Skip to content

fix: add tiered pricing support for models with different token tier rates #8984

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

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
+260 −74
Open

fix: add tiered pricing support for models with different token tier rates #8984

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
921cc45
fix: add tiered pricing support for models with different token tier …
roomote Nov 2, 2025
5e34db1
fix: correct test structure and tiered pricing logic
roomote Nov 3, 2025
7cfe770
fix: update tiered pricing for Gemini 2.5 Pro, Sonnet 4/4.5, and Qwen…
roomote Nov 3, 2025
389524d
test: update OpenRouter test snapshots for tiered pricing
roomote Nov 3, 2025
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
18 changes: 18 additions & 0 deletions packages/types/src/providers/bedrock.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,15 @@ export const bedrockModels = {
minTokensPerCachePoint: 1024,
maxCachePoints: 4,
cachableFields: ["system", "messages", "tools"],
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 6.0,
outputPrice: 22.5,
cacheWritesPrice: 7.5,
cacheReadsPrice: 0.6,
},
],
},
"amazon.nova-pro-v1:0": {
maxTokens: 5000,
Expand Down Expand Up @@ -90,6 +99,15 @@ export const bedrockModels = {
minTokensPerCachePoint: 1024,
maxCachePoints: 4,
cachableFields: ["system", "messages", "tools"],
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 6.0,
outputPrice: 22.5,
cacheWritesPrice: 7.5,
cacheReadsPrice: 0.6,
},
],
},
"anthropic.claude-opus-4-1-20250805-v1:0": {
maxTokens: 8192,
Expand Down
84 changes: 32 additions & 52 deletions packages/types/src/providers/gemini.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,24 +138,19 @@ export const geminiModels = {
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheWritesPrice: 4.5,
inputPrice: 1.25, // Base price for ≤200k tokens
outputPrice: 10,
cacheReadsPrice: 0.125,
cacheWritesPrice: 1.625,
maxThinkingTokens: 32_768,
supportsReasoningBudget: true,
tiers: [
{
contextWindow: 200_000,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.31,
},
{
contextWindow: Infinity,
inputPrice: 2.5,
contextWindow: 1_000_000,
inputPrice: 2.5, // >200k tokens
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
Expand All @@ -164,22 +159,17 @@ export const geminiModels = {
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheWritesPrice: 4.5,
inputPrice: 1.25, // Base price for ≤200k tokens
outputPrice: 10,
cacheReadsPrice: 0.125,
cacheWritesPrice: 1.625,
tiers: [
{
contextWindow: 200_000,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.31,
},
{
contextWindow: Infinity,
inputPrice: 2.5,
contextWindow: 1_000_000,
inputPrice: 2.5, // >200k tokens
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
Expand All @@ -188,24 +178,19 @@ export const geminiModels = {
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheWritesPrice: 4.5,
inputPrice: 1.25, // Base price for ≤200k tokens
outputPrice: 10,
cacheReadsPrice: 0.125,
cacheWritesPrice: 1.625,
maxThinkingTokens: 32_768,
supportsReasoningBudget: true,
tiers: [
{
contextWindow: 200_000,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.31,
},
{
contextWindow: Infinity,
inputPrice: 2.5,
contextWindow: 1_000_000,
inputPrice: 2.5, // >200k tokens
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
Expand All @@ -222,25 +207,20 @@ export const geminiModels = {
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5, // This is the pricing for prompts above 200k tokens.
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheWritesPrice: 4.5,
inputPrice: 1.25, // Base price for ≤200k tokens
outputPrice: 10,
cacheReadsPrice: 0.125,
cacheWritesPrice: 1.625,
maxThinkingTokens: 32_768,
supportsReasoningBudget: true,
requiredReasoningBudget: true,
tiers: [
{
contextWindow: 200_000,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.31,
},
{
contextWindow: Infinity,
inputPrice: 2.5,
contextWindow: 1_000_000,
inputPrice: 2.5, // >200k tokens
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
Expand Down
89 changes: 73 additions & 16 deletions packages/types/src/providers/vertex.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,49 +61,79 @@ export const vertexModels = {
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5,
outputPrice: 15,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.125,
cacheWritesPrice: 1.625,
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
"gemini-2.5-pro-preview-05-06": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5,
outputPrice: 15,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.125,
cacheWritesPrice: 1.625,
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
"gemini-2.5-pro-preview-06-05": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5,
outputPrice: 15,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.125,
cacheWritesPrice: 1.625,
maxThinkingTokens: 32_768,
supportsReasoningBudget: true,
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
"gemini-2.5-pro": {
maxTokens: 64_000,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 2.5,
outputPrice: 15,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.125,
cacheWritesPrice: 1.625,
maxThinkingTokens: 32_768,
supportsReasoningBudget: true,
requiredReasoningBudget: true,
tiers: [
{
contextWindow: 200_000,
inputPrice: 1.25,
outputPrice: 10,
cacheReadsPrice: 0.31,
},
{
contextWindow: Infinity,
contextWindow: 1_000_000,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.625,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
Expand Down Expand Up @@ -173,6 +203,15 @@ export const vertexModels = {
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
supportsReasoningBudget: true,
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 6.0,
outputPrice: 22.5,
cacheWritesPrice: 7.5,
cacheReadsPrice: 0.6,
},
],
},
"claude-sonnet-4-5@20250929": {
maxTokens: 8192,
Expand All @@ -184,6 +223,15 @@ export const vertexModels = {
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
supportsReasoningBudget: true,
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 6.0,
outputPrice: 22.5,
cacheWritesPrice: 7.5,
cacheReadsPrice: 0.6,
},
],
},
"claude-haiku-4-5@20251001": {
maxTokens: 8192,
Expand Down Expand Up @@ -216,6 +264,15 @@ export const vertexModels = {
outputPrice: 75.0,
cacheWritesPrice: 18.75,
cacheReadsPrice: 1.5,
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 30.0,
outputPrice: 112.5,
cacheWritesPrice: 37.5,
cacheReadsPrice: 3.0,
},
],
},
"claude-3-7-sonnet@20250219:thinking": {
maxTokens: 64_000,
Expand Down
22 changes: 20 additions & 2 deletions src/api/providers/fetchers/__tests__/openrouter.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,10 +93,19 @@ describe("OpenRouter API", () => {
inputPrice: 1.25,
outputPrice: 10,
cacheWritesPrice: 1.625,
cacheReadsPrice: 0.31,
cacheReadsPrice: 0.125,
description: undefined,
supportsReasoningEffort: undefined,
supportedParameters: undefined,
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
"google-ai-studio": {
maxTokens: 65536,
Expand All @@ -107,10 +116,19 @@ describe("OpenRouter API", () => {
inputPrice: 1.25,
outputPrice: 10,
cacheWritesPrice: 1.625,
cacheReadsPrice: 0.31,
cacheReadsPrice: 0.125,
description: undefined,
supportsReasoningEffort: undefined,
supportedParameters: undefined,
tiers: [
{
contextWindow: 1_000_000,
inputPrice: 2.5,
outputPrice: 15,
cacheReadsPrice: 0.25,
cacheWritesPrice: 2.875,
},
],
},
})

Expand Down
Loading