax key access several APIs?
A key can access the services assigned to its scopes. Review the key in the dashboard before sharing it with an application.
Where can I review my usage?
Open the key manager to inspect recorded requests, status, latency, and available usage data for the selected key.
What if I lose a key?
Sign in to manage your keys. If a key may be exposed, revoke it and update the applications that use it.
Do keys expire?
Access follows the expiry and status configured for the key. A key that is revoked or expired cannot be used for new requests.
Can tokens be moved between keys?
Use only the transfer options available in your account. Do not assume that provider balances and Chatsax balances are interchangeable.
Can I revoke an API key?
Use the key manager. Revocation stops future access, so update any dependent applications before retiring a key.
Are my documents used to train models?
Check the platform privacy terms and the selected provider’s policy. Avoid sending material your organization has not approved for that service.
How do I handle rate limits?
Use the status and retry information returned by the API. Add backoff and control concurrency instead of continuously retrying the same request.
Can I process a large collection asynchronously?
The batch workflow supports submitting a job, checking its status, and downloading its output when the selected provider completes it.
Is Chatsax operated by Jina AI?
Chatsax is independently operated. The current model APIs are provided by Jina, whose papers and model cards are linked for reference.
How do I get an API key?
Open the dashboard to receive a visitor API key automatically. Copy it into your application or try a request immediately. Sign in when you want to manage an account and add tokens.
Get an API keyBilling questions
Is usage counted by sentences or requests?
Each service has its own metering rules. Reading, search, embedding, and generation can count different units; review the active pricing before use.
How do I get started?
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.
Can an interrupted request consume resources?
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.
Which payment methods are available?
The checkout screen displays payment methods available for your region, currency, and account.
Where can I find a receipt or invoice?
Use the billing portal linked from your account, and retain the payment confirmation associated with the purchase.
Does buying API credit grant a model license?
No. API credit pays for hosted usage. Downloading and commercially running model weights follows the model’s separate license.
Can I discuss a larger deployment?
Use the contact page to describe the services, traffic, latency, and deployment requirements you need.
Why is the balance different from what I expected?
Check the selected account and key, the payment status, and the latest usage records. Keep the payment reference when contacting support.
How do I manage future charges?
Use the billing controls provided in the account or payment portal. Check the confirmation after changing an automatic payment setting.