📖 feat: Add Claude Fable 5.1 Support (#15512)

Claude Fable 5.1 (`claude-fable-5-1`, GA 2026-09-01) succeeds Claude Fable 5
at the same input/output prices, with a 1M context window and 128K max output.
The Mythos-class helpers added for Fable 5 already match it — `isMythosClassModel`
tests `claude-(?:fable|mythos)[-.]?\d`, so adaptive thinking, summarized-display
opt-in, sampling omission, 1M context, the 128K output clamp, prompt caching,
the Vertex multi-region gate, and the Bedrock PDF exemption all cover 5.1
without a code change. What was missing was registration and pricing.

Cache reads are the one rate that differs, and the substring matcher would have
silently gotten it wrong: `claude-fable-5-1` falls through to the `claude-fable-5`
key, which prices cache hits at the usual 0.1x base input ($1/MTok). Fable 5.1
and Mythos 5.1 price them at 0.025x ($0.25/MTok), so every cache read would have
billed 4x — on exactly the long agentic sessions this model is built for.

- Register `claude-fable-5-1` in the shared Anthropic list and
  `global.anthropic.claude-fable-5-1` in the Bedrock list
- Add 1M context / 128K output entries for `claude-fable-5-1` and
  `claude-mythos-5-1`
- Add $10/$50 rates and `{ write: 12.5, read: 0.25 }` cache rates for both
- Update the `.env.example` and Vertex `librechat.example.yaml` examples
- Test that 5.1 resolves to its own key rather than collapsing onto 5.0, across
  token maps, pricing, cache rates, and Mythos-class detection

The three documented breaking changes from Fable 5 need no handling here:
LibreChat never sends a forced `tool_choice` on the Anthropic path (the agents
SDK omits the param when unset, so the API default `auto` applies); thinking
blocks an earlier model can't read are dropped server-side, unbilled; and
history is rebuilt from stored content parts rather than replayed signed
thinking blocks, so the prefix-binding check has nothing to reject.

Refs #15506

.env.example

@@ -419,14 +419,14 @@ PROXY=
 #============#
 
 ANTHROPIC_API_KEY=user_provided
-# ANTHROPIC_MODELS=claude-fable-5,claude-opus-5,claude-opus-4-8,claude-opus-4-7,claude-sonnet-5,claude-sonnet-4-6,claude-opus-4-6,claude-opus-4-20250514,claude-3-7-sonnet-20250219,claude-3-5-sonnet-20241022,claude-3-5-haiku-20241022,claude-3-opus-20240229,claude-3-sonnet-20240229,claude-3-haiku-20240307
+# ANTHROPIC_MODELS=claude-fable-5-1,claude-fable-5,claude-opus-5,claude-opus-4-8,claude-opus-4-7,claude-sonnet-5,claude-sonnet-4-6,claude-opus-4-6,claude-opus-4-20250514,claude-3-7-sonnet-20250219,claude-3-5-sonnet-20241022,claude-3-5-haiku-20241022,claude-3-opus-20240229,claude-3-sonnet-20240229,claude-3-haiku-20240307
 # ANTHROPIC_REVERSE_PROXY=
 
 # Set to true to use Anthropic models through Google Vertex AI instead of direct API
 # ANTHROPIC_USE_VERTEX=
 # Supports regional locations like us-east5 and multi-region locations: us, eu, global
 # IMPORTANT: specific regional endpoints (us-east5, europe-west1, ...) only serve Claude Sonnet 4.6
-# and earlier. Newer models (Opus 4.7+, Opus 5, Sonnet 5, Fable 5) require `global` or a multi-region
+# and earlier. Newer models (Opus 4.7+, Opus 5, Sonnet 5, Fable 5/5.1) require `global` or a multi-region
 # location (`us`/`eu`) and will 404 on a specific region. `global` also avoids the 10% regional premium.
 # ANTHROPIC_VERTEX_REGION=us-east5
 
@@ -490,8 +490,8 @@ ANTHROPIC_API_KEY=user_provided
 # Note: This example list is not meant to be exhaustive. If omitted, all known, supported model IDs will be included for you.
 # Claude 4+ models cannot be invoked on-demand by their bare `anthropic.` foundation-model ID; Bedrock requires a
 # cross-region inference profile (`global.` or `us.`) for those. The `global.` profile has no regional pricing premium.
-# BEDROCK_AWS_MODELS=global.anthropic.claude-fable-5,global.anthropic.claude-opus-5,global.anthropic.claude-opus-4-8,global.anthropic.claude-opus-4-7,global.anthropic.claude-sonnet-5,global.anthropic.claude-sonnet-4-6,global.anthropic.claude-opus-4-6-v1,global.anthropic.claude-haiku-4-5-20251001-v1:0,meta.llama3-1-8b-instruct-v1:0
-# US-only routing alternative: us.anthropic.claude-fable-5,us.anthropic.claude-opus-5,us.anthropic.claude-opus-4-8,us.anthropic.claude-opus-4-7,us.anthropic.claude-sonnet-5,us.anthropic.claude-sonnet-4-6,us.anthropic.claude-opus-4-6-v1
+# BEDROCK_AWS_MODELS=global.anthropic.claude-fable-5-1,global.anthropic.claude-fable-5,global.anthropic.claude-opus-5,global.anthropic.claude-opus-4-8,global.anthropic.claude-opus-4-7,global.anthropic.claude-sonnet-5,global.anthropic.claude-sonnet-4-6,global.anthropic.claude-opus-4-6-v1,global.anthropic.claude-haiku-4-5-20251001-v1:0,meta.llama3-1-8b-instruct-v1:0
+# US-only routing alternative: us.anthropic.claude-fable-5-1,us.anthropic.claude-fable-5,us.anthropic.claude-opus-5,us.anthropic.claude-opus-4-8,us.anthropic.claude-opus-4-7,us.anthropic.claude-sonnet-5,us.anthropic.claude-sonnet-4-6,us.anthropic.claude-opus-4-6-v1
 # List the profiles available to your account with: aws bedrock list-inference-profiles --region <your-region>
 
 # See all Bedrock model IDs here: https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns
@@ -503,9 +503,10 @@ ANTHROPIC_API_KEY=user_provided
 # The following models are not support due to not supporting conversation history:
 # ai21.j2-ultra-v1, cohere.command-text-v14, cohere.command-light-text-v14
 
-# Claude Mythos-class models (anthropic.claude-fable-5, anthropic.claude-mythos-5) are inference-profile
-# only on Bedrock — use a profile ID (e.g. us.anthropic.claude-fable-5) — and require opting into Anthropic
-# data sharing via the Bedrock Data Retention API/console before they can be invoked.
+# Claude Mythos-class models (anthropic.claude-fable-5-1, anthropic.claude-mythos-5-1, and their 5.0
+# predecessors) are inference-profile only on Bedrock — use a profile ID (e.g. us.anthropic.claude-fable-5-1)
+# — and require opting into Anthropic data sharing via the Bedrock Data Retention API/console before they
+# can be invoked.
 
 #============#
 # Google     #

api/utils/tokens.spec.js

@@ -1640,6 +1640,40 @@ describe('Claude Model Tests', () => {
     });
   });
 
+  it('should return correct context length for Claude Fable 5.1 (1M)', () => {
+    expect(maxTokensMap[EModelEndpoint.anthropic]['claude-fable-5-1']).toBe(1000000);
+    expect(maxTokensMap[EModelEndpoint.anthropic]['claude-mythos-5-1']).toBe(1000000);
+    expect(getModelMaxTokens('claude-fable-5-1', EModelEndpoint.anthropic)).toBe(1000000);
+    expect(getModelMaxTokens('claude-mythos-5-1', EModelEndpoint.anthropic)).toBe(1000000);
+  });
+
+  it('should return correct max output tokens for Claude Fable 5.1 (128K)', () => {
+    const { getModelMaxOutputTokens } = require('@librechat/api');
+    expect(maxOutputTokensMap[EModelEndpoint.anthropic]['claude-fable-5-1']).toBe(128000);
+    expect(maxOutputTokensMap[EModelEndpoint.anthropic]['claude-mythos-5-1']).toBe(128000);
+    expect(getModelMaxOutputTokens('claude-fable-5-1', EModelEndpoint.anthropic)).toBe(128000);
+    expect(getModelMaxOutputTokens('claude-mythos-5-1', EModelEndpoint.anthropic)).toBe(128000);
+  });
+
+  it('should match model names correctly for Claude Fable 5.1 without collapsing to Fable 5', () => {
+    const modelVariations = [
+      'claude-fable-5-1',
+      'claude-fable-5-1-20260901',
+      'claude-fable-5-1-latest',
+      'anthropic/claude-fable-5-1',
+      'claude-fable-5-1/anthropic',
+      'anthropic.claude-fable-5-1',
+    ];
+
+    modelVariations.forEach((model) => {
+      expect(matchModelName(model, EModelEndpoint.anthropic)).toBe('claude-fable-5-1');
+    });
+
+    expect(matchModelName('claude-fable-5-20260609', EModelEndpoint.anthropic)).toBe(
+      'claude-fable-5',
+    );
+  });
+
   it('should return correct context length for Claude Sonnet 4.6 (1M)', () => {
     expect(getModelMaxTokens('claude-sonnet-4-6', EModelEndpoint.anthropic)).toBe(
       maxTokensMap[EModelEndpoint.anthropic]['claude-sonnet-4-6'],

librechat.example.yaml

@@ -656,7 +656,7 @@ endpoints:
   #     # Available regions: us-east5, us-central1, europe-west1, europe-west4, asia-southeast1
   #     # Multi-region endpoints: us, eu, global
   #     # IMPORTANT: specific regional endpoints only serve Claude Sonnet 4.6 and earlier. Newer
-  #     # models (Opus 4.7+, Opus 5, Sonnet 5, Fable 5) require "global" or a multi-region value
+  #     # models (Opus 4.7+, Opus 5, Sonnet 5, Fable 5/5.1) require "global" or a multi-region value
   #     # ("us"/"eu") and will 404 on a specific region. "global" also avoids the 10% regional premium.
   #     region: "us-east5"
   #     # Path to Google service account key file (optional)
@@ -675,6 +675,7 @@ endpoints:
   #     # Option 1: Simple array (legacy format - model name = deployment name)
   #     # Use this if you want the technical model IDs to show in the UI
   #     # models:
+  #     #   - "claude-fable-5-1"
   #     #   - "claude-fable-5"
   #     #   - "claude-opus-5"
   #     #   - "claude-opus-4-8"
@@ -688,6 +689,8 @@ endpoints:
   #     # The deploymentName is the actual Vertex AI model ID used for API calls
   #     # You can use friendly names (avoid spaces for cleaner YAML) or technical IDs as keys
   #     models:
+  #       claude-fable-5.1:
+  #         deploymentName: claude-fable-5-1
   #       claude-fable-5:
   #         deploymentName: claude-fable-5
   #       claude-opus-5:

packages/api/src/utils/tokens.ts

@@ -183,6 +183,8 @@ const anthropicModels = {
   'claude-opus-5': 1000000,
   'claude-fable-5': 1000000,
   'claude-mythos-5': 1000000,
+  'claude-fable-5-1': 1000000,
+  'claude-mythos-5-1': 1000000,
 };
 
 const ANTHROPIC_CONTEXT_1M = 1000000;
@@ -539,6 +541,8 @@ const anthropicMaxOutputs = {
   'claude-opus-5': 128000,
   'claude-fable-5': 128000,
   'claude-mythos-5': 128000,
+  'claude-fable-5-1': 128000,
+  'claude-mythos-5-1': 128000,
   'claude-3.5-sonnet': 8192,
   'claude-3-5-sonnet': 8192,
   'claude-3.7-sonnet': 128000,

packages/data-provider/specs/bedrock.spec.ts

@@ -29,6 +29,8 @@ describe('isMythosClassModel (single source of truth for Fable/Mythos)', () => {
       expect(isMythosClassModel(`anthropic.claude-${family}-5`)).toBe(true);
       expect(isMythosClassModel(`us.anthropic.claude-${family}-5`)).toBe(true);
       expect(isMythosClassModel(`claude-${family}-5-20260609`)).toBe(true);
+      expect(isMythosClassModel(`claude-${family}-5-1`)).toBe(true);
+      expect(isMythosClassModel(`global.anthropic.claude-${family}-5-1`)).toBe(true);
     });
   });
 

packages/data-provider/src/config.ts

@@ -2663,6 +2663,7 @@ const sharedOpenAIModels = [
 ];
 
 const sharedAnthropicModels = [
+  'claude-fable-5-1',
   'claude-fable-5',
   'claude-opus-5',
   'claude-opus-4-8',
@@ -2698,6 +2699,7 @@ const sharedAnthropicModels = [
  * availability); Opus 4.1 has no global profile, so it uses `us.`.
  */
 export const bedrockModels = [
+  'global.anthropic.claude-fable-5-1',
   'global.anthropic.claude-fable-5',
   'global.anthropic.claude-opus-5',
   'global.anthropic.claude-opus-4-8',

packages/data-schemas/src/methods/tx.spec.ts

@@ -2661,6 +2661,38 @@ describe('Claude Model Tests', () => {
     );
   });
 
+  it('should pin Claude Fable 5.1 pricing to $10 / $50 per MTok', () => {
+    expect(tokenValues['claude-fable-5-1']).toEqual({ prompt: 10, completion: 50 });
+    expect(tokenValues['claude-mythos-5-1']).toEqual({ prompt: 10, completion: 50 });
+  });
+
+  it('should charge Claude Fable 5.1 cache reads at a quarter of the Fable 5 rate', () => {
+    expect(cacheTokenValues['claude-fable-5-1']).toEqual({ write: 12.5, read: 0.25 });
+    expect(cacheTokenValues['claude-mythos-5-1']).toEqual({ write: 12.5, read: 0.25 });
+    expect(getCacheMultiplier({ model: 'claude-fable-5-1', cacheType: 'read' })).toBe(0.25);
+    expect(getCacheMultiplier({ model: 'claude-fable-5-1', cacheType: 'write' })).toBe(12.5);
+    expect(getCacheMultiplier({ model: 'claude-fable-5', cacheType: 'read' })).toBe(1);
+  });
+
+  it('should handle Claude Fable 5.1 model name variations without collapsing to Fable 5', () => {
+    const modelVariations = [
+      'claude-fable-5-1',
+      'claude-fable-5-1-20260901',
+      'claude-fable-5-1-latest',
+      'anthropic/claude-fable-5-1',
+      'claude-fable-5-1/anthropic',
+      'anthropic.claude-fable-5-1',
+      'global.anthropic.claude-fable-5-1',
+    ];
+
+    modelVariations.forEach((model) => {
+      expect(getValueKey(model)).toBe('claude-fable-5-1');
+      expect(getCacheMultiplier({ model, cacheType: 'read' })).toBe(0.25);
+    });
+
+    expect(getValueKey('claude-fable-5-20260609')).toBe('claude-fable-5');
+  });
+
   it('should return correct prompt and completion rates for Claude Sonnet 5', () => {
     expect(getMultiplier({ model: 'claude-sonnet-5', tokenType: 'prompt' })).toBe(
       tokenValues['claude-sonnet-5'].prompt,

packages/data-schemas/src/methods/tx.ts

@@ -186,6 +186,8 @@ export const tokenValues: Record<string, { prompt: number; completion: number }>
     'claude-opus-5': { prompt: 5, completion: 25 },
     'claude-fable-5': { prompt: 10, completion: 50 },
     'claude-mythos-5': { prompt: 10, completion: 50 },
+    'claude-fable-5-1': { prompt: 10, completion: 50 },
+    'claude-mythos-5-1': { prompt: 10, completion: 50 },
     'claude-sonnet-4': { prompt: 3, completion: 15 },
     'claude-sonnet-4-5': { prompt: 3, completion: 15 },
     'claude-sonnet-4-6': { prompt: 3, completion: 15 },
@@ -367,6 +369,9 @@ export const cacheTokenValues: Record<string, { write: number; read: number }> =
   'claude-opus-5': { write: 6.25, read: 0.5 },
   'claude-fable-5': { write: 12.5, read: 1 },
   'claude-mythos-5': { write: 12.5, read: 1 },
+  // Fable/Mythos 5.1 cache reads are 0.025x base input, not the usual 0.1x.
+  'claude-fable-5-1': { write: 12.5, read: 0.25 },
+  'claude-mythos-5-1': { write: 12.5, read: 0.25 },
   'gpt-4o': { write: 2.5, read: 1.25 },
   'gpt-4o-mini': { write: 0.15, read: 0.075 },
   'gpt-4.1': { write: 2, read: 0.5 },