Add AI model pricing, Bedrock provider, and InferenceProvider/ModelFamily split (#18155)

## Summary

- **Model pricing overhaul**: All model constants updated with accurate
pricing in dollars per 1M tokens, including cached input rates, cache
creation rates, and tiered >200k context pricing
- **New providers**: Added Google (Gemini 3.x), Mistral, and AWS Bedrock
as inference providers. Bedrock serves Claude Opus 4.6 and Sonnet 4.6
via AWS, with proper credential handling following the existing S3/SES
pattern
- **InferenceProvider/ModelFamily split**: Refactored `ModelProvider`
into two orthogonal enums — `InferenceProvider` (who serves the model:
auth, SDK, metadata format) and `ModelFamily` (who created it: token
counting semantics). This eliminates growing `||` chains for token
normalization checks like `excludesCachedTokens`
- **Billing improvements**: Reasoning tokens charged at output rate,
cache token discounts applied accurately, real errors thrown to Sentry
on billing failures

## Test plan

- [x] All existing unit tests updated and passing (23 tests across 3
test files)
- [x] Lint passes for both twenty-server and twenty-front
- [ ] CI checks pass


Made with [Cursor](https://cursor.com)

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

packages/twenty-server/src/engine/core-modules/twenty-config/config-variables.ts

@@ -1196,7 +1196,7 @@ export class ConfigVariables {
   })
   @IsOptional()
   DEFAULT_AI_SPEED_MODEL_ID =
-    'gpt-4.1-mini,claude-haiku-4-5-20251001,grok-3-mini';
+    'gpt-5-mini,claude-haiku-4-5-20251001,gemini-3-flash-preview,grok-4-1-fast-reasoning,mistral-large-latest';
 
   @ConfigVariablesMetadata({
     group: ConfigVariablesGroup.LLM,
@@ -1205,7 +1205,8 @@ export class ConfigVariables {
     type: ConfigVariableType.STRING,
   })
   @IsOptional()
-  DEFAULT_AI_PERFORMANCE_MODEL_ID = 'gpt-4.1,claude-sonnet-4-5-20250929,grok-4';
+  DEFAULT_AI_PERFORMANCE_MODEL_ID =
+    'gpt-5.2,claude-sonnet-4-6,gemini-3.1-pro-preview,grok-4,mistral-large-latest';
 
   @ConfigVariablesMetadata({
     group: ConfigVariablesGroup.LLM,
@@ -1271,6 +1272,60 @@ export class ConfigVariables {
   @IsOptional()
   GROQ_API_KEY: string;
 
+  @ConfigVariablesMetadata({
+    group: ConfigVariablesGroup.LLM,
+    isSensitive: true,
+    description: 'API key for Google AI (Gemini) integration',
+    type: ConfigVariableType.STRING,
+  })
+  @IsOptional()
+  GOOGLE_API_KEY: string;
+
+  @ConfigVariablesMetadata({
+    group: ConfigVariablesGroup.LLM,
+    isSensitive: true,
+    description: 'API key for Mistral AI integration',
+    type: ConfigVariableType.STRING,
+  })
+  @IsOptional()
+  MISTRAL_API_KEY: string;
+
+  @ConfigVariablesMetadata({
+    group: ConfigVariablesGroup.LLM,
+    description: 'AWS region for Bedrock integration (e.g., us-east-1)',
+    type: ConfigVariableType.STRING,
+  })
+  @IsAWSRegion()
+  @IsOptional()
+  AWS_BEDROCK_REGION: AwsRegion;
+
+  @ConfigVariablesMetadata({
+    group: ConfigVariablesGroup.LLM,
+    isSensitive: true,
+    description: 'AWS access key ID for Bedrock authentication',
+    type: ConfigVariableType.STRING,
+  })
+  @IsOptional()
+  AWS_BEDROCK_ACCESS_KEY_ID: string;
+
+  @ConfigVariablesMetadata({
+    group: ConfigVariablesGroup.LLM,
+    isSensitive: true,
+    description: 'AWS secret access key for Bedrock authentication',
+    type: ConfigVariableType.STRING,
+  })
+  @IsOptional()
+  AWS_BEDROCK_SECRET_ACCESS_KEY: string;
+
+  @ConfigVariablesMetadata({
+    group: ConfigVariablesGroup.LLM,
+    isSensitive: true,
+    description: 'AWS session token for Bedrock (for IAM role-based auth)',
+    type: ConfigVariableType.STRING,
+  })
+  @IsOptional()
+  AWS_BEDROCK_SESSION_TOKEN: string;
+
   @ConfigVariablesMetadata({
     group: ConfigVariablesGroup.SERVER_CONFIG,
     description: 'Enable or disable multi-workspace support',