Skip to content

Commit

Permalink
🪙 feat: Update Token Values for gpt-4o-2024-08-06 and AWS Models (#…
Browse files Browse the repository at this point in the history 
…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)
  • Loading branch information
@danny-avila
danny-avila authored Aug 9, 2024
1 parent 016ed86 commit e05a6d3
Show file tree
Hide file tree
Showing 4 changed files with 139 additions and 26 deletions.
90 changes: 64 additions & 26 deletions api/models/tx.js
View file
Original file line number Diff line number Diff line change
@@ -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.
Expand All @@ -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')) {
Expand Down
73 changes: 73 additions & 0 deletions api/models/tx.spec.js
View file
Original file line number Diff line number Diff line change
Expand Up @@ -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-"', () => {
Expand Down Expand Up @@ -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);
});
});
1 change: 1 addition & 0 deletions api/utils/tokens.js
View file
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
1 change: 1 addition & 0 deletions packages/data-provider/src/config.ts
View file
Original file line number Diff line number Diff line change
Expand Up @@ -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',
Expand Down

0 comments on commit e05a6d3

Please sign in to comment.