Source: https://ailoot.ai/models/en/cohere-rerank-v3-5/ Canonical: https://ailoot.ai/models/en/cohere-rerank-v3-5/ Language: en # Cohere: Rerank v3.5 [Markdown](https://ailoot.ai/models/en/cohere-rerank-v3-5/index.md) · [JSON](https://ailoot.ai/models/en/cohere-rerank-v3-5/facts.json) ## [Cohere: Rerank v3.5](https://ailoot.ai/models/en/cohere-rerank-v3-5/) Cohere Rerank 3.5 reorders candidate text and semi-structured records by relevance to a query. It supports more than 100 languages and a 4096-token context for refining keyword or semantic search results before an answer or search display. - [**Ailoot Ultra · Rerank** `POST /v1/rerank` `cohere/rerank-v3.5`](https://ailoot.ai/models/en/cohere-rerank-v3-5/#method-0) About the model This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below. Cohere Rerank 3.5 is a multilingual model for relevance ranking of candidate documents and semi-structured text. It evaluates each candidate in relation to a query and returns a reordered result list with relevance scores. It can refine candidates obtained through keyword or semantic search and select passages for a retrieval-augmented answer. Its task is to improve the evidence ordering rather than generate a free-form answer or create a new corpus index. The exact producer identifier is rerank-v3.5. It uses a 4096-token context, distinct from Rerank 4 Pro and Fast’s 32K context. Query and document tokens count together against that per-candidate window. The model-specific preparation guide truncates a query beyond its first 2048 tokens and describes document chunks of 4093 tokens before the query is taken into account. Keep the query focused and prepare candidate passages containing the information needed to judge the requested relationship. Supply the query and a list of candidate text strings. Each result carries an index pointing to the original document position and a relevance score; top\_n chooses how many ranked results to retain. Without it, the documented producer workflow returns all results. Preserve document identifiers independently of the score so the top passage can still be traced to the original policy, product record or message. Rerank 3.5 supports more than 100 languages, including English and non-English material. A query can contain several aspects of the need, such as the product, user situation and desired procedure. For structured records, the V2 release removed raw document objects and recommends YAML strings. Keep useful fields in a deliberate order, with decisive content before less relevant metadata, because long strings can be truncated. This works for titles and content, product attributes or a message subject and body. The V2 producer reference uses max\_tokens\_per\_doc for document truncation, with a default of 4096. Cohere’s preparation guide also describes long-document chunking; the effective input depends on the selected workflow and its document settings. For greater control, prepare identifiable passages yourself rather than assuming every section of a long source remains visible. Preserve enough surrounding context to distinguish an answer-bearing passage from one that only shares its vocabulary. For request performance, the current reference recommends not sending more than 1,000 documents at once. Relevance scores are normalised between 0 and 1, but their values depend on the query and candidates and are not a linear scale of correctness. Use the ranking to identify useful evidence. If a score threshold is needed, choose representative domain queries and borderline relevant passages so the threshold reflects the actual retrieval task. A practical support workflow can rerank candidate return-policy sections for a question about a damaged item, then pass the selected source text to an answer-writing stage. An email search can rank messages by a specific issue and retain the original message identifier with each result. The useful artifact is the ordered evidence list. Keep Rerank 3.5’s shorter context and V2 document preparation attached to that result instead of substituting later-model limits. **Ailoot Ultra · Rerank** `POST /v1/rerank` `cohere/rerank-v3.5` [`cohere/rerank-v3.5`](https://ailoot.ai/models/en/#m=cohere%2Frerank-v3.5&route=Ultra&caller=cohere%2Frerank-v3.5&fmt=rerank) Cohere /`cohere/rerank-v3.5` ### Overview Cohere Rerank 3.5 reorders candidate text and semi-structured records by relevance to a query. It supports more than 100 languages and a 4096-token context for refining keyword or semantic search results before an answer or search display. Accepted inputs Text Results Ranked results ### Available in Ailoot · inputs & methods **Ailoot Ultra · Rerank** `POST /v1/rerank` Input types `text` Output types `rerank` Output format json | Field | Type | Requirement | Values & limits | Default | | --- | --- | --- | --- | --- | | Field`documents` | Type`array` | RequirementRequired | Values & limits | Default— | | Field`model` | Type`string` | RequirementRequired | Values & limits cohere/rerank-v3.5 | Default— | | Field`provider` | Type`schema` | RequirementOptional | Values & limits | Default— | | Field`query` | Type`string` | RequirementRequired | Values & limits | Default— | | Field`session_id` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`top_n` | Type`integer` | RequirementOptional | Values & limits Minimum: 1 | Default— | | Field`trace` | Type`schema` | RequirementOptional | Values & limits | Default— | | Field`user` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`documents[].text` | Type`string` | RequirementOptional | Values & limits | Default— | | Field`documents[].image` | Type`string` | RequirementOptional | Values & limits | Default— | Input material combinations **text\_rerank** · Required: query, documents array with minItems1 Method parameters and lifecycle | Parameter | Contract | | --- | --- | | Parameter`content_type` | Contractapplication/json | | Parameter`required` | Contractmodel, query, documents | | Parameter`material_types` | Contracttext | | Parameter`optional_controls` | Contractprovider, session\_id, top\_n, trace, user | | Parameter`multimodal_input_binding` | Contractnull | Lifecycle: `synchronous` Send the exact model ID and retain the complete native response. ### Pricing Tariff references do not add request options. Supported parameters are listed for the selected method. Fast mode Not specified When fast mode is selected Flex mode Not specified When flex mode is selected Maximum reasoning effort Not specified When maximum reasoning effort uses the default adjustment #### Ailoot rates #### Prices by configuration Match each charge to the conditions shown. Use one rate for each set of alternative configurations. | Configuration | Rate schedule | Billing unit | Charge | | --- | --- | --- | --- | | ConfigurationBase token rates | Rate scheduleBase rate | Billing unit— | Charge Input · Input tokens **—** / 1K tokens Output · Output tokens **—** / 1K tokens Input · Cache read **—** / 1K tokens Input · Cache write **—** / 1K tokens Input · Cache write, 1 hour **—** / 1K tokens | | ConfigurationUltra | Rate schedule— | Billing unitper search unit | Charge total · search unit **$0.002** per search unit | Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/) ### Example requests #### Ailoot Ultra · Rerank Retained official request structure; documentary exampleUse your actual request material and retain the complete result ```json { "documents": [ "Paris is the capital of France.", "Berlin is the capital of Germany." ], "model": "cohere/rerank-v3.5", "query": "What is the capital of France?", "top_n": 3 } ``` ```bash set -eu : "${AILOOT_API_KEY:?Set your Ailoot API key}" : "${AILOOT_REQUEST_FILE:?Set your actual JSON request file}" export AILOOT_REQUEST_FILE python3 - <<'PY_REQUEST' import json,os from pathlib import Path p=json.loads(Path(os.environ['AILOOT_REQUEST_FILE']).read_text(encoding='utf-8')) if not isinstance(p,dict): raise SystemExit('Request must be a JSON object') p['model']='cohere/rerank-v3.5' Path('request.json').write_text(json.dumps(p,ensure_ascii=False),encoding='utf-8') PY_REQUEST curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/rerank \ -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \ --data-binary @request.json -D response-headers.txt -o result.json python3 - <<'PY_RESULT' import json from pathlib import Path print(json.dumps(json.loads(Path('result.json').read_text()),ensure_ascii=False,indent=2)) PY_RESULT ``` ### Receive and save results #### Ailoot Ultra · Rerank json ##### Keep all completed results Keep every complete returned response, file and content part. Every actual result index, finite relevance\_score and original document object is retained. Indices bind the original document array. Entire original JSON is stored and returned only after settlement. ##### If the original response needs checking Preserve original operation and full/partial reply; do not replay POST. Response fields | Field | Type | | --- | --- | | Field`model` | Typestring | | Field`id` | Typestring | | Field`provider` | Typestring | | Field`results[].index` | Typeinteger | | Field`results[].relevance_score` | Typenumber | | Field`results[].document.text` | Typestring | | Field`results[].document.image` | Typestring | | Field`usage.search_units` | Typeinteger | | Field`usage.total_tokens` | Typeinteger | | Field`usage.cost` | Typenumber | Errors and next steps | Response | Condition | Next step | | --- | --- | --- | | Response400 · `invalid_request_error` | ConditionInvalid required field, representation or value | Next stepCorrect the indicated request field. | ### Aliases #### Model aliases **Ailoot Ultra** [`cohere/rerank-v3.5`](https://ailoot.ai/models/en/#m=cohere%2Frerank-v3.5&route=Ultra&caller=cohere%2Frerank-v3.5&fmt=rerank) #### Method path aliases Use the method paths shown above. #### Related caller IDs [`cohere/rerank-v3.5`](https://ailoot.ai/models/en/#m=cohere%2Frerank-v3.5&route=Ultra&caller=cohere%2Frerank-v3.5&fmt=rerank) FAQ · Cohere: Rerank v3.5 What inputs and results are available? `POST /v1/rerank` · `cohere/rerank-v3.5`: `text` → `rerank` Which fields does the request use? `POST /v1/rerank` · `cohere/rerank-v3.5`: `documents`, `model`, `provider`, `query`, `session_id`, `top_n`, `trace`, `user` What limits apply? `POST /v1/rerank` · `cohere/rerank-v3.5`: `top_n.minimum`: `1` Connect Ailoot to Claude Code, OpenCode, Hermes or your own app. ## The company and its project portfolio The company and its project portfolio: millions of customers; monthly sales in the billions. ## Buy tokens at a discount. Subscription discounts for regular use. Promo codes offer up to 50% off token purchases. Subscription Choose a discounted plan for your regular requests. Promo code: up to 50% off Enter your code at checkout. The price updates to reflect the current promotion. Spending in your history The model, tokens and amount are recorded for each request. [Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/) ## Connect the API to a product you sell. Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale. Commercial application Add text, image, video and audio generation to paid features in your service. Reseller licence Send a description of your project and how you provide access. Request written terms for use and resale. Documents on the website The service offer, licence agreement and data processing policy are available before you connect. [Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en) ## Ailoot · The company and its project portfolio Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control. The company and its project portfolio: millions of customers; monthly sales in the billions. Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.