mirror of
https://github.com/danny-avila/LibreChat.git
synced 2026-01-23 18:56:12 +01:00
🧮 feat: Enhance Model Pricing Coverage and Pattern Matching (#10173)
Some checks failed
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Has been cancelled
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Has been cancelled
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Has been cancelled
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Has been cancelled
Some checks failed
Docker Dev Branch Images Build / build (Dockerfile, lc-dev, node) (push) Has been cancelled
Docker Dev Branch Images Build / build (Dockerfile.multi, lc-dev-api, api-build) (push) Has been cancelled
Docker Dev Images Build / build (Dockerfile, librechat-dev, node) (push) Has been cancelled
Docker Dev Images Build / build (Dockerfile.multi, librechat-dev-api, api-build) (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Sync Translation Keys with Locize (push) Has been cancelled
Sync Locize Translations & Create Translation PR / Create Translation PR on Version Published (push) Has been cancelled
* updated gpt5-pro it is here and on openrouter https://platform.openai.com/docs/models/gpt-5-pro * feat: Add gpt-5-pro pricing - Implemented handling for the new gpt-5-pro model in the getValueKey function. - Updated tests to ensure correct behavior for gpt-5-pro across various scenarios. - Adjusted token limits and multipliers for gpt-5-pro in the tokens utility files. - Enhanced model matching functionality to include gpt-5-pro variations. * refactor: optimize model pricing and validation logic - Added new model pricing entries for llama2, llama3, and qwen variants in tx.js. - Updated tokenValues to include additional models and their pricing structures. - Implemented validation tests in tx.spec.js to ensure all models resolve correctly to pricing. - Refactored getValueKey function to improve model matching and resolution efficiency. - Removed outdated model entries from tokens.ts to streamline pricing management. * fix: add missing pricing * chore: update model pricing for qwen and gemma variants * chore: update model pricing and add validation for context windows - Removed outdated model entries from tx.js and updated tokenValues with new models. - Added a test in tx.spec.js to ensure all models with pricing have corresponding context windows defined in tokens.ts. - Introduced 'command-text' model pricing in tokens.ts to maintain consistency across model definitions. * chore: update model names and pricing for AI21 and Amazon models - Refactored model names in tx.js for AI21 and Amazon models to remove versioning and improve consistency. - Updated pricing values in tokens.ts to reflect the new model names. - Added comprehensive tests in tx.spec.js to validate pricing for both short and full model names across AI21 and Amazon models. * feat: add pricing and validation for Claude Haiku 4.5 model * chore: increase default max context tokens to 18000 for agents * feat: add Qwen3 model pricing and validation tests * chore: reorganize and update Qwen model pricing in tx.js and tokens.ts --------- Co-authored-by: khfung <68192841+khfung@users.noreply.github.com>
This commit is contained in:
Danny Avila
GitHub
parent
589f119310
commit
36f0365fd4
5 changed files with 964 additions and 132 deletions
258
api/models/tx.js
258
api/models/tx.js
|
|
@ -1,4 +1,4 @@
|
|||
const { matchModelName } = require('@librechat/api');
|
||||
const { matchModelName, findMatchingPattern } = require('@librechat/api');
|
||||
const defaultRate = 6;
|
||||
|
||||
/**
|
||||
|
|
@ -6,44 +6,58 @@ const defaultRate = 6;
|
|||
* source: https://aws.amazon.com/bedrock/pricing/
|
||||
* */
|
||||
const bedrockValues = {
|
||||
// Basic llama2 patterns
|
||||
// Basic llama2 patterns (base defaults to smallest variant)
|
||||
llama2: { prompt: 0.75, completion: 1.0 },
|
||||
'llama-2': { prompt: 0.75, completion: 1.0 },
|
||||
'llama2-13b': { 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 },
|
||||
|
||||
// Basic llama3 patterns
|
||||
// Basic llama3 patterns (base defaults to smallest variant)
|
||||
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-x-Nb pattern
|
||||
// llama3-x-Nb pattern (base defaults to smallest variant)
|
||||
'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.x:Nb pattern
|
||||
// llama3.x:Nb pattern (base defaults to smallest variant)
|
||||
'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.x-Nb pattern
|
||||
// llama-3.x-Nb pattern (base defaults to smallest variant)
|
||||
'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 },
|
||||
|
|
@ -52,15 +66,19 @@ const bedrockValues = {
|
|||
'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 },
|
||||
'ai21.j2-mid-v1': { prompt: 12.5, completion: 12.5 },
|
||||
'ai21.j2-ultra-v1': { prompt: 18.8, completion: 18.8 },
|
||||
'ai21.jamba-instruct-v1:0': { prompt: 0.5, completion: 0.7 },
|
||||
'amazon.titan-text-lite-v1': { prompt: 0.15, completion: 0.2 },
|
||||
'amazon.titan-text-express-v1': { prompt: 0.2, completion: 0.6 },
|
||||
'amazon.titan-text-premier-v1:0': { prompt: 0.5, completion: 1.5 },
|
||||
'amazon.nova-micro-v1:0': { prompt: 0.035, completion: 0.14 },
|
||||
'amazon.nova-lite-v1:0': { prompt: 0.06, completion: 0.24 },
|
||||
'amazon.nova-pro-v1:0': { prompt: 0.8, completion: 3.2 },
|
||||
// AI21 models
|
||||
'j2-mid': { prompt: 12.5, completion: 12.5 },
|
||||
'j2-ultra': { prompt: 18.8, completion: 18.8 },
|
||||
'jamba-instruct': { prompt: 0.5, completion: 0.7 },
|
||||
// Amazon Titan models
|
||||
'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 },
|
||||
// Amazon Nova models
|
||||
'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 },
|
||||
};
|
||||
|
||||
|
|
@ -71,100 +89,136 @@ const bedrockValues = {
|
|||
*/
|
||||
const tokenValues = Object.assign(
|
||||
{
|
||||
// Legacy token size mappings (generic patterns - check LAST)
|
||||
'8k': { prompt: 30, completion: 60 },
|
||||
'32k': { prompt: 60, completion: 120 },
|
||||
'4k': { prompt: 1.5, completion: 2 },
|
||||
'16k': { prompt: 3, completion: 4 },
|
||||
// Generic fallback patterns (check LAST)
|
||||
'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 }, // Base pattern (using gemma-3n-e4b pricing)
|
||||
gemini: { prompt: 0.5, completion: 1.5 },
|
||||
'gpt-oss': { prompt: 0.05, completion: 0.2 },
|
||||
// Specific model variants (check FIRST - more specific patterns at end)
|
||||
'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
|
||||
'o4-mini': { prompt: 1.1, completion: 4.4 },
|
||||
'o3-mini': { prompt: 1.1, completion: 4.4 },
|
||||
o3: { prompt: 2, completion: 8 },
|
||||
'o1-mini': { prompt: 1.1, completion: 4.4 },
|
||||
'o1-preview': { prompt: 15, completion: 60 },
|
||||
o1: { prompt: 15, completion: 60 },
|
||||
'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-4.1': { prompt: 2, completion: 8 },
|
||||
'gpt-4.5': { prompt: 75, completion: 150 },
|
||||
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
|
||||
'gpt-5': { prompt: 1.25, completion: 10 },
|
||||
'gpt-5-mini': { prompt: 0.25, completion: 2 },
|
||||
'gpt-5-nano': { prompt: 0.05, completion: 0.4 },
|
||||
'gpt-4o': { prompt: 2.5, completion: 10 },
|
||||
'gpt-4o-2024-05-13': { prompt: 5, completion: 15 },
|
||||
'gpt-4-1106': { prompt: 10, completion: 30 },
|
||||
'gpt-3.5-turbo-0125': { prompt: 0.5, completion: 1.5 },
|
||||
'claude-3-opus': { prompt: 15, completion: 75 },
|
||||
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
|
||||
'gpt-5': { prompt: 1.25, completion: 10 },
|
||||
'gpt-5-nano': { prompt: 0.05, completion: 0.4 },
|
||||
'gpt-5-mini': { prompt: 0.25, completion: 2 },
|
||||
'gpt-5-pro': { prompt: 15, completion: 120 },
|
||||
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-3-5-haiku': { prompt: 0.8, completion: 4 },
|
||||
'claude-3.5-haiku': { prompt: 0.8, completion: 4 },
|
||||
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
|
||||
'claude-sonnet-4': { prompt: 3, completion: 15 },
|
||||
'claude-haiku-4-5': { prompt: 1, completion: 5 },
|
||||
'claude-opus-4': { prompt: 15, completion: 75 },
|
||||
'claude-2.1': { prompt: 8, completion: 24 },
|
||||
'claude-2': { prompt: 8, completion: 24 },
|
||||
'claude-instant': { prompt: 0.8, completion: 2.4 },
|
||||
'claude-': { prompt: 0.8, completion: 2.4 },
|
||||
'command-r-plus': { prompt: 3, completion: 15 },
|
||||
'claude-sonnet-4': { 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-reasoner': { prompt: 0.28, completion: 0.42 },
|
||||
deepseek: { prompt: 0.28, completion: 0.42 },
|
||||
/* cohere doesn't have rates for the older command models,
|
||||
so this was from https://artificialanalysis.ai/models/command-light/providers */
|
||||
command: { prompt: 0.38, completion: 0.38 },
|
||||
gemma: { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
|
||||
'gemma-2': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
|
||||
'gemma-3': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
|
||||
'gemma-3-27b': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
|
||||
'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
|
||||
'deepseek-r1': { prompt: 0.4, completion: 2.0 },
|
||||
'deepseek-v3': { prompt: 0.2, completion: 0.8 },
|
||||
'gemma-2': { prompt: 0.01, completion: 0.03 }, // Base pattern (using gemma-2-9b pricing)
|
||||
'gemma-3': { prompt: 0.02, completion: 0.04 }, // Base pattern (using gemma-3n-e4b pricing)
|
||||
'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 }, // Base pattern (using 2.0-flash pricing)
|
||||
'gemini-2.0-flash': { prompt: 0.1, completion: 0.4 },
|
||||
'gemini-2.0': { prompt: 0, completion: 0 }, // https://ai.google.dev/pricing
|
||||
'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
|
||||
'gemini-2.0-flash-lite': { prompt: 0.075, completion: 0.3 },
|
||||
'gemini-2.5': { prompt: 0.3, completion: 2.5 }, // Base pattern (using 2.5-flash pricing)
|
||||
'gemini-2.5-flash': { prompt: 0.3, completion: 2.5 },
|
||||
'gemini-2.5-flash-lite': { prompt: 0.1, completion: 0.4 },
|
||||
'gemini-2.5': { prompt: 0, completion: 0 }, // Free for a period of time
|
||||
'gemini-1.5-flash-8b': { prompt: 0.075, completion: 0.3 },
|
||||
'gemini-1.5-flash': { prompt: 0.15, completion: 0.6 },
|
||||
'gemini-1.5': { prompt: 2.5, completion: 10 },
|
||||
'gemini-2.5-pro': { prompt: 1.25, completion: 10 },
|
||||
'gemini-pro-vision': { prompt: 0.5, completion: 1.5 },
|
||||
gemini: { prompt: 0.5, completion: 1.5 },
|
||||
'grok-2-vision-1212': { prompt: 2.0, completion: 10.0 },
|
||||
'grok-2-vision-latest': { prompt: 2.0, completion: 10.0 },
|
||||
'grok-2-vision': { prompt: 2.0, completion: 10.0 },
|
||||
grok: { prompt: 2.0, completion: 10.0 }, // Base pattern defaults to grok-2
|
||||
'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': { prompt: 2.0, completion: 10.0 },
|
||||
'grok-3-mini-fast': { prompt: 0.6, completion: 4 },
|
||||
'grok-3-mini': { prompt: 0.3, completion: 0.5 },
|
||||
'grok-3-fast': { prompt: 5.0, completion: 25.0 },
|
||||
'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-beta': { prompt: 5.0, completion: 15.0 },
|
||||
'mistral-large': { prompt: 2.0, completion: 6.0 },
|
||||
'pixtral-large': { prompt: 2.0, completion: 6.0 },
|
||||
'mistral-saba': { prompt: 0.2, completion: 0.6 },
|
||||
codestral: { prompt: 0.3, completion: 0.9 },
|
||||
'ministral-8b': { prompt: 0.1, completion: 0.1 },
|
||||
'ministral-3b': { prompt: 0.04, completion: 0.04 },
|
||||
// GPT-OSS models
|
||||
'gpt-oss': { prompt: 0.05, completion: 0.2 },
|
||||
'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: 0.14, completion: 2.49 }, // Base pattern (using kimi-k2 pricing)
|
||||
// GPT-OSS models (specific sizes)
|
||||
'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 },
|
||||
// GLM models (Zhipu AI)
|
||||
// GLM models (Zhipu AI) - general to specific
|
||||
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-4.5v': { prompt: 0.6, completion: 1.8 },
|
||||
'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 models
|
||||
qwen: { prompt: 0.08, completion: 0.33 }, // Qwen base pattern (using qwen2.5-72b pricing)
|
||||
'qwen2.5': { prompt: 0.08, completion: 0.33 }, // Qwen 2.5 base pattern
|
||||
'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 models
|
||||
qwen3: { prompt: 0.035, completion: 0.138 }, // Qwen3 base pattern (using qwen3-4b pricing)
|
||||
'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 (Vision-Language) models
|
||||
'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 specialized models
|
||||
'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,
|
||||
);
|
||||
|
|
@ -195,67 +249,39 @@ const cacheTokenValues = {
|
|||
* @returns {string|undefined} The key corresponding to the model name, or undefined if no match is found.
|
||||
*/
|
||||
const getValueKey = (model, endpoint) => {
|
||||
if (!model || typeof model !== 'string') {
|
||||
return undefined;
|
||||
}
|
||||
|
||||
// Use findMatchingPattern directly against tokenValues for efficient lookup
|
||||
if (!endpoint || (typeof endpoint === 'string' && !tokenValues[endpoint])) {
|
||||
const matchedKey = findMatchingPattern(model, tokenValues);
|
||||
if (matchedKey) {
|
||||
return matchedKey;
|
||||
}
|
||||
}
|
||||
|
||||
// Fallback: use matchModelName for edge cases and legacy handling
|
||||
const modelName = matchModelName(model, endpoint);
|
||||
if (!modelName) {
|
||||
return undefined;
|
||||
}
|
||||
|
||||
// Legacy token size mappings and aliases for older models
|
||||
if (modelName.includes('gpt-3.5-turbo-16k')) {
|
||||
return '16k';
|
||||
} else if (modelName.includes('gpt-3.5-turbo-0125')) {
|
||||
return 'gpt-3.5-turbo-0125';
|
||||
} else if (modelName.includes('gpt-3.5-turbo-1106')) {
|
||||
return 'gpt-3.5-turbo-1106';
|
||||
} else if (modelName.includes('gpt-3.5')) {
|
||||
return '4k';
|
||||
} else if (modelName.includes('o4-mini')) {
|
||||
return 'o4-mini';
|
||||
} else if (modelName.includes('o4')) {
|
||||
return 'o4';
|
||||
} else if (modelName.includes('o3-mini')) {
|
||||
return 'o3-mini';
|
||||
} else if (modelName.includes('o3')) {
|
||||
return 'o3';
|
||||
} else if (modelName.includes('o1-preview')) {
|
||||
return 'o1-preview';
|
||||
} else if (modelName.includes('o1-mini')) {
|
||||
return 'o1-mini';
|
||||
} else if (modelName.includes('o1')) {
|
||||
return 'o1';
|
||||
} else if (modelName.includes('gpt-4.5')) {
|
||||
return 'gpt-4.5';
|
||||
} else if (modelName.includes('gpt-4.1-nano')) {
|
||||
return 'gpt-4.1-nano';
|
||||
} else if (modelName.includes('gpt-4.1-mini')) {
|
||||
return 'gpt-4.1-mini';
|
||||
} else if (modelName.includes('gpt-4.1')) {
|
||||
return 'gpt-4.1';
|
||||
} else if (modelName.includes('gpt-4o-2024-05-13')) {
|
||||
return 'gpt-4o-2024-05-13';
|
||||
} else if (modelName.includes('gpt-5-nano')) {
|
||||
return 'gpt-5-nano';
|
||||
} else if (modelName.includes('gpt-5-mini')) {
|
||||
return 'gpt-5-mini';
|
||||
} else if (modelName.includes('gpt-5')) {
|
||||
return 'gpt-5';
|
||||
} else if (modelName.includes('gpt-4o-mini')) {
|
||||
return 'gpt-4o-mini';
|
||||
} else if (modelName.includes('gpt-4o')) {
|
||||
return 'gpt-4o';
|
||||
} else if (modelName.includes('gpt-4-vision')) {
|
||||
return 'gpt-4-1106';
|
||||
} else if (modelName.includes('gpt-4-1106')) {
|
||||
return 'gpt-4-1106';
|
||||
return 'gpt-4-1106'; // Alias for gpt-4-vision
|
||||
} else if (modelName.includes('gpt-4-0125')) {
|
||||
return 'gpt-4-1106';
|
||||
return 'gpt-4-1106'; // Alias for gpt-4-0125
|
||||
} else if (modelName.includes('gpt-4-turbo')) {
|
||||
return 'gpt-4-1106';
|
||||
return 'gpt-4-1106'; // Alias for gpt-4-turbo
|
||||
} else if (modelName.includes('gpt-4-32k')) {
|
||||
return '32k';
|
||||
} else if (modelName.includes('gpt-4')) {
|
||||
return '8k';
|
||||
} else if (tokenValues[modelName]) {
|
||||
return modelName;
|
||||
}
|
||||
|
||||
return undefined;
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue