🤖 feat: Claude Opus 4.6 - 1M Context, Premium Pricing, Adaptive Thinking (#11670)

* feat: Implement new features for Claude Opus 4.6 model

- Added support for tiered pricing based on input token count for the Claude Opus 4.6 model.
- Updated token value calculations to include inputTokenCount for accurate pricing.
- Enhanced transaction handling to apply premium rates when input tokens exceed defined thresholds.
- Introduced comprehensive tests to validate pricing logic for both standard and premium rates across various scenarios.
- Updated related utility functions and models to accommodate new pricing structure.

This change improves the flexibility and accuracy of token pricing for the Claude Opus 4.6 model, ensuring users are charged appropriately based on their usage.

* feat: Add effort field to conversation and preset schemas

- Introduced a new optional `effort` field of type `String` in both the `IPreset` and `IConversation` interfaces.
- Updated the `conversationPreset` schema to include the `effort` field, enhancing the data structure for better context management.

* chore: Clean up unused variable and comments in initialize function

* chore: update dependencies and SDK versions

- Updated @anthropic-ai/sdk to version 0.73.0 in package.json and overrides.
- Updated @anthropic-ai/vertex-sdk to version 0.14.3 in packages/api/package.json.
- Updated @librechat/agents to version 3.1.34 in packages/api/package.json.
- Refactored imports in packages/api/src/endpoints/anthropic/vertex.ts for consistency.

* chore: remove postcss-loader from dependencies

* feat: Bedrock model support for adaptive thinking configuration

- Updated .env.example to include new Bedrock model IDs for Claude Opus 4.6.
- Refactored bedrockInputParser to support adaptive thinking for Opus models, allowing for dynamic thinking configurations.
- Introduced a new function to check model compatibility with adaptive thinking.
- Added an optional `effort` field to the input schemas and updated related configurations.
- Enhanced tests to validate the new adaptive thinking logic and model configurations.

* feat: Add tests for Opus 4.6 adaptive thinking configuration

* feat: Update model references for Opus 4.6 by removing version suffix

* feat: Update @librechat/agents to version 3.1.35 in package.json and package-lock.json

* chore: @librechat/agents to version 3.1.36 in package.json and package-lock.json

* feat: Normalize inputTokenCount for spendTokens and enhance transaction handling

- Introduced normalization for promptTokens to ensure inputTokenCount does not go negative.
- Updated transaction logic to reflect normalized inputTokenCount in pricing calculations.
- Added comprehensive tests to validate the new normalization logic and its impact on transaction rates for both standard and premium models.
- Refactored related functions to improve clarity and maintainability of token value calculations.

* chore: Simplify adaptive thinking configuration in helpers.ts

- Removed unnecessary type casting for the thinking property in updatedOptions.
- Ensured that adaptive thinking is directly assigned when conditions are met, improving code clarity.

* refactor: Replace hard-coded token values with dynamic retrieval from maxTokensMap in model tests

* fix: Ensure non-negative token values in spendTokens calculations

- Updated token value retrieval to use Math.max for prompt and completion tokens, preventing negative values.
- Enhanced clarity in token calculations for both prompt and completion transactions.

* test: Add test for normalization of negative structured token values in spendStructuredTokens

- Implemented a test to ensure that negative structured token values are normalized to zero during token spending.
- Verified that the transaction rates remain consistent with the expected standard values after normalization.

* refactor: Bedrock model support for adaptive thinking and context handling

- Added tests for various alternate naming conventions of Claude models to validate adaptive thinking and context support.
- Refactored `supportsAdaptiveThinking` and `supportsContext1m` functions to utilize new parsing methods for model version extraction.
- Updated `bedrockInputParser` to handle effort configurations more effectively and strip unnecessary fields for non-adaptive models.
- Improved handling of anthropic model configurations in the input parser.

* fix: Improve token value retrieval in getMultiplier function

- Updated the token value retrieval logic to use optional chaining for better safety against undefined values.
- Added a test case to ensure that the function returns the default rate when the provided valueKey does not exist in tokenValues.

api/models/tx.js

@@ -174,6 +174,7 @@ const tokenValues = Object.assign(
     'claude-haiku-4-5': { prompt: 1, completion: 5 },
     'claude-opus-4': { prompt: 15, completion: 75 },
     'claude-opus-4-5': { prompt: 5, completion: 25 },
+    'claude-opus-4-6': { prompt: 5, completion: 25 },
     'claude-sonnet-4': { prompt: 3, completion: 15 },
     'command-r': { prompt: 0.5, completion: 1.5 },
     'command-r-plus': { prompt: 3, completion: 15 },
@@ -310,6 +311,7 @@ const cacheTokenValues = {
   'claude-sonnet-4': { write: 3.75, read: 0.3 },
   'claude-opus-4': { write: 18.75, read: 1.5 },
   'claude-opus-4-5': { write: 6.25, read: 0.5 },
+  'claude-opus-4-6': { write: 6.25, read: 0.5 },
   // DeepSeek models - cache hit: $0.028/1M, cache miss: $0.28/1M
   deepseek: { write: 0.28, read: 0.028 },
   'deepseek-chat': { write: 0.28, read: 0.028 },
@@ -328,6 +330,15 @@ const cacheTokenValues = {
   'kimi-k2-thinking-turbo': { write: 1.15, read: 0.15 },
 };
 
+/**
+ * Premium (tiered) pricing for models whose rates change based on prompt size.
+ * Each entry specifies the token threshold and the rates that apply above it.
+ * @type {Object.<string, {threshold: number, prompt: number, completion: number}>}
+ */
+const premiumTokenValues = {
+  'claude-opus-4-6': { threshold: 200000, prompt: 10, completion: 37.5 },
+};
+
 /**
  * Retrieves the key associated with a given model name.
  *
@@ -384,15 +395,27 @@ const getValueKey = (model, endpoint) => {
  * @param {string} [params.model] - The model name to derive the value key from if not provided.
  * @param {string} [params.endpoint] - The endpoint name to derive the value key from if not provided.
  * @param {EndpointTokenConfig} [params.endpointTokenConfig] - The token configuration for the endpoint.
+ * @param {number} [params.inputTokenCount] - Total input token count for tiered pricing.
  * @returns {number} The multiplier for the given parameters, or a default value if not found.
  */
-const getMultiplier = ({ valueKey, tokenType, model, endpoint, endpointTokenConfig }) => {
+const getMultiplier = ({
+  model,
+  valueKey,
+  endpoint,
+  tokenType,
+  inputTokenCount,
+  endpointTokenConfig,
+}) => {
   if (endpointTokenConfig) {
     return endpointTokenConfig?.[model]?.[tokenType] ?? defaultRate;
   }
 
   if (valueKey && tokenType) {
-    return tokenValues[valueKey][tokenType] ?? defaultRate;
+    const premiumRate = getPremiumRate(valueKey, tokenType, inputTokenCount);
+    if (premiumRate != null) {
+      return premiumRate;
+    }
+    return tokenValues[valueKey]?.[tokenType] ?? defaultRate;
   }
 
   if (!tokenType || !model) {
@@ -404,10 +427,33 @@ const getMultiplier = ({ valueKey, tokenType, model, endpoint, endpointTokenConf
     return defaultRate;
   }
 
-  // If we got this far, and values[tokenType] is undefined somehow, return a rough average of default multipliers
+  const premiumRate = getPremiumRate(valueKey, tokenType, inputTokenCount);
+  if (premiumRate != null) {
+    return premiumRate;
+  }
+
   return tokenValues[valueKey]?.[tokenType] ?? defaultRate;
 };
 
+/**
+ * Checks if premium (tiered) pricing applies and returns the premium rate.
+ * Each model defines its own threshold in `premiumTokenValues`.
+ * @param {string} valueKey
+ * @param {string} tokenType
+ * @param {number} [inputTokenCount]
+ * @returns {number|null}
+ */
+const getPremiumRate = (valueKey, tokenType, inputTokenCount) => {
+  if (inputTokenCount == null) {
+    return null;
+  }
+  const premiumEntry = premiumTokenValues[valueKey];
+  if (!premiumEntry || inputTokenCount <= premiumEntry.threshold) {
+    return null;
+  }
+  return premiumEntry[tokenType] ?? null;
+};
+
 /**
  * Retrieves the cache multiplier for a given value key and token type. If no value key is provided,
  * it attempts to derive it from the model name.
@@ -444,8 +490,10 @@ const getCacheMultiplier = ({ valueKey, cacheType, model, endpoint, endpointToke
 
 module.exports = {
   tokenValues,
+  premiumTokenValues,
   getValueKey,
   getMultiplier,
+  getPremiumRate,
   getCacheMultiplier,
   defaultRate,
   cacheTokenValues,