Select Baichuan-Text-Embedding in a /v1/embeddings request. The required input accepts a nonempty string or a nonempty array of strings, allowing a single passage and a prepared collection to use the same endpoint. The JSON result includes data[].embedding and data[].index, plus the selected model and usage.
For a knowledge collection, divide source documents into passages that preserve the definitions and context needed by a later reader. Maintain document IDs in your application and match each vector to its submitted position. A search workflow can encode the user’s query with the same model and retain the source passage beside any retrieved result.
Save the complete synchronous response before committing the vectors to storage. Check the input-to-index mapping, preserve all returned vectors and keep usage with the operation. Using the exact model identity for saved embeddings makes it clear which collection and query representation belong together.
", "aboutText": "Select Baichuan-Text-Embedding in a /v1/embeddings request. The required input accepts a nonempty string or a nonempty array of strings, allowing a single passage and a prepared collection to use the same endpoint. The JSON result includes data[].embedding and data[].index, plus the selected model and usage.\n\nFor a knowledge collection, divide source documents into passages that preserve the definitions and context needed by a later reader. Maintain document IDs in your application and match each vector to its submitted position. A search workflow can encode the user’s query with the same model and retain the source passage beside any retrieved result.\n\nSave the complete synchronous response before committing the vectors to storage. Check the input-to-index mapping, preserve all returned vectors and keep usage with the operation. Using the exact model identity for saved embeddings makes it clear which collection and query representation belong together.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "272d5fecc33ad5d80c0b8ee9620e418ab101e5f1b9f5bdd940785d38113fc90e", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "Baichuan-Text-EmbeddingBaichuan-Text-Embedding returns numerical vectors for supplied text through Ailoot’s embeddings API. Send one passage or a list and retain the response indices when building a searchable collection.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Select Baichuan-Text-Embedding in a /v1/embeddings request. The required input accepts a nonempty string or a nonempty array of strings, allowing a single passage and a prepared collection to use the same endpoint. The JSON result includes data[].embedding and data[].index, plus the selected model and usage.
For a knowledge collection, divide source documents into passages that preserve the definitions and context needed by a later reader. Maintain document IDs in your application and match each vector to its submitted position. A search workflow can encode the user’s query with the same model and retain the source passage beside any retrieved result.
Save the complete synchronous response before committing the vectors to storage. Check the input-to-index mapping, preserve all returned vectors and keep usage with the operation. Using the exact model identity for saved embeddings makes it clear which collection and query representation belong together.
POST /v1/embeddingstextembedding| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits Baichuan-Text-Embedding Conditions: Use this exact Ailoot routing selector. | Default— |
Fieldinput | Typestring or array<string> | RequirementRequired | Values & limits Conditions: | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, input |
Parameteroptional | Contract |
Parametermaterial_types | Contracttext |
Parameterconditions | ContractUse this exact Ailoot routing selector. |
Lifecycle: synchronous_json
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.00016 / 1K tokens Output · Output tokens $0 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "Baichuan-Text-Embedding", "input": "The quick brown fox jumps over the lazy dog"}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/embeddings \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Submit once. Retain the complete result, original identifiers and every response header.\nAiloot Ultra Baichuan-Text-Embedding
Use the method paths shown above.