Andreas/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2026-04-03 14:27:20 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
LibreChat/packages/data-schemas/src/methods/tx.ts
Danny Avila fda1bfc3cc
Some checks are pending
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Waiting to run
Details
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Waiting to run
Details
🔬 ci: Add TypeScript Type Checks to Backend Workflow and Fix All Type Errors (#12451) 
* fix(data-schemas): resolve TypeScript strict type check errors in source files

- Constrain ConfigSection to string keys via `string & keyof TCustomConfig`
- Replace broken `z` import from data-provider with TCustomConfig derivation
- Add `_id: Types.ObjectId` to IUser matching other Document interfaces
- Add `federatedTokens` and `openidTokens` optional fields to IUser
- Type mongoose model accessors as `Model<IRole>` and `Model<IUser>`
- Widen `getPremiumRate` param to accept `number | null`
- Widen `bulkWriteAclEntries` ops to untyped `AnyBulkWriteOperation[]`
- Fix `getUserPrincipals` return type to use `PrincipalType` enum
- Add non-null assertions for `connection.db` in migration files
- Import DailyRotateFile constructor directly instead of relying on
  broken module augmentation across mismatched node_modules trees
- Add winston-daily-rotate-file as devDependency for type resolution

* fix(data-schemas): resolve TypeScript type errors in test files

- Replace arbitrary test keys with valid TCustomConfig properties in config.spec
- Use non-null assertions for permission objects in role.methods.spec
- Replace `.SHARED_GLOBAL` access with `.not.toHaveProperty()` for legacy field
- Add non-null assertions for balance, writeRate, readRate in spendTokens.spec
- Update mock user _id to use ObjectId in user.test
- Remove unused Schema import in tenantIndexes.spec

* fix(api): resolve TypeScript strict type check errors across source and test files

- Widen getUserPrincipals dep type in capabilities middleware
- Fix federatedTokens type in createSafeUser return
- Use proper mock req type for read-only properties in preAuthTenant.spec
- Replace `as IUser` casts with ObjectId-typed mocks in openid/oidc specs
- Use TokenExchangeMethodEnum values instead of string literals in MCP specs
- Fix SessionStore type compatibility in sessionCache specs
- Replace `catch (error: any)` with `(error as Error)` in redis specs
- Remove invalid properties from test data in initialize and MCP specs
- Add String.prototype.isWellFormed declaration for sanitizeTitle spec

* fix(client): resolve TypeScript type errors in shared client components

- Add default values for destructured bindings in OGDialogTemplate
- Replace broken ExtendedFile import with inline type in FileIcon

* ci: add TypeScript type-check job to backend review workflow

Add a `typecheck` job that runs `tsc --noEmit` on all four TypeScript
workspaces (data-provider, data-schemas, @librechat/api, @librechat/client)
after the build step. Catches type errors that rollup builds may miss.

* fix(data-schemas): add local type declaration for DailyRotateFile transport

The `winston-daily-rotate-file` package ships a module augmentation for
`winston/lib/winston/transports`, but it fails when winston and
winston-daily-rotate-file resolve from different node_modules trees
(which happens in this monorepo due to npm hoisting).

Add a local `.d.ts` declaration that augments the same module path from
within data-schemas' compilation unit, so `tsc --noEmit` passes while
keeping the original runtime pattern (`new winston.transports.DailyRotateFile`).

* fix: address code review findings from PR #12451

- Restore typed `AnyBulkWriteOperation<AclEntry>[]` on bulkWriteAclEntries,
  cast to untyped only at the tenantSafeBulkWrite call site (Finding 1)
- Type `findUser` model accessor consistently with `findUsers` (Finding 2)
- Replace inline `import('mongoose').ClientSession` with top-level import type
- Use `toHaveLength` for spy assertions in playwright-expect spec file
- Replace numbered Record casts with `.not.toHaveProperty()` in
  role.methods.spec for SHARED_GLOBAL assertions
- Use per-test ObjectIds instead of shared testUserId in openid.spec
- Replace inline `import()` type annotations with top-level SessionData
  import in sessionCache spec
- Remove extraneous blank line in user.ts searchUsers

* refactor: address remaining review findings (4–7)

- Extract OIDCTokens interface in user.ts; deduplicate across IUser fields
  and oidc.ts FederatedTokens (Finding 4)
- Move String.isWellFormed declaration from spec file to project-level
  src/types/es2024-string.d.ts (Finding 5)
- Replace verbose `= undefined` defaults in OGDialogTemplate with null
  coalescing pattern (Finding 6)
- Replace `Record<string, unknown>` TestConfig with named interface
  containing explicit test fields (Finding 7)
2026-03-28 21:06:39 -04:00

497 lines
20 KiB
TypeScript
Raw Blame History

/**
* Token Pricing Configuration
*
* Pattern Matching
* ================
* `findMatchingPattern` uses `modelName.includes(key)` and selects the **longest**
* matching key. If a key's length equals the model name's length (exact match), it
* returns immediately — no further keys are checked.
*
* For keys of different lengths, definition order does not affect the result — the
* longest match always wins. For **same-length ties**, the function iterates in
* reverse, so the last-defined key wins. Key ordering therefore matters for:
* 1. **Performance**: list older/legacy models first, newer models last — newer
* models are more commonly used and will match earlier in the reverse scan.
* 2. **Same-length tie-breaking**: when two keys of equal length both match,
* the last-defined key wins.
*/
export interface TxDeps {
/** From @librechat/api — matches a model name to a canonical key. */
matchModelName: (model: string, endpoint?: string) => string | undefined;
/** From @librechat/api — finds the longest key in `values` whose key is a substring of `model`. */
findMatchingPattern: (
model: string,
values: Record<string, number | Record<string, number>>,
) => string | undefined;
}
export const defaultRate = 6;
/** AWS Bedrock pricing (source: https://aws.amazon.com/bedrock/pricing/) */
const bedrockValues: Record<string, { prompt: number; completion: number }> = {
llama2: { prompt: 0.75, completion: 1.0 },
'llama-2': { prompt: 0.75, completion: 1.0 },
'llama2-13b': { prompt: 0.75, completion: 1.0 },
'llama2:70b': { prompt: 1.95, completion: 2.56 },
'llama2-70b': { prompt: 1.95, completion: 2.56 },
llama3: { prompt: 0.3, completion: 0.6 },
'llama-3': { prompt: 0.3, completion: 0.6 },
'llama3-8b': { prompt: 0.3, completion: 0.6 },
'llama3:8b': { prompt: 0.3, completion: 0.6 },
'llama3-70b': { prompt: 2.65, completion: 3.5 },
'llama3:70b': { prompt: 2.65, completion: 3.5 },
'llama3-1': { prompt: 0.22, completion: 0.22 },
'llama3-1-8b': { prompt: 0.22, completion: 0.22 },
'llama3-1-70b': { prompt: 0.72, completion: 0.72 },
'llama3-1-405b': { prompt: 2.4, completion: 2.4 },
'llama3-2': { prompt: 0.1, completion: 0.1 },
'llama3-2-1b': { prompt: 0.1, completion: 0.1 },
'llama3-2-3b': { prompt: 0.15, completion: 0.15 },
'llama3-2-11b': { prompt: 0.16, completion: 0.16 },
'llama3-2-90b': { prompt: 0.72, completion: 0.72 },
'llama3-3': { prompt: 2.65, completion: 3.5 },
'llama3-3-70b': { prompt: 2.65, completion: 3.5 },
'llama3.1': { prompt: 0.22, completion: 0.22 },
'llama3.1:8b': { prompt: 0.22, completion: 0.22 },
'llama3.1:70b': { prompt: 0.72, completion: 0.72 },
'llama3.1:405b': { prompt: 2.4, completion: 2.4 },
'llama3.2': { prompt: 0.1, completion: 0.1 },
'llama3.2:1b': { prompt: 0.1, completion: 0.1 },
'llama3.2:3b': { prompt: 0.15, completion: 0.15 },
'llama3.2:11b': { prompt: 0.16, completion: 0.16 },
'llama3.2:90b': { prompt: 0.72, completion: 0.72 },
'llama3.3': { prompt: 2.65, completion: 3.5 },
'llama3.3:70b': { prompt: 2.65, completion: 3.5 },
'llama-3.1': { prompt: 0.22, completion: 0.22 },
'llama-3.1-8b': { prompt: 0.22, completion: 0.22 },
'llama-3.1-70b': { prompt: 0.72, completion: 0.72 },
'llama-3.1-405b': { prompt: 2.4, completion: 2.4 },
'llama-3.2': { prompt: 0.1, completion: 0.1 },
'llama-3.2-1b': { prompt: 0.1, completion: 0.1 },
'llama-3.2-3b': { prompt: 0.15, completion: 0.15 },
'llama-3.2-11b': { prompt: 0.16, completion: 0.16 },
'llama-3.2-90b': { prompt: 0.72, completion: 0.72 },
'llama-3.3': { prompt: 2.65, completion: 3.5 },
'llama-3.3-70b': { prompt: 2.65, completion: 3.5 },
'mistral-7b': { prompt: 0.15, completion: 0.2 },
'mistral-small': { prompt: 0.15, completion: 0.2 },
'mixtral-8x7b': { prompt: 0.45, completion: 0.7 },
'mistral-large-2402': { prompt: 4.0, completion: 12.0 },
'mistral-large-2407': { prompt: 3.0, completion: 9.0 },
'command-text': { prompt: 1.5, completion: 2.0 },
'command-light': { prompt: 0.3, completion: 0.6 },
'j2-mid': { prompt: 12.5, completion: 12.5 },
'j2-ultra': { prompt: 18.8, completion: 18.8 },
'jamba-instruct': { prompt: 0.5, completion: 0.7 },
'titan-text-lite': { prompt: 0.15, completion: 0.2 },
'titan-text-express': { prompt: 0.2, completion: 0.6 },
'titan-text-premier': { prompt: 0.5, completion: 1.5 },
'nova-micro': { prompt: 0.035, completion: 0.14 },
'nova-lite': { prompt: 0.06, completion: 0.24 },
'nova-pro': { prompt: 0.8, completion: 3.2 },
'nova-premier': { prompt: 2.5, completion: 12.5 },
'deepseek.r1': { prompt: 1.35, completion: 5.4 },
'moonshot.kimi': { prompt: 0.6, completion: 2.5 },
'moonshot.kimi-k2': { prompt: 0.6, completion: 2.5 },
'moonshot.kimi-k2.5': { prompt: 0.6, completion: 3.0 },
'moonshot.kimi-k2-thinking': { prompt: 0.6, completion: 2.5 },
};
/**
* Mapping of model token sizes to their respective multipliers for prompt and completion.
* The rates are 1 USD per 1M tokens.
*/
export const tokenValues: Record<string, { prompt: number; completion: number }> = Object.assign(
{
'8k': { prompt: 30, completion: 60 },
'32k': { prompt: 60, completion: 120 },
'4k': { prompt: 1.5, completion: 2 },
'16k': { prompt: 3, completion: 4 },
'claude-': { prompt: 0.8, completion: 2.4 },
deepseek: { prompt: 0.28, completion: 0.42 },
command: { prompt: 0.38, completion: 0.38 },
gemma: { prompt: 0.02, completion: 0.04 },
gemini: { prompt: 0.5, completion: 1.5 },
'gpt-oss': { prompt: 0.05, completion: 0.2 },
'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
'gpt-4-1106': { prompt: 10, completion: 30 },
'gpt-4.1': { prompt: 2, completion: 8 },
'gpt-4.1-nano': { prompt: 0.1, completion: 0.4 },
'gpt-4.1-mini': { prompt: 0.4, completion: 1.6 },
'gpt-4.5': { prompt: 75, completion: 150 },
'gpt-4o': { prompt: 2.5, completion: 10 },
'gpt-4o-2024-05-13': { prompt: 5, completion: 15 },
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
'gpt-5': { prompt: 1.25, completion: 10 },
'gpt-5.1': { prompt: 1.25, completion: 10 },
'gpt-5.2': { prompt: 1.75, completion: 14 },
'gpt-5.3': { prompt: 1.75, completion: 14 },
'gpt-5.4': { prompt: 2.5, completion: 15 },
// TODO: gpt-5.4-pro pricing not yet officially published — verify before release
'gpt-5.4-pro': { prompt: 5, completion: 30 },
'gpt-5-nano': { prompt: 0.05, completion: 0.4 },
'gpt-5-mini': { prompt: 0.25, completion: 2 },
'gpt-5-pro': { prompt: 15, completion: 120 },
'gpt-5.2-pro': { prompt: 21, completion: 168 },
o1: { prompt: 15, completion: 60 },
'o1-mini': { prompt: 1.1, completion: 4.4 },
'o1-preview': { prompt: 15, completion: 60 },
o3: { prompt: 2, completion: 8 },
'o3-mini': { prompt: 1.1, completion: 4.4 },
'o4-mini': { prompt: 1.1, completion: 4.4 },
'claude-instant': { prompt: 0.8, completion: 2.4 },
'claude-2': { prompt: 8, completion: 24 },
'claude-2.1': { prompt: 8, completion: 24 },
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
'claude-3-sonnet': { prompt: 3, completion: 15 },
'claude-3-opus': { prompt: 15, completion: 75 },
'claude-3-5-haiku': { prompt: 0.8, completion: 4 },
'claude-3.5-haiku': { prompt: 0.8, completion: 4 },
'claude-3-5-sonnet': { prompt: 3, completion: 15 },
'claude-3.5-sonnet': { prompt: 3, completion: 15 },
'claude-3-7-sonnet': { prompt: 3, completion: 15 },
'claude-3.7-sonnet': { prompt: 3, completion: 15 },
'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 },
'claude-sonnet-4-6': { prompt: 3, completion: 15 },
'command-r': { prompt: 0.5, completion: 1.5 },
'command-r-plus': { prompt: 3, completion: 15 },
'command-text': { prompt: 1.5, completion: 2.0 },
'deepseek-chat': { prompt: 0.28, completion: 0.42 },
'deepseek-reasoner': { prompt: 0.28, completion: 0.42 },
'deepseek-r1': { prompt: 0.4, completion: 2.0 },
'deepseek-v3': { prompt: 0.2, completion: 0.8 },
'gemma-2': { prompt: 0.01, completion: 0.03 },
'gemma-3': { prompt: 0.02, completion: 0.04 },
'gemma-3-27b': { prompt: 0.09, completion: 0.16 },
'gemini-1.5': { prompt: 2.5, completion: 10 },
'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
'gemini-2.0': { prompt: 0.1, completion: 0.4 },
'gemini-2.0-flash': { prompt: 0.1, completion: 0.4 },
'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
'gemini-2.5': { prompt: 0.3, completion: 2.5 },
'gemini-2.5-flash': { prompt: 0.3, completion: 2.5 },
'gemini-2.5-flash-lite': { prompt: 0.1, completion: 0.4 },
'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
'gemini-2.5-flash-image': { prompt: 0.15, completion: 30 },
'gemini-3': { prompt: 2, completion: 12 },
'gemini-3-pro-image': { prompt: 2, completion: 120 },
'gemini-3.1': { prompt: 2, completion: 12 },
'gemini-3.1-flash-lite': { prompt: 0.25, completion: 1.5 },
'gemini-pro-vision': { prompt: 0.5, completion: 1.5 },
grok: { prompt: 2.0, completion: 10.0 },
'grok-beta': { prompt: 5.0, completion: 15.0 },
'grok-vision-beta': { prompt: 5.0, completion: 15.0 },
'grok-2': { prompt: 2.0, completion: 10.0 },
'grok-2-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-latest': { prompt: 2.0, completion: 10.0 },
'grok-2-vision': { prompt: 2.0, completion: 10.0 },
'grok-2-vision-1212': { prompt: 2.0, completion: 10.0 },
'grok-2-vision-latest': { prompt: 2.0, completion: 10.0 },
'grok-3': { prompt: 3.0, completion: 15.0 },
'grok-3-fast': { prompt: 5.0, completion: 25.0 },
'grok-3-mini': { prompt: 0.3, completion: 0.5 },
'grok-3-mini-fast': { prompt: 0.6, completion: 4 },
'grok-4': { prompt: 3.0, completion: 15.0 },
'grok-4-fast': { prompt: 0.2, completion: 0.5 },
'grok-4-1-fast': { prompt: 0.2, completion: 0.5 },
'grok-code-fast': { prompt: 0.2, completion: 1.5 },
codestral: { prompt: 0.3, completion: 0.9 },
'ministral-3b': { prompt: 0.04, completion: 0.04 },
'ministral-8b': { prompt: 0.1, completion: 0.1 },
'mistral-nemo': { prompt: 0.15, completion: 0.15 },
'mistral-saba': { prompt: 0.2, completion: 0.6 },
'pixtral-large': { prompt: 2.0, completion: 6.0 },
'mistral-large': { prompt: 2.0, completion: 6.0 },
'mixtral-8x22b': { prompt: 0.65, completion: 0.65 },
kimi: { prompt: 0.6, completion: 2.5 },
moonshot: { prompt: 2.0, completion: 5.0 },
'kimi-latest': { prompt: 0.2, completion: 2.0 },
'kimi-k2': { prompt: 0.6, completion: 2.5 },
'kimi-k2.5': { prompt: 0.6, completion: 3.0 },
'kimi-k2-turbo': { prompt: 1.15, completion: 8.0 },
'kimi-k2-turbo-preview': { prompt: 1.15, completion: 8.0 },
'kimi-k2-0905': { prompt: 0.6, completion: 2.5 },
'kimi-k2-0905-preview': { prompt: 0.6, completion: 2.5 },
'kimi-k2-0711': { prompt: 0.6, completion: 2.5 },
'kimi-k2-0711-preview': { prompt: 0.6, completion: 2.5 },
'kimi-k2-thinking': { prompt: 0.6, completion: 2.5 },
'kimi-k2-thinking-turbo': { prompt: 1.15, completion: 8.0 },
'moonshot-v1': { prompt: 2.0, completion: 5.0 },
'moonshot-v1-auto': { prompt: 2.0, completion: 5.0 },
'moonshot-v1-8k': { prompt: 0.2, completion: 2.0 },
'moonshot-v1-8k-vision': { prompt: 0.2, completion: 2.0 },
'moonshot-v1-8k-vision-preview': { prompt: 0.2, completion: 2.0 },
'moonshot-v1-32k': { prompt: 1.0, completion: 3.0 },
'moonshot-v1-32k-vision': { prompt: 1.0, completion: 3.0 },
'moonshot-v1-32k-vision-preview': { prompt: 1.0, completion: 3.0 },
'moonshot-v1-128k': { prompt: 2.0, completion: 5.0 },
'moonshot-v1-128k-vision': { prompt: 2.0, completion: 5.0 },
'moonshot-v1-128k-vision-preview': { prompt: 2.0, completion: 5.0 },
'gpt-oss:20b': { prompt: 0.05, completion: 0.2 },
'gpt-oss-20b': { prompt: 0.05, completion: 0.2 },
'gpt-oss:120b': { prompt: 0.15, completion: 0.6 },
'gpt-oss-120b': { prompt: 0.15, completion: 0.6 },
glm4: { prompt: 0.1, completion: 0.1 },
'glm-4': { prompt: 0.1, completion: 0.1 },
'glm-4-32b': { prompt: 0.1, completion: 0.1 },
'glm-4.5': { prompt: 0.35, completion: 1.55 },
'glm-4.5-air': { prompt: 0.14, completion: 0.86 },
'glm-4.5v': { prompt: 0.6, completion: 1.8 },
'glm-4.6': { prompt: 0.5, completion: 1.75 },
qwen: { prompt: 0.08, completion: 0.33 },
'qwen2.5': { prompt: 0.08, completion: 0.33 },
'qwen-turbo': { prompt: 0.05, completion: 0.2 },
'qwen-plus': { prompt: 0.4, completion: 1.2 },
'qwen-max': { prompt: 1.6, completion: 6.4 },
'qwq-32b': { prompt: 0.15, completion: 0.4 },
qwen3: { prompt: 0.035, completion: 0.138 },
'qwen3-8b': { prompt: 0.035, completion: 0.138 },
'qwen3-14b': { prompt: 0.05, completion: 0.22 },
'qwen3-30b-a3b': { prompt: 0.06, completion: 0.22 },
'qwen3-32b': { prompt: 0.05, completion: 0.2 },
'qwen3-235b-a22b': { prompt: 0.08, completion: 0.55 },
'qwen3-vl-8b-thinking': { prompt: 0.18, completion: 2.1 },
'qwen3-vl-8b-instruct': { prompt: 0.18, completion: 0.69 },
'qwen3-vl-30b-a3b': { prompt: 0.29, completion: 1.0 },
'qwen3-vl-235b-a22b': { prompt: 0.3, completion: 1.2 },
'qwen3-max': { prompt: 1.2, completion: 6 },
'qwen3-coder': { prompt: 0.22, completion: 0.95 },
'qwen3-coder-30b-a3b': { prompt: 0.06, completion: 0.25 },
'qwen3-coder-plus': { prompt: 1, completion: 5 },
'qwen3-coder-flash': { prompt: 0.3, completion: 1.5 },
'qwen3-next-80b-a3b': { prompt: 0.1, completion: 0.8 },
},
bedrockValues,
);
/**
* Mapping of model token sizes to their respective multipliers for cached input, read and write.
* The rates are 1 USD per 1M tokens.
*/
export const cacheTokenValues: Record<string, { write: number; read: number }> = {
'claude-3.7-sonnet': { write: 3.75, read: 0.3 },
'claude-3-7-sonnet': { write: 3.75, read: 0.3 },
'claude-3.5-sonnet': { write: 3.75, read: 0.3 },
'claude-3-5-sonnet': { write: 3.75, read: 0.3 },
'claude-3.5-haiku': { write: 1, read: 0.08 },
'claude-3-5-haiku': { write: 1, read: 0.08 },
'claude-3-haiku': { write: 0.3, read: 0.03 },
'claude-haiku-4-5': { write: 1.25, read: 0.1 },
'claude-sonnet-4': { write: 3.75, read: 0.3 },
'claude-sonnet-4-6': { 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 },
'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 },
'gpt-4.1-mini': { write: 0.4, read: 0.1 },
'gpt-4.1-nano': { write: 0.1, read: 0.025 },
'gpt-5': { write: 1.25, read: 0.125 },
'gpt-5.1': { write: 1.25, read: 0.125 },
'gpt-5.2': { write: 1.75, read: 0.175 },
'gpt-5.3': { write: 1.75, read: 0.175 },
'gpt-5.4': { write: 2.5, read: 0.25 },
'gpt-5-mini': { write: 0.25, read: 0.025 },
'gpt-5-nano': { write: 0.05, read: 0.005 },
o1: { write: 15, read: 7.5 },
'o1-mini': { write: 1.1, read: 0.55 },
'o1-preview': { write: 15, read: 7.5 },
o3: { write: 2, read: 0.5 },
'o3-mini': { write: 1.1, read: 0.275 },
'o4-mini': { write: 1.1, read: 0.275 },
deepseek: { write: 0.28, read: 0.028 },
'deepseek-chat': { write: 0.28, read: 0.028 },
'deepseek-reasoner': { write: 0.28, read: 0.028 },
kimi: { write: 0.6, read: 0.15 },
'kimi-k2': { write: 0.6, read: 0.15 },
'kimi-k2.5': { write: 0.6, read: 0.1 },
'kimi-k2-turbo': { write: 1.15, read: 0.15 },
'kimi-k2-turbo-preview': { write: 1.15, read: 0.15 },
'kimi-k2-0905': { write: 0.6, read: 0.15 },
'kimi-k2-0905-preview': { write: 0.6, read: 0.15 },
'kimi-k2-0711': { write: 0.6, read: 0.15 },
'kimi-k2-0711-preview': { write: 0.6, read: 0.15 },
'kimi-k2-thinking': { write: 0.6, read: 0.15 },
'kimi-k2-thinking-turbo': { write: 1.15, read: 0.15 },
// Gemini 3.1 Pro - cache write: $2.00/1M, cache read: $0.20/1M
'gemini-3.1': { write: 2, read: 0.2 },
// Gemini 3.1 Flash-Lite - cache write: $0.25/1M, cache read: $0.025/1M
'gemini-3.1-flash-lite': { write: 0.25, read: 0.025 },
};
/**
* Premium (tiered) pricing for models whose rates change based on prompt size.
*/
export const premiumTokenValues: Record<
string,
{ threshold: number; prompt: number; completion: number }
> = {
'claude-opus-4-6': { threshold: 200000, prompt: 10, completion: 37.5 },
'claude-sonnet-4-6': { threshold: 200000, prompt: 6, completion: 22.5 },
'gemini-3.1': { threshold: 200000, prompt: 4, completion: 18 },
};
export function createTxMethods(_mongoose: typeof import('mongoose'), txDeps: TxDeps) {
const { matchModelName, findMatchingPattern } = txDeps;
/**
* Retrieves the key associated with a given model name.
*/
function getValueKey(model: string, endpoint?: string): string | undefined {
if (!model || typeof model !== 'string') {
return undefined;
}
if (!endpoint || (typeof endpoint === 'string' && !tokenValues[endpoint])) {
const matchedKey = findMatchingPattern(model, tokenValues);
if (matchedKey) {
return matchedKey;
}
}
const modelName = matchModelName(model, endpoint);
if (!modelName) {
return undefined;
}
if (modelName.includes('gpt-3.5-turbo-16k')) {
return '16k';
} else if (modelName.includes('gpt-3.5')) {
return '4k';
} else if (modelName.includes('gpt-4-vision')) {
return 'gpt-4-1106';
} else if (modelName.includes('gpt-4-0125')) {
return 'gpt-4-1106';
} else if (modelName.includes('gpt-4-turbo')) {
return 'gpt-4-1106';
} else if (modelName.includes('gpt-4-32k')) {
return '32k';
} else if (modelName.includes('gpt-4')) {
return '8k';
}
return undefined;
}
/**
* Checks if premium (tiered) pricing applies and returns the premium rate.
*/
function getPremiumRate(
valueKey: string,
tokenType: string,
inputTokenCount?: number | null,
): number | null {
if (inputTokenCount == null) {
return null;
}
const premiumEntry = premiumTokenValues[valueKey];
if (!premiumEntry || inputTokenCount <= premiumEntry.threshold) {
return null;
}
return premiumEntry[tokenType as 'prompt' | 'completion'] ?? null;
}
/**
* Retrieves the multiplier for a given value key and token type.
*/
function getMultiplier({
model,
valueKey,
endpoint,
tokenType,
inputTokenCount,
endpointTokenConfig,
}: {
model?: string;
valueKey?: string;
endpoint?: string;
tokenType?: 'prompt' | 'completion';
inputTokenCount?: number;
endpointTokenConfig?: Record<string, Record<string, number>>;
}): number {
if (endpointTokenConfig && model) {
return endpointTokenConfig?.[model]?.[tokenType as string] ?? defaultRate;
}
if (valueKey && tokenType) {
const premiumRate = getPremiumRate(valueKey, tokenType, inputTokenCount);
if (premiumRate != null) {
return premiumRate;
}
return tokenValues[valueKey]?.[tokenType] ?? defaultRate;
}
if (!tokenType || !model) {
return 1;
}
valueKey = getValueKey(model, endpoint);
if (!valueKey) {
return defaultRate;
}
const premiumRate = getPremiumRate(valueKey, tokenType, inputTokenCount);
if (premiumRate != null) {
return premiumRate;
}
return tokenValues[valueKey]?.[tokenType] ?? defaultRate;
}
/**
* Retrieves the cache multiplier for a given value key and token type.
*/
function getCacheMultiplier({
valueKey,
cacheType,
model,
endpoint,
endpointTokenConfig,
}: {
valueKey?: string;
cacheType?: 'write' | 'read';
model?: string;
endpoint?: string;
endpointTokenConfig?: Record<string, Record<string, number>>;
}): number | null {
if (endpointTokenConfig && model) {
return endpointTokenConfig?.[model]?.[cacheType as string] ?? null;
}
if (valueKey && cacheType) {
return cacheTokenValues[valueKey]?.[cacheType] ?? null;
}
if (!cacheType || !model) {
return null;
}
valueKey = getValueKey(model, endpoint);
if (!valueKey) {
return null;
}
return cacheTokenValues[valueKey]?.[cacheType] ?? null;
}
return {
tokenValues,
premiumTokenValues,
getValueKey,
getMultiplier,
getPremiumRate,
getCacheMultiplier,
defaultRate,
cacheTokenValues,
};
}
export type TxMethods = ReturnType<typeof createTxMethods>;
Reference in a new issue View git blame Copy permalink