Skip to content

updated prices to match US-West-2 list price shown at https://aws.ama… #1607

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
mrubens merged 1 commit into from
Mar 12, 2025
Merged

updated prices to match US-West-2 list price shown at https://aws.ama… #1607

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
103 changes: 100 additions & 3 deletions src/shared/api.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -246,6 +246,8 @@ export interface MessageContent {

export type BedrockModelId = keyof typeof bedrockModels
export const bedrockDefaultModelId: BedrockModelId = "anthropic.claude-3-7-sonnet-20250219-v1:0"
// March, 12 2025 - updated prices to match US-West-2 list price shown at https://aws.amazon.com/bedrock/pricing/
// including older models that are part of the default prompt routers AWS enabled for GA of the promot router feature
export const bedrockModels = {
"amazon.nova-pro-v1:0": {
maxTokens: 5000,
Expand All @@ -258,14 +260,26 @@ export const bedrockModels = {
cacheWritesPrice: 0.8, // per million tokens
cacheReadsPrice: 0.2, // per million tokens
},
"amazon.nova-pro-latency-optimized-v1:0": {
maxTokens: 5000,
contextWindow: 300_000,
supportsImages: true,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 1.0,
outputPrice: 4.0,
cacheWritesPrice: 1.0, // per million tokens
cacheReadsPrice: 0.25, // per million tokens
description: "Amazon Nova Pro with latency optimized inference",
},
"amazon.nova-lite-v1:0": {
maxTokens: 5000,
contextWindow: 300_000,
supportsImages: true,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.06,
outputPrice: 0.024,
outputPrice: 0.24,
cacheWritesPrice: 0.06, // per million tokens
cacheReadsPrice: 0.015, // per million tokens
},
Expand Down Expand Up @@ -307,8 +321,8 @@ export const bedrockModels = {
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1.0,
outputPrice: 5.0,
inputPrice: 0.8,
outputPrice: 4.0,
cacheWritesPrice: 1.0,
cacheReadsPrice: 0.08,
},
Expand Down Expand Up @@ -344,6 +358,33 @@ export const bedrockModels = {
inputPrice: 0.25,
outputPrice: 1.25,
},
"anthropic.claude-2-1-v1:0": {
maxTokens: 4096,
contextWindow: 100_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 8.0,
outputPrice: 24.0,
description: "Claude 2.1",
},
"anthropic.claude-2-0-v1:0": {
maxTokens: 4096,
contextWindow: 100_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 8.0,
outputPrice: 24.0,
description: "Claude 2.0",
},
"anthropic.claude-instant-v1:0": {
maxTokens: 4096,
contextWindow: 100_000,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.8,
outputPrice: 2.4,
description: "Claude Instant",
},
"deepseek.r1-v1:0": {
maxTokens: 32_768,
contextWindow: 128_000,
Expand All @@ -360,6 +401,7 @@ export const bedrockModels = {
supportsPromptCache: false,
inputPrice: 0.72,
outputPrice: 0.72,
description: "Llama 3.3 Instruct (70B)",
},
"meta.llama3-2-90b-instruct-v1:0": {
maxTokens: 8192,
Expand All @@ -369,6 +411,7 @@ export const bedrockModels = {
supportsPromptCache: false,
inputPrice: 0.72,
outputPrice: 0.72,
description: "Llama 3.2 Instruct (90B)",
},
"meta.llama3-2-11b-instruct-v1:0": {
maxTokens: 8192,
Expand All @@ -378,6 +421,7 @@ export const bedrockModels = {
supportsPromptCache: false,
inputPrice: 0.16,
outputPrice: 0.16,
description: "Llama 3.2 Instruct (11B)",
},
"meta.llama3-2-3b-instruct-v1:0": {
maxTokens: 8192,
Expand All @@ -387,6 +431,7 @@ export const bedrockModels = {
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.15,
description: "Llama 3.2 Instruct (3B)",
},
"meta.llama3-2-1b-instruct-v1:0": {
maxTokens: 8192,
Expand All @@ -396,6 +441,7 @@ export const bedrockModels = {
supportsPromptCache: false,
inputPrice: 0.1,
outputPrice: 0.1,
description: "Llama 3.2 Instruct (1B)",
},
"meta.llama3-1-405b-instruct-v1:0": {
maxTokens: 8192,
Expand All @@ -405,6 +451,7 @@ export const bedrockModels = {
supportsPromptCache: false,
inputPrice: 2.4,
outputPrice: 2.4,
description: "Llama 3.1 Instruct (405B)",
},
"meta.llama3-1-70b-instruct-v1:0": {
maxTokens: 8192,
Expand All @@ -414,6 +461,17 @@ export const bedrockModels = {
supportsPromptCache: false,
inputPrice: 0.72,
outputPrice: 0.72,
description: "Llama 3.1 Instruct (70B)",
},
"meta.llama3-1-70b-instruct-latency-optimized-v1:0": {
maxTokens: 8192,
contextWindow: 128_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.9,
outputPrice: 0.9,
description: "Llama 3.1 Instruct (70B) (w/ latency optimized inference)",
},
"meta.llama3-1-8b-instruct-v1:0": {
maxTokens: 8192,
Expand All @@ -423,6 +481,7 @@ export const bedrockModels = {
supportsPromptCache: false,
inputPrice: 0.22,
outputPrice: 0.22,
description: "Llama 3.1 Instruct (8B)",
},
"meta.llama3-70b-instruct-v1:0": {
maxTokens: 2048,
Expand All @@ -442,6 +501,44 @@ export const bedrockModels = {
inputPrice: 0.3,
outputPrice: 0.6,
},
"amazon.titan-text-lite-v1:0": {
maxTokens: 4096,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.2,
description: "Amazon Titan Text Lite",
},
"amazon.titan-text-express-v1:0": {
maxTokens: 4096,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.2,
outputPrice: 0.6,
description: "Amazon Titan Text Express",
},
"amazon.titan-text-embeddings-v1:0": {
maxTokens: 8192,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.1,
description: "Amazon Titan Text Embeddings",
},
"amazon.titan-text-embeddings-v2:0": {
maxTokens: 8192,
contextWindow: 8_000,
supportsImages: false,
supportsComputerUse: false,
supportsPromptCache: false,
inputPrice: 0.02,
description: "Amazon Titan Text Embeddings V2",
},
} as const satisfies Record<string, ModelInfo>

// Glama
Expand Down
Loading