Creator Center
/Model/Tokener.ai
🤖

Tokener.ai

Verified by Dify
No ratings yet
27
L
langgenius/tokener

Tokener.ai model provider for Dify.

Tokener.ai

Configure

Tokener.ai provides language, text embedding, rerank, speech recognition, and text-to-speech models for Dify.

  1. Install Tokener.ai from the Dify Marketplace.
  2. Create an API key in the Tokener.ai Console.
  3. Open Settings → Model Provider → Tokener.ai and enter the key.

The API endpoint changes from to .
Existing keys from the same Tokener.ai Console remain valid. The API key must have access to the selected model.

In a Workflow or Chatflow, select Tokener.ai and a model in the corresponding node or model configuration.
Embedding models appear in the provider list after installation. Embeddings retain the selected model ID and default vector dimensions.
For and , the plugin sends up to 10 texts per request.
Both models accept up to 8192 tokens per text and retain the default 1024 vector dimensions.
Other embedding models use up to 32 texts per request. The plugin does not truncate texts.
For , , and , the plugin sends for queries and for documents.
These models retain their default vector dimensions: 1024 for both v3 models and 1536 for v4.
For , the plugin adds Google's retrieval prefixes to distinguish queries from documents. Existing knowledge bases need cache cleanup and reindexing after all plugin instances are updated.
Self-hosted administrators must clear document caches for provider and model . Also clear matching query caches: Redis prefix , prefixed with and a colon when configured. These caches are shared across knowledge bases.
Then, during low traffic, switch each affected knowledge base to another configured embedding model, then back. After each switch, wait for indexing and resolve document errors.
Each switch can incur embedding charges and causes empty, then partial retrieval results while applications continue running. Saving the same model does not rebuild. Failed documents are not retried automatically.
Dify Cloud users must contact support for cache cleanup before switching models. The retrieval-quality effect of mixing old and new vectors is unverified.
For , the plugin sends for queries and for documents. The input text stays unchanged.

Provider, LLM, and embedding validation use authenticated .
Rerank validation sends a small rerank request. Speech validation sends demo audio or a short speech request.
These validation requests can incur charges.

Model parameters

The generator reads family rules from and capabilities from the catalog.
The SDK filters parameters that the selected model does not declare.
New reasoning models expose no sampling controls unless a profile explicitly permits them.
Unknown families expose the output limit and catalog-declared structured output controls.

GPT-4o-mini and its 2024-07-18 version expose temperature, top-p, presence penalty, and frequency penalty controls.
For , , , , and , temperature ranges from 0 to 1.

The existing GPT-5.6 profile retains seed and reasoning effort controls.
The existing DeepSeek V4, GLM-5.2, and Kimi K3 profiles retain their verified sampling controls and seed.
Other GPT-5, GPT-6, and o-series models expose no unverified sampling or reasoning controls.
Claude, Gemini, Grok, Qwen, DeepSeek, GLM, Kimi, and MiniMax family rules expose sampling only for models without reasoning capability.
Catalog metadata does not describe deployment parameter overrides. Recheck the profiles when the upstream contract or deployment policy changes.

Sync models

Run the generator from this plugin directory with a complete Tokener catalog snapshot JSON file.
The snapshot must include restricted models available to your users. The public catalog hides restricted models.
An OpenAI response lacks the context, capability, and price metadata needed for generation.

The snapshot must contain the complete array. Each item supplies , , , , and model metadata.
The generator includes models with both and , regardless of access scope.
Both display labels use the public model ID. Internal identifiers and display names are excluded.
Decision routes are outside the supported Dify model types. Unknown categories stop generation and identify the affected public model IDs.
Keep the source snapshot outside Git. The snapshot does not prove that a particular API key has model access.

The generator also accepts a complete machine catalog snapshot with , , and .
The input path is required. If the file contains an HTML login page, re-authenticate and obtain a new JSON snapshot.
Never put keys in snapshots or commits.

The default selection is all five supported types.
Select , , , , or to update one type.
Synchronization validates all selected types before writing. It deletes model YAMLs that lack a matching snapshot entry in each selected type.
An empty type produces an empty position list and removes its model definitions. reports drift without writing.

Embedding prices use the catalog input price. Rerank and audio definitions omit optional Dify prices because their billing units differ.
LLM prices show the catalog base input and output rates. Dify's model definitions cannot represent cache read, cache write, or context-tier prices.
Tokener.ai determines charges. Audio models require complete voice or upload metadata and prices.
New audio models use their catalog type and metadata, without an ID allowlist.

Audio behavior

Speech recognition uploads files to . Upload limits and extensions come from catalog metadata. Upload limits use decimal megabytes.
The diarization model uses automatic chunking and returns text without speaker labels.
Text-to-speech sends requests to . Voices, languages, the default voice, text limits, and format come from catalog metadata.
Voice languages must use Dify UI locale codes. An unsupported code stops generation and identifies the model, voice, and code.

Long speech text is split into sequential requests. The text limit counts characters, as in the OpenAI plugin.
The plugin streams audio bytes in order. A later failure raises an error after any audio already sent.
An empty stream raises an error. Supported formats are , , , and .
and are rejected because concatenated files can truncate playback.

Audio definitions appear only when the snapshot contains matching available models.
Live audio generation, Dify playback, and production latency remain unverified.
A segment without output for more than 120 seconds can exceed the serverless idle limit.

Support

Open an issue in dify-official-plugins.
Include the Dify version, plugin version, model ID, and request ID. Never include API keys or prompt content.

Apache License 2.0. See LICENSE.

CATEGORY
Model
VERSION
0.4.4
langgenius·Updated 12 days ago
REQUIREMENTS
LLM invocation
Maximum memory
256MB
Access domain

Some outbound calls build their address at runtime, so the list may be incomplete.

Detected
Security
Security Rating

Last checked 11/11/2026 03:34 AM · version 0.4.4

Give a rate
SHARE WITH