{ "aboutHtml": "

voyage-multimodal-3.5 is Voyage AI’s embedding model for retrieval across text, images and video. It processes interleaved text and visual content through a single transformer encoder, representing a complete multimodal input in a shared vector space. The 3.5 edition adds explicit video-frame support and flexible embedding dimensions.

Preserve the relationship between text and visuals

Prepare a document page or section in the form that preserves its useful visual information. A slide containing a chart and a short explanation can be represented with the slide image and accompanying text in the same ordered input. For a PDF-based collection, the documented visual input is a page screenshot or other image representation of the document.

For a report chart, retain the title, axis labels and legend in the image. Attach explanatory text when it provides the context needed to interpret the visual. Store the page number and source identifier beside the resulting vector so a retrieved candidate can open the relevant page rather than merely return a document name.

The maker’s input format supports sequences of text, images and videos. Its published image formats are PNG, JPEG, WebP and GIF, with MP4 for video. Visual content can be represented through URLs or Base64 data in the documented recipe; keep one representation style consistently within a request.

Retrieve a scene rather than an entire long video

The model represents video as an ordered sequence of frames. The maker recommends dividing a long video into related scenes, aligning scene boundaries with available transcript timestamps and retaining the corresponding transcript text. Lower resolution or a reduced frame rate can help a semantically continuous scene fit its context budget.

For a training-video collection, a query might ask for the scene that demonstrates adjusting a particular control. Associate each indexed scene with its time range. Return the matching scene and inspect the frames or original clip for the actual action, rather than treating the retrieved vector as a written description of everything in the recording.

Transcript text can contribute when prepared as part of the multimodal input. Video-frame embedding itself does not supply a speech transcript.

Context and preparation limits

The stated context length is 32,000 tokens per input. Voyage counts every 560 image pixels and every 1120 video pixels as a token in its published calculation, so visual content shares that budget with text. The documented limits also include 16 million pixels and 20 MB per image, and 20 MB per video. A list contains at most 1000 inputs and 320,000 combined tokens.

The default truncation setting clips an over-length input; if that boundary falls within an image, the entire image is discarded. Preparing complete pages or scenes within the budget therefore preserves more predictable input content. The alternative documented setting rejects over-length inputs instead of truncating them.

Vector dimensions and retrieval roles

The default output dimension is 1024, with 256, 512 and 2048 dimensions also documented for this edition. The announcement describes Matryoshka embeddings and floating-point, signed or unsigned 8-bit, and binary representations. Retain the chosen dimension and representation with the index.

Voyage’s retrieval recipe distinguishes query and document inputs. A query can be text or an image, and indexed documents can combine text and visuals. One vector represents each complete input sequence; store its source page, image or scene association so the ranked result remains inspectable.

Use the returned visual source

A retrieval stage can locate a report page, table, slide or scene relevant to the query. The answer-writing or analysis stage then reads that source material. For a table, inspect the actual headers and values before using a result; for a scene, inspect the relevant frames and associated text.

The substantive difference from voyage-multimodal-3 is the 3.5 edition’s explicit video support and additional representation choices. These are embedding capabilities for locating source material, with numerical vectors as output rather than generated images, video or a narrative answer.

", "aboutText": "voyage-multimodal-3.5 is Voyage AI’s embedding model for retrieval across text, images and video. It processes interleaved text and visual content through a single transformer encoder, representing a complete multimodal input in a shared vector space. The 3.5 edition adds explicit video-frame support and flexible embedding dimensions.\n\n### Preserve the relationship between text and visuals\n\nPrepare a document page or section in the form that preserves its useful visual information. A slide containing a chart and a short explanation can be represented with the slide image and accompanying text in the same ordered input. For a PDF-based collection, the documented visual input is a page screenshot or other image representation of the document.\n\nFor a report chart, retain the title, axis labels and legend in the image. Attach explanatory text when it provides the context needed to interpret the visual. Store the page number and source identifier beside the resulting vector so a retrieved candidate can open the relevant page rather than merely return a document name.\n\nThe maker’s input format supports sequences of text, images and videos. Its published image formats are PNG, JPEG, WebP and GIF, with MP4 for video. Visual content can be represented through URLs or Base64 data in the documented recipe; keep one representation style consistently within a request.\n\n### Retrieve a scene rather than an entire long video\n\nThe model represents video as an ordered sequence of frames. The maker recommends dividing a long video into related scenes, aligning scene boundaries with available transcript timestamps and retaining the corresponding transcript text. Lower resolution or a reduced frame rate can help a semantically continuous scene fit its context budget.\n\nFor a training-video collection, a query might ask for the scene that demonstrates adjusting a particular control. Associate each indexed scene with its time range. Return the matching scene and inspect the frames or original clip for the actual action, rather than treating the retrieved vector as a written description of everything in the recording.\n\nTranscript text can contribute when prepared as part of the multimodal input. Video-frame embedding itself does not supply a speech transcript.\n\n### Context and preparation limits\n\nThe stated context length is 32,000 tokens per input. Voyage counts every 560 image pixels and every 1120 video pixels as a token in its published calculation, so visual content shares that budget with text. The documented limits also include 16 million pixels and 20 MB per image, and 20 MB per video. A list contains at most 1000 inputs and 320,000 combined tokens.\n\nThe default truncation setting clips an over-length input; if that boundary falls within an image, the entire image is discarded. Preparing complete pages or scenes within the budget therefore preserves more predictable input content. The alternative documented setting rejects over-length inputs instead of truncating them.\n\n### Vector dimensions and retrieval roles\n\nThe default output dimension is 1024, with 256, 512 and 2048 dimensions also documented for this edition. The announcement describes Matryoshka embeddings and floating-point, signed or unsigned 8-bit, and binary representations. Retain the chosen dimension and representation with the index.\n\nVoyage’s retrieval recipe distinguishes query and document inputs. A query can be text or an image, and indexed documents can combine text and visuals. One vector represents each complete input sequence; store its source page, image or scene association so the ranked result remains inspectable.\n\n### Use the returned visual source\n\nA retrieval stage can locate a report page, table, slide or scene relevant to the query. The answer-writing or analysis stage then reads that source material. For a table, inspect the actual headers and values before using a result; for a scene, inspect the relevant frames and associated text.\n\nThe substantive difference from voyage-multimodal-3 is the 3.5 edition’s explicit video support and additional representation choices. These are embedding capabilities for locating source material, with numerical vectors as output rather than generated images, video or a narrative answer.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "37a0bdec3311d0256543de70684c27257f29a691152a6d34b0e9aabb7c1ca932", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "
•

VoyageAI by MongoDB: voyage-multimodal-3.5

VoyageAI by MongoDB /voyageai/voyage-multimodal-3.5

Overview

Voyage AI voyage-multimodal-3.5 embeds text, images and video frames into a shared retrieval space. It handles interleaved content such as document screenshots, tables and scenes, with 32,000-token inputs and a default 1024-dimensional representation.

Accepted inputs
Text · token_ids
Results
embedding
About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

voyage-multimodal-3.5 is Voyage AI’s embedding model for retrieval across text, images and video. It processes interleaved text and visual content through a single transformer encoder, representing a complete multimodal input in a shared vector space. The 3.5 edition adds explicit video-frame support and flexible embedding dimensions.

Preserve the relationship between text and visuals

Prepare a document page or section in the form that preserves its useful visual information. A slide containing a chart and a short explanation can be represented with the slide image and accompanying text in the same ordered input. For a PDF-based collection, the documented visual input is a page screenshot or other image representation of the document.

For a report chart, retain the title, axis labels and legend in the image. Attach explanatory text when it provides the context needed to interpret the visual. Store the page number and source identifier beside the resulting vector so a retrieved candidate can open the relevant page rather than merely return a document name.

The maker’s input format supports sequences of text, images and videos. Its published image formats are PNG, JPEG, WebP and GIF, with MP4 for video. Visual content can be represented through URLs or Base64 data in the documented recipe; keep one representation style consistently within a request.

Retrieve a scene rather than an entire long video

The model represents video as an ordered sequence of frames. The maker recommends dividing a long video into related scenes, aligning scene boundaries with available transcript timestamps and retaining the corresponding transcript text. Lower resolution or a reduced frame rate can help a semantically continuous scene fit its context budget.

For a training-video collection, a query might ask for the scene that demonstrates adjusting a particular control. Associate each indexed scene with its time range. Return the matching scene and inspect the frames or original clip for the actual action, rather than treating the retrieved vector as a written description of everything in the recording.

Transcript text can contribute when prepared as part of the multimodal input. Video-frame embedding itself does not supply a speech transcript.

Context and preparation limits

The stated context length is 32,000 tokens per input. Voyage counts every 560 image pixels and every 1120 video pixels as a token in its published calculation, so visual content shares that budget with text. The documented limits also include 16 million pixels and 20 MB per image, and 20 MB per video. A list contains at most 1000 inputs and 320,000 combined tokens.

The default truncation setting clips an over-length input; if that boundary falls within an image, the entire image is discarded. Preparing complete pages or scenes within the budget therefore preserves more predictable input content. The alternative documented setting rejects over-length inputs instead of truncating them.

Vector dimensions and retrieval roles

The default output dimension is 1024, with 256, 512 and 2048 dimensions also documented for this edition. The announcement describes Matryoshka embeddings and floating-point, signed or unsigned 8-bit, and binary representations. Retain the chosen dimension and representation with the index.

Voyage’s retrieval recipe distinguishes query and document inputs. A query can be text or an image, and indexed documents can combine text and visuals. One vector represents each complete input sequence; store its source page, image or scene association so the ranked result remains inspectable.

Use the returned visual source

A retrieval stage can locate a report page, table, slide or scene relevant to the query. The answer-writing or analysis stage then reads that source material. For a table, inspect the actual headers and values before using a result; for a scene, inspect the relevant frames and associated text.

The substantive difference from voyage-multimodal-3 is the 3.5 edition’s explicit video support and additional representation choices. These are embedding capabilities for locating source material, with numerical vectors as output rather than generated images, video or a narrative answer.

Available in Ailoot · inputs & methods

Ailoot Ultra · Embeddings POST /v1/embeddings
Input types
text, token_ids
Output types
embedding
Context
32,000 tokens
Output format
json
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
voyageai/voyage-multimodal-3.5
Default—
FieldinputTypestring|string[]|integer[]|integer[][]RequirementRequiredValues & limits
Minimum items: 1
Conditions: Nonempty homogeneous batch. Token IDs are nonnegative integers.
Input budget: Maximum: 32,000 · Text unit: UTF8 bytes · Token unit: token-array elements
Default—
Fieldencoding_formatTypestringRequirementOptionalValues & limits
float
Defaultfloat
FielddimensionsTypeintegerRequirementNot supportedValues & limits
Minimum: 1
Default—
FielduserTypejson_valueRequirementOptionalValues & limits
Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific.
Default—
Fieldsession_idTypejson_valueRequirementOptionalValues & limits
Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific.
Default—
FieldtraceTypejson_valueRequirementOptionalValues & limits
Conditions: Source allows this JSON metadata field; exact upstream semantics are model-specific.
Default—
FieldproviderTypeobjectRequirementOptionalValues & limits
Conditions: provider.options rejected
Default—
Input material combinations

text_to_embedding

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, input
Parameterinput_shapesContractstring, string[], nonnegative_integer_token_array, nonnegative_integer_token_array[]
Parameterencoding_formatContractfloat
Parameterdimensions_overrideContractfalse
Parametermax_input_budget_unitsContract32000
Parametermultimodal_objectsContractfalse
Parametermaterial_typesContracttext, token_ids

Lifecycle: synchronous_json

Keep every vector index and dimension.

Multimodal model name does not admit image objects on this exact path.

Pricing

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode
Standard rate When fast mode is selected
Flex mode
Standard rate When flex mode is selected
Maximum reasoning effort
Standard rate When maximum reasoning effort uses the default adjustment

Ailoot rates

Prices by configuration

ConfigurationRate scheduleCharge
ConfigurationBase token ratesRate scheduleBase rateCharge
Input · Input tokens $0.00024 / 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 →

Example requests

Ailoot Ultra · Embeddings

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "voyageai/voyage-multimodal-3.5", "input": ["First document", "Second document"]}')\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\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("data",[]): print(json.dumps({"index":x.get("index"),"embedding":x.get("embedding")}))\nPY_RESULT\n

Receive and save results

Ailoot Ultra · Embeddings

json

Keep all completed results

Keep every complete returned response, file and content part.

Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.

If the original response needs checking

No embedding job endpoint is introduced.

Response fields
FieldType
FieldobjectTypestring
FieldmodelTypestring
Fielddata[].indexTypeinteger
Fielddata[].embeddingTypefinite float[]
FieldusageTypeobject
Errors and next steps
ResponseConditionNext step
Response400 · invalid_request_errorConditionInvalid required fields, material representation or parameter valueNext stepCorrect the indicated fields before a new creation request.

Aliases

Model aliases

Ailoot Ultra voyageai/voyage-multimodal-3.5

Method path aliases

Use the method paths shown above.

Related caller IDs

voyageai/voyage-multimodal-3.5

", "method_identity": { "effective_request_model_id": "voyageai/voyage-multimodal-3.5", "fmt": "embeddings", "http": "POST", "path": "/v1/embeddings", "request_model_id": "voyageai/voyage-multimodal-3.5", "route_label": "Ultra" }, "method_key": "Ultra|embeddings|/v1/embeddings|voyageai%2Fvoyage-multimodal-3.5", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.", "errors": [ { "code": null, "condition": "Invalid required fields, material representation or parameter value", "http_status": 400, "recovery": "Correct the indicated fields before a new creation request.", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "No embedding job endpoint is introduced." }, "material_combinations": [ { "alternatives": [ "string", "string[]", "nonnegative_integer_token_array", "nonnegative_integer_token_array[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.", "default_dimensions": null, "family": "embedding", "fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "voyageai/voyage-multimodal-3.5" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "budget": { "maximum": 32000, "text_unit": "UTF8 bytes", "token_unit": "token-array elements" }, "conditions": "Nonempty homogeneous batch. Token IDs are nonnegative integers.", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]|integer[]|integer[][]" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "unsupported", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "pass_through_metadata", "conditions": "Source allows this JSON metadata field; exact upstream semantics are model-specific.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "json_value" }, { "availability": "pass_through_metadata", "conditions": "Source allows this JSON metadata field; exact upstream semantics are model-specific.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "session_id", "required": false, "type": "json_value" }, { "availability": "pass_through_metadata", "conditions": "Source allows this JSON metadata field; exact upstream semantics are model-specific.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "trace", "required": false, "type": "json_value" }, { "availability": "source_interface", "conditions": "provider.options rejected", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "provider", "required": false, "type": "object" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "mixed input kinds", "empty input", "image/audio/file objects", "encoding_format=base64", "dimensions override" ] }, "hints": [ "Keep every vector index and dimension.", "Multimodal model name does not admit image objects on this exact path." ], "input": { "content_type": "application/json", "dimensions_override": false, "encoding_format": [ "float" ], "input_shapes": [ "string", "string[]", "nonnegative_integer_token_array", "nonnegative_integer_token_array[]" ], "material_types": [ "text", "token_ids" ], "max_input_budget_units": 32000, "multimodal_objects": false, "required": [ "model", "input" ] }, "lifecycle": { "mode": "synchronous_json", "unknown": "no embedding job endpoint inferred" }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/embeddings" }, "method_aliases": [], "operation_modes": [ "text_to_embedding" ], "output": { "default_dimensions": null, "family": "embedding", "format": "json", "http_success": 200, "vectors": "one dense float vector per input; indices/model/usage validated" } }, "ctx": 32000, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.00024000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000024", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"voyageai/voyage-multimodal-3.5\", \"input\": [\"First document\", \"Second document\"]}')\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\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "curl · retained exact creation", "language": "bash" }, { "code": "from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.embeddings.create(model='voyageai/voyage-multimodal-3.5',input=[\"First document\",\"Second document\"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n", "label": "Python SDK · all vectors", "language": "python" } ], "family": "openai", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "embeddings", "hints": [ "Keep every vector index and dimension.", "Multimodal model name does not admit image objects on this exact path." ], "http": "POST", "in": 0.24, "input": [ "text", "token_ids" ], "label": "Эмбеддинги", "max_out": null, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.00024000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000024", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "voyageai/voyage-multimodal-3.5", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0.00024000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000024", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } } ], "model_id": "voyageai/voyage-multimodal-3.5", "nativeProvenance": { "input_facts_canonical_sha256": "6eb692ab0a8f52824e948000845e46fdcef6f2cddbf2f495647443ce194c3ff3", "input_html_sha256": "cf5f806dd8cb9f1d13a3990e41b93b8c44a5797053eea3ac3c20587cc6b2be83", "private_audit_sha256": "a561ad3ce59cd87835487d4866c71cf406a1601036bf27662e12dc3a4a233773", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/en/voyageai-voyage-multimodal-3-5/", "description": "Voyage AI voyage-multimodal-3.5 embeds text, images and video frames into a shared retrieval space. It handles interleaved content such as document screenshots, tables and scenes, with 32,000-token inputs and a default 1024-dimensional representation.", "locale": "en", "md_url": "https://ailoot.ai/models/en/voyageai-voyage-multimodal-3-5/index.md", "title": "VoyageAI by MongoDB: voyage-multimodal-3.5 — Ailoot", "url": "https://ailoot.ai/models/en/voyageai-voyage-multimodal-3-5/" }, "rawModel": { "about": "voyage-multimodal-3.5 is Voyage AI’s embedding model for retrieval across text, images and video. It processes interleaved text and visual content through a single transformer encoder, representing a complete multimodal input in a shared vector space. The 3.5 edition adds explicit video-frame support and flexible embedding dimensions.\n\n### Preserve the relationship between text and visuals\n\nPrepare a document page or section in the form that preserves its useful visual information. A slide containing a chart and a short explanation can be represented with the slide image and accompanying text in the same ordered input. For a PDF-based collection, the documented visual input is a page screenshot or other image representation of the document.\n\nFor a report chart, retain the title, axis labels and legend in the image. Attach explanatory text when it provides the context needed to interpret the visual. Store the page number and source identifier beside the resulting vector so a retrieved candidate can open the relevant page rather than merely return a document name.\n\nThe maker’s input format supports sequences of text, images and videos. Its published image formats are PNG, JPEG, WebP and GIF, with MP4 for video. Visual content can be represented through URLs or Base64 data in the documented recipe; keep one representation style consistently within a request.\n\n### Retrieve a scene rather than an entire long video\n\nThe model represents video as an ordered sequence of frames. The maker recommends dividing a long video into related scenes, aligning scene boundaries with available transcript timestamps and retaining the corresponding transcript text. Lower resolution or a reduced frame rate can help a semantically continuous scene fit its context budget.\n\nFor a training-video collection, a query might ask for the scene that demonstrates adjusting a particular control. Associate each indexed scene with its time range. Return the matching scene and inspect the frames or original clip for the actual action, rather than treating the retrieved vector as a written description of everything in the recording.\n\nTranscript text can contribute when prepared as part of the multimodal input. Video-frame embedding itself does not supply a speech transcript.\n\n### Context and preparation limits\n\nThe stated context length is 32,000 tokens per input. Voyage counts every 560 image pixels and every 1120 video pixels as a token in its published calculation, so visual content shares that budget with text. The documented limits also include 16 million pixels and 20 MB per image, and 20 MB per video. A list contains at most 1000 inputs and 320,000 combined tokens.\n\nThe default truncation setting clips an over-length input; if that boundary falls within an image, the entire image is discarded. Preparing complete pages or scenes within the budget therefore preserves more predictable input content. The alternative documented setting rejects over-length inputs instead of truncating them.\n\n### Vector dimensions and retrieval roles\n\nThe default output dimension is 1024, with 256, 512 and 2048 dimensions also documented for this edition. The announcement describes Matryoshka embeddings and floating-point, signed or unsigned 8-bit, and binary representations. Retain the chosen dimension and representation with the index.\n\nVoyage’s retrieval recipe distinguishes query and document inputs. A query can be text or an image, and indexed documents can combine text and visuals. One vector represents each complete input sequence; store its source page, image or scene association so the ranked result remains inspectable.\n\n### Use the returned visual source\n\nA retrieval stage can locate a report page, table, slide or scene relevant to the query. The answer-writing or analysis stage then reads that source material. For a table, inspect the actual headers and values before using a result; for a scene, inspect the relevant frames and associated text.\n\nThe substantive difference from voyage-multimodal-3 is the 3.5 edition’s explicit video support and additional representation choices. These are embedding capabilities for locating source material, with numerical vectors as output rather than generated images, video or a narrative answer.", "alias_of": null, "aliases": [], "author": "VoyageAI by MongoDB", "available": null, "canonical_model": "voyageai/voyage-multimodal-3.5", "capabilities": { "context_length": 32000, "manufacturer_input": [ "text", "image" ], "manufacturer_output": [ "embeddings" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.00024000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000024", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" } ], "summary": "Full configuration pricing in details." } ], "ctx": 32000, "entity_type": "model", "formats": [ "embeddings" ], "id": "voyageai/voyage-multimodal-3.5", "input": [ "text", "token_ids" ], "kind": "embedding", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.", "errors": [ { "code": null, "condition": "Invalid required fields, material representation or parameter value", "http_status": 400, "recovery": "Correct the indicated fields before a new creation request.", "type": "invalid_request_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "create": { "http": "POST", "path": "/v1/embeddings" }, "job_read": null, "mode": "synchronous_json", "unknown": "No embedding job endpoint is introduced." }, "material_combinations": [ { "alternatives": [ "string", "string[]", "nonnegative_integer_token_array", "nonnegative_integer_token_array[]" ], "mode": "text_to_embedding" } ], "operation_modes": [ "single_embedding", "batched_embeddings" ], "outputs": { "all_results": "Keep every vector with its index. Vector count must equal input count; dimensions must be consistent.", "default_dimensions": null, "family": "embedding", "fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "data[].index", "type": "integer" }, { "description": null, "name": "data[].embedding", "type": "finite float[]" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "voyageai/voyage-multimodal-3.5" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "budget": { "maximum": 32000, "text_unit": "UTF8 bytes", "token_unit": "token-array elements" }, "conditions": "Nonempty homogeneous batch. Token IDs are nonnegative integers.", "default": null, "default_known": false, "enum": null, "enum_known": false, "min_items": 1, "name": "input", "required": true, "type": "string|string[]|integer[]|integer[][]" }, { "availability": "source_interface", "default": "float", "default_known": true, "enum": [ "float" ], "enum_known": true, "name": "encoding_format", "required": false, "type": "string" }, { "availability": "unsupported", "default": null, "default_known": false, "enum": null, "enum_known": false, "minimum": 1, "name": "dimensions", "required": false, "type": "integer" }, { "availability": "pass_through_metadata", "conditions": "Source allows this JSON metadata field; exact upstream semantics are model-specific.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "user", "required": false, "type": "json_value" }, { "availability": "pass_through_metadata", "conditions": "Source allows this JSON metadata field; exact upstream semantics are model-specific.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "session_id", "required": false, "type": "json_value" }, { "availability": "pass_through_metadata", "conditions": "Source allows this JSON metadata field; exact upstream semantics are model-specific.", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "trace", "required": false, "type": "json_value" }, { "availability": "source_interface", "conditions": "provider.options rejected", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "provider", "required": false, "type": "object" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [ "mixed input kinds", "empty input", "image/audio/file objects", "encoding_format=base64", "dimensions override" ] }, "hints": [ "Keep every vector index and dimension.", "Multimodal model name does not admit image objects on this exact path." ], "input": { "content_type": "application/json", "dimensions_override": false, "encoding_format": [ "float" ], "input_shapes": [ "string", "string[]", "nonnegative_integer_token_array", "nonnegative_integer_token_array[]" ], "material_types": [ "text", "token_ids" ], "max_input_budget_units": 32000, "multimodal_objects": false, "required": [ "model", "input" ] }, "lifecycle": { "mode": "synchronous_json", "unknown": "no embedding job endpoint inferred" }, "manufacturer_capability": null, "method": { "http": "POST", "path": "/v1/embeddings" }, "method_aliases": [], "operation_modes": [ "text_to_embedding" ], "output": { "default_dimensions": null, "family": "embedding", "format": "json", "http_success": 200, "vectors": "one dense float vector per input; indices/model/usage validated" } }, "ctx": 32000, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.00024000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000024", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"voyageai/voyage-multimodal-3.5\", \"input\": [\"First document\", \"Second document\"]}')\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\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"data\",[]): print(json.dumps({\"index\":x.get(\"index\"),\"embedding\":x.get(\"embedding\")}))\nPY_RESULT\n", "label": "curl · retained exact creation", "language": "bash" }, { "code": "from openai import OpenAI\nimport os\n\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.embeddings.create(model='voyageai/voyage-multimodal-3.5',input=[\"First document\",\"Second document\"])\nprint(result)\nfor item in result.data:print(item.index,item.embedding)\n", "label": "Python SDK · all vectors", "language": "python" } ], "family": "openai", "fast_multiplier": 1, "flex_multiplier": 1, "fmt": "embeddings", "hints": [ "Keep every vector index and dimension.", "Multimodal model name does not admit image objects on this exact path." ], "http": "POST", "in": 0.24, "input": [ "text", "token_ids" ], "label": "Эмбеддинги", "max_out": null, "max_reasoning_effort_multiplier": 1, "method_aliases": [], "out": 0, "output": [ "embedding" ], "path": "/v1/embeddings", "price_conditions": [ { "label": "Fast mode", "value": "Standard rate", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Standard rate", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Standard rate", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "token", "image_input_price": null, "image_output_price": null, "per_request_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": "0.00024000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000024", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "request_model_id": "voyageai/voyage-multimodal-3.5", "route_label": "Ultra", "status_reads": [], "tiers": [], "units": [ { "amount": "0.00024000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000024", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "model_aliases": [ { "canonical_model_id": "voyageai/voyage-multimodal-3.5", "request_model_id": "voyageai/voyage-multimodal-3.5", "route_label": "Ultra" } ], "name": "VoyageAI by MongoDB: voyage-multimodal-3.5", "price": { "in": 0.24, "in_label": null, "out": 0, "out_label": null, "scope_label": "Token rates", "sort_in": 0.24, "sort_out": 0, "varies": false }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Эмбеддинги · Base token rates", "units": [ { "amount": "0.00024000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": "0.00000024", "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": "0", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": "0", "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": false, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] } ], "public_id": "voyageai/voyage-multimodal-3.5", "short": "Voyage AI voyage-multimodal-3.5 embeds text, images and video frames into a shared retrieval space. It handles interleaved content such as document screenshots, tables and scenes, with 32,000-token inputs and a default 1024-dimensional representation." }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "Voyage AI voyage-multimodal-3.5 embeds text, images and video frames into a shared retrieval space. It handles interleaved content such as document screenshots, tables and scenes, with 32,000-token inputs and a default 1024-dimensional representation.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "177e9ad28b9914665f926d51fb3a46f459de125ed0021036a1d4de6e7d646a79", "renderer_sha256": "fed50305bd3bcc4980ac14df23640efb8c1bc1e819f9d53643d6f43e8974d3fe" }, "sourceRevision": "abf660b0143bc3cf3ffea5c5c59ccce682a15b4852e7588e38a1aea3cf336228" }