shumengya/sproutclaw
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(ai): update Google Vertex Gemini models

Browse Source 
closes #5761
This commit is contained in:
Armin Ronacher
2026-06-16 01:03:12 +02:00
parent 7cfd1af395
commit b0c8f65ffa
6 changed files with 162 additions and 298 deletions
Download Patch File Download Diff File Expand all files Collapse all files

223
packages/ai/src/models.generated.ts
View File

@@ -4769,11 +4769,12 @@ export const MODELS = {
provider: "google",
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 0.3,
output: 2.5,
cacheRead: 0.075,
input: 1.5,
output: 9,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -4786,10 +4787,11 @@ export const MODELS = {
provider: "google",
baseUrl: "https://generativelanguage.googleapis.com/v1beta",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 0.1,
output: 0.4,
input: 0.25,
output: 1.5,
cacheRead: 0.025,
cacheWrite: 0,
},
@@ -4870,94 +4872,9 @@ export const MODELS = {
} satisfies Model<"google-generative-ai">,
},
"google-vertex": {
"gemini-1.5-flash": {
id: "gemini-1.5-flash",
name: "Gemini 1.5 Flash (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.075,
output: 0.3,
cacheRead: 0.01875,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 8192,
} satisfies Model<"google-vertex">,
"gemini-1.5-flash-8b": {
id: "gemini-1.5-flash-8b",
name: "Gemini 1.5 Flash-8B (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.0375,
output: 0.15,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 8192,
} satisfies Model<"google-vertex">,
"gemini-1.5-pro": {
id: "gemini-1.5-pro",
name: "Gemini 1.5 Pro (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: false,
input: ["text", "image"],
cost: {
input: 1.25,
output: 5,
cacheRead: 0.3125,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 8192,
} satisfies Model<"google-vertex">,
"gemini-2.0-flash": {
id: "gemini-2.0-flash",
name: "Gemini 2.0 Flash (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: false,
input: ["text", "image"],
cost: {
input: 0.15,
output: 0.6,
cacheRead: 0.0375,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 8192,
} satisfies Model<"google-vertex">,
"gemini-2.0-flash-lite": {
id: "gemini-2.0-flash-lite",
name: "Gemini 2.0 Flash Lite (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.075,
output: 0.3,
cacheRead: 0.01875,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-2.5-flash": {
id: "gemini-2.5-flash",
name: "Gemini 2.5 Flash (Vertex)",
name: "Gemini 2.5 Flash",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -4974,24 +4891,7 @@ export const MODELS = {
} satisfies Model<"google-vertex">,
"gemini-2.5-flash-lite": {
id: "gemini-2.5-flash-lite",
name: "Gemini 2.5 Flash Lite (Vertex)",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.1,
output: 0.4,
cacheRead: 0.01,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-2.5-flash-lite-preview-09-2025": {
id: "gemini-2.5-flash-lite-preview-09-2025",
name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
name: "Gemini 2.5 Flash-Lite",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5008,7 +4908,7 @@ export const MODELS = {
} satisfies Model<"google-vertex">,
"gemini-2.5-pro": {
id: "gemini-2.5-pro",
name: "Gemini 2.5 Pro (Vertex)",
name: "Gemini 2.5 Pro",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5025,7 +4925,7 @@ export const MODELS = {
} satisfies Model<"google-vertex">,
"gemini-3-flash-preview": {
id: "gemini-3-flash-preview",
name: "Gemini 3 Flash Preview (Vertex)",
name: "Gemini 3 Flash Preview",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5041,27 +4941,27 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-3-pro-preview": {
id: "gemini-3-pro-preview",
name: "Gemini 3 Pro Preview (Vertex)",
"gemini-3.1-flash-lite": {
id: "gemini-3.1-flash-lite",
name: "Gemini 3.1 Flash Lite",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 2,
output: 12,
cacheRead: 0.2,
input: 0.25,
output: 1.5,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 1000000,
maxTokens: 64000,
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-3.1-pro-preview": {
id: "gemini-3.1-pro-preview",
name: "Gemini 3.1 Pro Preview (Vertex)",
name: "Gemini 3.1 Pro Preview",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5079,7 +4979,7 @@ export const MODELS = {
} satisfies Model<"google-vertex">,
"gemini-3.1-pro-preview-customtools": {
id: "gemini-3.1-pro-preview-customtools",
name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
name: "Gemini 3.1 Pro Preview Custom Tools",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5095,6 +4995,60 @@ export const MODELS = {
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-3.5-flash": {
id: "gemini-3.5-flash",
name: "Gemini 3.5 Flash",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 1.5,
output: 9,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-flash-latest": {
id: "gemini-flash-latest",
name: "Gemini Flash Latest",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 1.5,
output: 9,
cacheRead: 0.15,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
"gemini-flash-lite-latest": {
id: "gemini-flash-lite-latest",
name: "Gemini Flash-Lite Latest",
api: "google-vertex",
provider: "google-vertex",
baseUrl: "https://{location}-aiplatform.googleapis.com",
reasoning: true,
thinkingLevelMap: {"off":null},
input: ["text", "image"],
cost: {
input: 0.25,
output: 1.5,
cacheRead: 0.025,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
} satisfies Model<"google-vertex">,
},
"groq": {
"llama-3.1-8b-instant": {
@@ -9489,13 +9443,13 @@ export const MODELS = {
thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh"},
input: ["text"],
cost: {
input: 0.09,
output: 0.18,
input: 0.098,
output: 0.196,
cacheRead: 0.02,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 65536,
maxTokens: 4096,
} satisfies Model<"openai-completions">,
"deepseek/deepseek-v4-pro": {
id: "deepseek/deepseek-v4-pro",
@@ -12333,7 +12287,7 @@ export const MODELS = {
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 262144,
maxTokens: 81920,
} satisfies Model<"openai-completions">,
"qwen/qwen3.5-397b-a17b": {
id: "qwen/qwen3.5-397b-a17b",
@@ -15065,6 +15019,23 @@ export const MODELS = {
contextWindow: 256000,
maxTokens: 32768,
} satisfies Model<"anthropic-messages">,
"moonshotai/kimi-k2.7-code-highspeed": {
id: "moonshotai/kimi-k2.7-code-highspeed",
name: "Kimi K2.7 Code High Speed",
api: "anthropic-messages",
provider: "vercel-ai-gateway",
baseUrl: "https://ai-gateway.vercel.sh",
reasoning: true,
input: ["text", "image"],
cost: {
input: 1.9,
output: 8,
cacheRead: 0.38,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 4096,
} satisfies Model<"anthropic-messages">,
"nvidia/nemotron-3-super-120b-a12b": {
id: "nvidia/nemotron-3-super-120b-a12b",
name: "NVIDIA Nemotron 3 Super 120B A12B",