mirror of
https://github.com/danny-avila/LibreChat.git
synced 2025-12-17 00:40:14 +01:00
🪙 feat: Update Token Values for gpt-4o-2024-08-06 and AWS Models (#3594)
* feat: gpt-4o-2024-08-06 pricing for tx * feat: add AWS models to tokenValues in tx.js for pricing transactions * feat: Update tokenValues in tx.js for AWS models pricing * refactor: add bedrock prefix values as well (temporary until we update value keys which includes context)
This commit is contained in:
Danny Avila
GitHub
parent
016ed866a3
commit
e05a6d306d
4 changed files with 139 additions and 26 deletions
|
|
@ -1,38 +1,74 @@
|
|||
const { matchModelName } = require('../utils');
|
||||
const defaultRate = 6;
|
||||
|
||||
/** AWS Bedrock pricing */
|
||||
const bedrockValues = {
|
||||
'anthropic.claude-3-haiku-20240307-v1:0': { prompt: 0.25, completion: 1.25 },
|
||||
'anthropic.claude-3-sonnet-20240229-v1:0': { prompt: 3.0, completion: 15.0 },
|
||||
'anthropic.claude-3-opus-20240229-v1:0': { prompt: 15.0, completion: 75.0 },
|
||||
'anthropic.claude-3-5-sonnet-20240620-v1:0': { prompt: 3.0, completion: 15.0 },
|
||||
'anthropic.claude-v2:1': { prompt: 8.0, completion: 24.0 },
|
||||
'anthropic.claude-instant-v1': { prompt: 0.8, completion: 2.4 },
|
||||
'meta.llama2-13b-chat-v1': { prompt: 0.75, completion: 1.0 },
|
||||
'meta.llama2-70b-chat-v1': { prompt: 1.95, completion: 2.56 },
|
||||
'meta.llama3-8b-instruct-v1:0': { prompt: 0.3, completion: 0.6 },
|
||||
'meta.llama3-70b-instruct-v1:0': { prompt: 2.65, completion: 3.5 },
|
||||
'meta.llama3-1-8b-instruct-v1:0': { prompt: 0.3, completion: 0.6 },
|
||||
'meta.llama3-1-70b-instruct-v1:0': { prompt: 2.65, completion: 3.5 },
|
||||
'meta.llama3-1-405b-instruct-v1:0': { prompt: 5.32, completion: 16.0 },
|
||||
'mistral.mistral-7b-instruct-v0:2': { prompt: 0.15, completion: 0.2 },
|
||||
'mistral.mistral-small-2402-v1:0': { prompt: 0.15, completion: 0.2 },
|
||||
'mistral.mixtral-8x7b-instruct-v0:1': { prompt: 0.45, completion: 0.7 },
|
||||
'mistral.mistral-large-2402-v1:0': { prompt: 4.0, completion: 12.0 },
|
||||
'mistral.mistral-large-2407-v1:0': { prompt: 3.0, completion: 9.0 },
|
||||
'cohere.command-text-v14': { prompt: 1.5, completion: 2.0 },
|
||||
'cohere.command-light-text-v14': { prompt: 0.3, completion: 0.6 },
|
||||
'cohere.command-r-v1:0': { prompt: 0.5, completion: 1.5 },
|
||||
'cohere.command-r-plus-v1:0': { prompt: 3.0, completion: 15.0 },
|
||||
'ai21.j2-mid-v1': { prompt: 12.5, completion: 12.5 },
|
||||
'ai21.j2-ultra-v1': { prompt: 18.8, completion: 18.8 },
|
||||
'amazon.titan-text-lite-v1': { prompt: 0.15, completion: 0.2 },
|
||||
'amazon.titan-text-express-v1': { prompt: 0.2, completion: 0.6 },
|
||||
};
|
||||
|
||||
for (const [key, value] of Object.entries(bedrockValues)) {
|
||||
bedrockValues[`bedrock/${key}`] = value;
|
||||
}
|
||||
|
||||
/**
|
||||
* Mapping of model token sizes to their respective multipliers for prompt and completion.
|
||||
* The rates are 1 USD per 1M tokens.
|
||||
* @type {Object.<string, {prompt: number, completion: number}>}
|
||||
*/
|
||||
const tokenValues = {
|
||||
'8k': { prompt: 30, completion: 60 },
|
||||
'32k': { prompt: 60, completion: 120 },
|
||||
'4k': { prompt: 1.5, completion: 2 },
|
||||
'16k': { prompt: 3, completion: 4 },
|
||||
'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
|
||||
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
|
||||
'gpt-4o': { 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 },
|
||||
'claude-3-sonnet': { prompt: 3, completion: 15 },
|
||||
'claude-3-5-sonnet': { prompt: 3, completion: 15 },
|
||||
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
|
||||
'claude-2.1': { prompt: 8, completion: 24 },
|
||||
'claude-2': { prompt: 8, completion: 24 },
|
||||
'claude-': { prompt: 0.8, completion: 2.4 },
|
||||
'command-r-plus': { prompt: 3, completion: 15 },
|
||||
'command-r': { prompt: 0.5, completion: 1.5 },
|
||||
/* cohere doesn't have rates for the older command models,
|
||||
const tokenValues = Object.assign(
|
||||
{
|
||||
'8k': { prompt: 30, completion: 60 },
|
||||
'32k': { prompt: 60, completion: 120 },
|
||||
'4k': { prompt: 1.5, completion: 2 },
|
||||
'16k': { prompt: 3, completion: 4 },
|
||||
'gpt-3.5-turbo-1106': { prompt: 1, completion: 2 },
|
||||
'gpt-4o-2024-08-06': { prompt: 2.5, completion: 10 },
|
||||
'gpt-4o-mini': { prompt: 0.15, completion: 0.6 },
|
||||
'gpt-4o': { 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 },
|
||||
'claude-3-sonnet': { prompt: 3, completion: 15 },
|
||||
'claude-3-5-sonnet': { prompt: 3, completion: 15 },
|
||||
'claude-3-haiku': { prompt: 0.25, completion: 1.25 },
|
||||
'claude-2.1': { prompt: 8, completion: 24 },
|
||||
'claude-2': { prompt: 8, completion: 24 },
|
||||
'claude-': { prompt: 0.8, completion: 2.4 },
|
||||
'command-r-plus': { prompt: 3, completion: 15 },
|
||||
'command-r': { prompt: 0.5, completion: 1.5 },
|
||||
/* 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 },
|
||||
// 'gemini-1.5': { prompt: 7, completion: 21 }, // May 2nd, 2024 pricing
|
||||
// 'gemini': { prompt: 0.5, completion: 1.5 }, // May 2nd, 2024 pricing
|
||||
'gemini-1.5': { prompt: 0, completion: 0 }, // currently free
|
||||
gemini: { prompt: 0, completion: 0 }, // currently free
|
||||
};
|
||||
command: { prompt: 0.38, completion: 0.38 },
|
||||
'gemini-1.5': { prompt: 7, completion: 21 }, // May 2nd, 2024 pricing
|
||||
gemini: { prompt: 0.5, completion: 1.5 }, // May 2nd, 2024 pricing
|
||||
},
|
||||
bedrockValues,
|
||||
);
|
||||
|
||||
/**
|
||||
* Retrieves the key associated with a given model name.
|
||||
|
|
@ -55,6 +91,8 @@ const getValueKey = (model, endpoint) => {
|
|||
return 'gpt-3.5-turbo-1106';
|
||||
} else if (modelName.includes('gpt-3.5')) {
|
||||
return '4k';
|
||||
} else if (modelName.includes('gpt-4o-2024-08-06')) {
|
||||
return 'gpt-4o-2024-08-06';
|
||||
} else if (modelName.includes('gpt-4o-mini')) {
|
||||
return 'gpt-4o-mini';
|
||||
} else if (modelName.includes('gpt-4o')) {
|
||||
|
|
|
|||
|
|
@ -53,6 +53,14 @@ describe('getValueKey', () => {
|
|||
expect(getValueKey('gpt-4o-mini-2024-07-18')).toBe('gpt-4o-mini');
|
||||
expect(getValueKey('openai/gpt-4o-mini')).toBe('gpt-4o-mini');
|
||||
expect(getValueKey('gpt-4o-mini-0718')).toBe('gpt-4o-mini');
|
||||
expect(getValueKey('gpt-4o-2024-08-06-0718')).not.toBe('gpt-4o');
|
||||
});
|
||||
|
||||
it('should return "gpt-4o-2024-08-06" for model type of "gpt-4o-2024-08-06"', () => {
|
||||
expect(getValueKey('gpt-4o-2024-08-06-2024-07-18')).toBe('gpt-4o-2024-08-06');
|
||||
expect(getValueKey('openai/gpt-4o-2024-08-06')).toBe('gpt-4o-2024-08-06');
|
||||
expect(getValueKey('gpt-4o-2024-08-06-0718')).toBe('gpt-4o-2024-08-06');
|
||||
expect(getValueKey('gpt-4o-2024-08-06-0718')).not.toBe('gpt-4o');
|
||||
});
|
||||
|
||||
it('should return "claude-3-5-sonnet" for model type of "claude-3-5-sonnet-"', () => {
|
||||
|
|
@ -152,3 +160,68 @@ describe('getMultiplier', () => {
|
|||
);
|
||||
});
|
||||
});
|
||||
|
||||
describe('AWS Bedrock Model Tests', () => {
|
||||
const awsModels = [
|
||||
'anthropic.claude-3-haiku-20240307-v1:0',
|
||||
'anthropic.claude-3-sonnet-20240229-v1:0',
|
||||
'anthropic.claude-3-opus-20240229-v1:0',
|
||||
'anthropic.claude-3-5-sonnet-20240620-v1:0',
|
||||
'anthropic.claude-v2:1',
|
||||
'anthropic.claude-instant-v1',
|
||||
'meta.llama2-13b-chat-v1',
|
||||
'meta.llama2-70b-chat-v1',
|
||||
'meta.llama3-8b-instruct-v1:0',
|
||||
'meta.llama3-70b-instruct-v1:0',
|
||||
'meta.llama3-1-8b-instruct-v1:0',
|
||||
'meta.llama3-1-70b-instruct-v1:0',
|
||||
'meta.llama3-1-405b-instruct-v1:0',
|
||||
'mistral.mistral-7b-instruct-v0:2',
|
||||
'mistral.mistral-small-2402-v1:0',
|
||||
'mistral.mixtral-8x7b-instruct-v0:1',
|
||||
'mistral.mistral-large-2402-v1:0',
|
||||
'mistral.mistral-large-2407-v1:0',
|
||||
'cohere.command-text-v14',
|
||||
'cohere.command-light-text-v14',
|
||||
'cohere.command-r-v1:0',
|
||||
'cohere.command-r-plus-v1:0',
|
||||
'ai21.j2-mid-v1',
|
||||
'ai21.j2-ultra-v1',
|
||||
'amazon.titan-text-lite-v1',
|
||||
'amazon.titan-text-express-v1',
|
||||
];
|
||||
|
||||
it('should return the correct prompt multipliers for all models', () => {
|
||||
const results = awsModels.map((model) => {
|
||||
const multiplier = getMultiplier({ valueKey: model, tokenType: 'prompt' });
|
||||
return multiplier === tokenValues[model].prompt;
|
||||
});
|
||||
expect(results.every(Boolean)).toBe(true);
|
||||
});
|
||||
|
||||
it('should return the correct completion multipliers for all models', () => {
|
||||
const results = awsModels.map((model) => {
|
||||
const multiplier = getMultiplier({ valueKey: model, tokenType: 'completion' });
|
||||
return multiplier === tokenValues[model].completion;
|
||||
});
|
||||
expect(results.every(Boolean)).toBe(true);
|
||||
});
|
||||
|
||||
it('should return the correct prompt multipliers for all models with Bedrock prefix', () => {
|
||||
const results = awsModels.map((model) => {
|
||||
const modelName = `bedrock/${model}`;
|
||||
const multiplier = getMultiplier({ valueKey: modelName, tokenType: 'prompt' });
|
||||
return multiplier === tokenValues[model].prompt;
|
||||
});
|
||||
expect(results.every(Boolean)).toBe(true);
|
||||
});
|
||||
|
||||
it('should return the correct completion multipliers for all models with Bedrock prefix', () => {
|
||||
const results = awsModels.map((model) => {
|
||||
const modelName = `bedrock/${model}`;
|
||||
const multiplier = getMultiplier({ valueKey: modelName, tokenType: 'completion' });
|
||||
return multiplier === tokenValues[model].completion;
|
||||
});
|
||||
expect(results.every(Boolean)).toBe(true);
|
||||
});
|
||||
});
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@ const openAIModels = {
|
|||
'gpt-4-0125': 127990, // -10 from max
|
||||
'gpt-4o': 127990, // -10 from max
|
||||
'gpt-4o-mini': 127990, // -10 from max
|
||||
'gpt-4o-2024-08-06': 127990, // -10 from max
|
||||
'gpt-4-turbo': 127990, // -10 from max
|
||||
'gpt-4-vision': 127990, // -10 from max
|
||||
'gpt-3.5-turbo': 16375, // -10 from max
|
||||
|
|
|
|||
|
|
@ -12,6 +12,7 @@ export const defaultSocialLogins = ['google', 'facebook', 'openid', 'github', 'd
|
|||
export const defaultRetrievalModels = [
|
||||
'gpt-4o',
|
||||
'gpt-4o-2024-05-13',
|
||||
'gpt-4o-2024-08-06',
|
||||
'gpt-4o-mini',
|
||||
'gpt-4o-mini-2024-07-18',
|
||||
'gpt-4-turbo-preview',
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue