fix(ai): refresh Xiaomi token plan model catalogs

Use the new provider-specific Xiaomi Token Plan catalogs from models.dev instead of cloning the API-billing Xiaomi catalog into every token-plan region. This removes API-billing-only models such as mimo-v2-omni from xiaomi-token-plan-{cn,ams,sgp}.
This commit is contained in:
Vegard Stikbakke
2026-07-08 09:39:44 +02:00
parent 4ea062f9f3
commit cc2db98002
14 changed files with 270 additions and 353 deletions
@@ -4,24 +4,6 @@
import type { Model } from "../types.ts";
export const XIAOMI_TOKEN_PLAN_CN_MODELS = {
"mimo-v2-omni": {
id: "mimo-v2-omni",
name: "MiMo-V2-Omni",
api: "openai-completions",
provider: "xiaomi-token-plan-cn",
baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.14,
output: 0.28,
cacheRead: 0.0028,
cacheWrite: 0,
},
contextWindow: 262144,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"mimo-v2-pro": {
id: "mimo-v2-pro",
name: "MiMo-V2-Pro",
@@ -32,9 +14,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.435,
output: 0.87,
cacheRead: 0.0036,
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -50,9 +32,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = {
reasoning: true,
input: ["text", "image"],
cost: {
input: 0.14,
output: 0.28,
cacheRead: 0.0028,
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1048576,
@@ -68,27 +50,9 @@ export const XIAOMI_TOKEN_PLAN_CN_MODELS = {
reasoning: true,
input: ["text"],
cost: {
input: 0.435,
output: 0.87,
cacheRead: 0.0036,
cacheWrite: 0,
},
contextWindow: 1048576,
maxTokens: 131072,
} satisfies Model<"openai-completions">,
"mimo-v2.5-pro-ultraspeed": {
id: "mimo-v2.5-pro-ultraspeed",
name: "MiMo-V2.5-Pro-UltraSpeed",
api: "openai-completions",
provider: "xiaomi-token-plan-cn",
baseUrl: "https://token-plan-cn.xiaomimimo.com/v1",
compat: {"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},
reasoning: true,
input: ["text"],
cost: {
input: 1.305,
output: 2.61,
cacheRead: 0.0108,
input: 0,
output: 0,
cacheRead: 0,
cacheWrite: 0,
},
contextWindow: 1048576,