Skip to content

Commit acac9e9

Browse files
mrubensmrubens
authored
Merge pull request #1607 from Smartsheet-JB-Brown/jbbrown/update_bedrock_prices_to_current
updated prices to match US-West-2 list price shown at https://aws.ama…
2 parents b63c136 + 179d97c commit acac9e9

File tree

1 file changed

+100
-3
lines changed

1 file changed

+100
-3
lines changed

‎src/shared/api.ts‎

Lines changed: 100 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -246,6 +246,8 @@ export interface MessageContent {
246246

247247
export type BedrockModelId = keyof typeof bedrockModels
248248
export const bedrockDefaultModelId: BedrockModelId = "anthropic.claude-3-7-sonnet-20250219-v1:0"
249+
// March, 12 2025 - updated prices to match US-West-2 list price shown at https://aws.amazon.com/bedrock/pricing/
250+
// including older models that are part of the default prompt routers AWS enabled for GA of the promot router feature
249251
export const bedrockModels = {
250252
"amazon.nova-pro-v1:0": {
251253
maxTokens: 5000,
@@ -258,14 +260,26 @@ export const bedrockModels = {
258260
cacheWritesPrice: 0.8, // per million tokens
259261
cacheReadsPrice: 0.2, // per million tokens
260262
},
263+
"amazon.nova-pro-latency-optimized-v1:0": {
264+
maxTokens: 5000,
265+
contextWindow: 300_000,
266+
supportsImages: true,
267+
supportsComputerUse: false,
268+
supportsPromptCache: false,
269+
inputPrice: 1.0,
270+
outputPrice: 4.0,
271+
cacheWritesPrice: 1.0, // per million tokens
272+
cacheReadsPrice: 0.25, // per million tokens
273+
description: "Amazon Nova Pro with latency optimized inference",
274+
},
261275
"amazon.nova-lite-v1:0": {
262276
maxTokens: 5000,
263277
contextWindow: 300_000,
264278
supportsImages: true,
265279
supportsComputerUse: false,
266280
supportsPromptCache: false,
267281
inputPrice: 0.06,
268-
outputPrice: 0.024,
282+
outputPrice: 0.24,
269283
cacheWritesPrice: 0.06, // per million tokens
270284
cacheReadsPrice: 0.015, // per million tokens
271285
},
@@ -307,8 +321,8 @@ export const bedrockModels = {
307321
contextWindow: 200_000,
308322
supportsImages: false,
309323
supportsPromptCache: false,
310-
inputPrice: 1.0,
311-
outputPrice: 5.0,
324+
inputPrice: 0.8,
325+
outputPrice: 4.0,
312326
cacheWritesPrice: 1.0,
313327
cacheReadsPrice: 0.08,
314328
},
@@ -344,6 +358,33 @@ export const bedrockModels = {
344358
inputPrice: 0.25,
345359
outputPrice: 1.25,
346360
},
361+
"anthropic.claude-2-1-v1:0": {
362+
maxTokens: 4096,
363+
contextWindow: 100_000,
364+
supportsImages: false,
365+
supportsPromptCache: false,
366+
inputPrice: 8.0,
367+
outputPrice: 24.0,
368+
description: "Claude 2.1",
369+
},
370+
"anthropic.claude-2-0-v1:0": {
371+
maxTokens: 4096,
372+
contextWindow: 100_000,
373+
supportsImages: false,
374+
supportsPromptCache: false,
375+
inputPrice: 8.0,
376+
outputPrice: 24.0,
377+
description: "Claude 2.0",
378+
},
379+
"anthropic.claude-instant-v1:0": {
380+
maxTokens: 4096,
381+
contextWindow: 100_000,
382+
supportsImages: false,
383+
supportsPromptCache: false,
384+
inputPrice: 0.8,
385+
outputPrice: 2.4,
386+
description: "Claude Instant",
387+
},
347388
"deepseek.r1-v1:0": {
348389
maxTokens: 32_768,
349390
contextWindow: 128_000,
@@ -360,6 +401,7 @@ export const bedrockModels = {
360401
supportsPromptCache: false,
361402
inputPrice: 0.72,
362403
outputPrice: 0.72,
404+
description: "Llama 3.3 Instruct (70B)",
363405
},
364406
"meta.llama3-2-90b-instruct-v1:0": {
365407
maxTokens: 8192,
@@ -369,6 +411,7 @@ export const bedrockModels = {
369411
supportsPromptCache: false,
370412
inputPrice: 0.72,
371413
outputPrice: 0.72,
414+
description: "Llama 3.2 Instruct (90B)",
372415
},
373416
"meta.llama3-2-11b-instruct-v1:0": {
374417
maxTokens: 8192,
@@ -378,6 +421,7 @@ export const bedrockModels = {
378421
supportsPromptCache: false,
379422
inputPrice: 0.16,
380423
outputPrice: 0.16,
424+
description: "Llama 3.2 Instruct (11B)",
381425
},
382426
"meta.llama3-2-3b-instruct-v1:0": {
383427
maxTokens: 8192,
@@ -387,6 +431,7 @@ export const bedrockModels = {
387431
supportsPromptCache: false,
388432
inputPrice: 0.15,
389433
outputPrice: 0.15,
434+
description: "Llama 3.2 Instruct (3B)",
390435
},
391436
"meta.llama3-2-1b-instruct-v1:0": {
392437
maxTokens: 8192,
@@ -396,6 +441,7 @@ export const bedrockModels = {
396441
supportsPromptCache: false,
397442
inputPrice: 0.1,
398443
outputPrice: 0.1,
444+
description: "Llama 3.2 Instruct (1B)",
399445
},
400446
"meta.llama3-1-405b-instruct-v1:0": {
401447
maxTokens: 8192,
@@ -405,6 +451,7 @@ export const bedrockModels = {
405451
supportsPromptCache: false,
406452
inputPrice: 2.4,
407453
outputPrice: 2.4,
454+
description: "Llama 3.1 Instruct (405B)",
408455
},
409456
"meta.llama3-1-70b-instruct-v1:0": {
410457
maxTokens: 8192,
@@ -414,6 +461,17 @@ export const bedrockModels = {
414461
supportsPromptCache: false,
415462
inputPrice: 0.72,
416463
outputPrice: 0.72,
464+
description: "Llama 3.1 Instruct (70B)",
465+
},
466+
"meta.llama3-1-70b-instruct-latency-optimized-v1:0": {
467+
maxTokens: 8192,
468+
contextWindow: 128_000,
469+
supportsImages: false,
470+
supportsComputerUse: false,
471+
supportsPromptCache: false,
472+
inputPrice: 0.9,
473+
outputPrice: 0.9,
474+
description: "Llama 3.1 Instruct (70B) (w/ latency optimized inference)",
417475
},
418476
"meta.llama3-1-8b-instruct-v1:0": {
419477
maxTokens: 8192,
@@ -423,6 +481,7 @@ export const bedrockModels = {
423481
supportsPromptCache: false,
424482
inputPrice: 0.22,
425483
outputPrice: 0.22,
484+
description: "Llama 3.1 Instruct (8B)",
426485
},
427486
"meta.llama3-70b-instruct-v1:0": {
428487
maxTokens: 2048,
@@ -442,6 +501,44 @@ export const bedrockModels = {
442501
inputPrice: 0.3,
443502
outputPrice: 0.6,
444503
},
504+
"amazon.titan-text-lite-v1:0": {
505+
maxTokens: 4096,
506+
contextWindow: 8_000,
507+
supportsImages: false,
508+
supportsComputerUse: false,
509+
supportsPromptCache: false,
510+
inputPrice: 0.15,
511+
outputPrice: 0.2,
512+
description: "Amazon Titan Text Lite",
513+
},
514+
"amazon.titan-text-express-v1:0": {
515+
maxTokens: 4096,
516+
contextWindow: 8_000,
517+
supportsImages: false,
518+
supportsComputerUse: false,
519+
supportsPromptCache: false,
520+
inputPrice: 0.2,
521+
outputPrice: 0.6,
522+
description: "Amazon Titan Text Express",
523+
},
524+
"amazon.titan-text-embeddings-v1:0": {
525+
maxTokens: 8192,
526+
contextWindow: 8_000,
527+
supportsImages: false,
528+
supportsComputerUse: false,
529+
supportsPromptCache: false,
530+
inputPrice: 0.1,
531+
description: "Amazon Titan Text Embeddings",
532+
},
533+
"amazon.titan-text-embeddings-v2:0": {
534+
maxTokens: 8192,
535+
contextWindow: 8_000,
536+
supportsImages: false,
537+
supportsComputerUse: false,
538+
supportsPromptCache: false,
539+
inputPrice: 0.02,
540+
description: "Amazon Titan Text Embeddings V2",
541+
},
445542
} as const satisfies Record<string, ModelInfo>
446543

447544
// Glama

0 commit comments

Comments
 (0)