@code-yeongyu/senpi-ai 2026.11.5-1 → 2026.11.6-2

package/dist/api/anthropic-messages.js

@@ -14,7 +14,7 @@ import { withGzipRequestBodies } from "../utils/gzip-request-body.js";
 import { headersToRecord, providerHeadersToRecord } from "../utils/headers.js";
 import { parseJsonWithRepair, parseStreamingJson } from "../utils/json-parse.js";
 import { getPiUserAgent } from "../utils/pi-user-agent.js";
-import { getAnthropicCompat, isAnthropicApiBaseUrl } from "../utils/prompt-cache-ttl.js";
+import { allowsAnthropicLongCacheRetention, getAnthropicCompat } from "../utils/prompt-cache-ttl.js";
 import { attachProviderDiagnostic } from "../utils/provider-diagnostic-carrier.js";
 import { anthropicProviderDiagnosticFromError, anthropicProviderDiagnosticFromSseData, awaitProviderTransport, } from "../utils/provider-diagnostic-sources.js";
 import { getProviderEnvValue } from "../utils/provider-env.js";
@@ -63,11 +63,7 @@ function getCacheControl(model, cacheRetention, env) {
     if (retention === "none") {
         return { retention };
     }
-    const ttl = retention === "long" &&
-        isAnthropicApiBaseUrl(model.baseUrl) &&
-        getAnthropicCompat(model).supportsLongCacheRetention
-        ? "1h"
-        : undefined;
+    const ttl = retention === "long" && allowsAnthropicLongCacheRetention(model) ? "1h" : undefined;
     return {
         retention,
         cacheControl: { type: "ephemeral", ...(ttl && { ttl }) },

package/dist/api/openai-codex-responses.js

@@ -351,7 +351,7 @@ export const stream = (model, context, options) => {
                 startEmitted = true;
                 stream.push({ type: "start", partial: output });
             }
-            await processStream(response, output, stream, model, grammarToolInputProperties, options);
+            await processStream(response, output, stream, model, grammarToolInputProperties, options, body.service_tier);
             if (options?.signal?.aborted) {
                 throw new Error("Request was aborted");
             }
@@ -485,15 +485,20 @@ function applyServiceTierPricing(usage, serviceTier, model) {
     usage.cost.cacheWrite *= multiplier;
     usage.cost.total = usage.cost.input + usage.cost.output + usage.cost.cacheRead + usage.cost.cacheWrite;
 }
+/**
+ * The tier a Codex turn was served at. The backend echoes `service_tier:
+ * "default"` or `"auto"` on turns it serves at the sent tier, so a `default`,
+ * `auto` or absent echo carries no information and, like an absent one,
+ * resolves to the tier that was sent. Any other echo (`flex`, `priority`,
+ * `fast`, `ultrafast`, `scale`) is authoritative. The echo cannot reveal a
+ * genuine downgrade, so a downgraded turn is recorded at the sent tier.
+ * Port of the oh-my-pi v18.8.1 fix (204b8f3); senpi#2890.
+ */
 function resolveCodexServiceTier(responseServiceTier, requestServiceTier) {
-    if (responseServiceTier === "default" &&
-        (requestServiceTier === "flex" ||
-            requestServiceTier === "priority" ||
-            requestServiceTier === "fast" ||
-            requestServiceTier === "ultrafast")) {
+    if (responseServiceTier === undefined || responseServiceTier === "default" || responseServiceTier === "auto") {
         return requestServiceTier;
     }
-    return responseServiceTier ?? requestServiceTier;
+    return responseServiceTier;
 }
 function resolveCodexUrl(baseUrl) {
     const raw = baseUrl && baseUrl.trim().length > 0 ? baseUrl : DEFAULT_CODEX_BASE_URL;
@@ -515,9 +520,13 @@ function resolveCodexWebSocketUrl(baseUrl) {
 // ============================================================================
 // Response Processing
 // ============================================================================
-async function processStream(response, output, stream, model, grammarToolInputProperties, options) {
+async function processStream(response, output, stream, model, grammarToolInputProperties, options, 
+// The tier the request body actually carried after `onPayload` (senpi#2890):
+// a payload hook such as `/fast` may set `service_tier` without it ever
+// appearing in `options.serviceTier`, and pricing must fall back to it.
+sentServiceTier) {
     await processResponsesStream(mapCodexEvents(parseSSE(response, options?.signal), output, model, options?.onProviderStreamEvent), output, stream, model, {
-        serviceTier: options?.serviceTier,
+        serviceTier: sentServiceTier,
         grammarToolInputProperties,
         resolveServiceTier: resolveCodexServiceTier,
         applyServiceTierPricing: (usage, serviceTier) => applyServiceTierPricing(usage, serviceTier, model),
@@ -1241,7 +1250,10 @@ async function processWebSocketStream(url, body, headers, output, stream, model,
             try {
                 socket.send(JSON.stringify({ type: "response.create", ...requestBody }));
                 await processResponsesStream(startWebSocketOutputOnFirstEvent(mapCodexEvents(parseWebSocket(socket, options?.signal, idleTimeoutMs), output, model, options?.onProviderStreamEvent), onStart), output, stream, model, {
-                    serviceTier: options?.serviceTier,
+                    // Price against the tier the frame just sent (senpi#2890, port of
+                    // oh-my-pi v18.8.1 6428580): `onPayload` may rewrite `service_tier`,
+                    // and the requested option no longer describes what went out.
+                    serviceTier: requestBody.service_tier,
                     grammarToolInputProperties,
                     resolveServiceTier: resolveCodexServiceTier,
                     applyServiceTierPricing: (usage, serviceTier) => applyServiceTierPricing(usage, serviceTier, model),

package/dist/api/openai-images-params.d.ts

@@ -6,6 +6,8 @@ export type OpenAIImageSize = "auto" | "1024x1024" | "1536x1024" | "1024x1536" |
 export type OpenAIImageBackground = "auto" | "transparent" | "opaque";
 export type OpenAIImageOutputFormat = "png" | "jpeg" | "webp";
 export type OpenAIImageModeration = "auto" | "low";
+/** GPT Image 2.6 planning effort before rendering; the API defaults to `high`. */
+export type OpenAIImageComplexity = "low" | "medium" | "high";
 export interface OpenAIImagesOptions extends ImagesOptions {
     size?: OpenAIImageSize;
     quality?: OpenAIImageQuality;
@@ -17,12 +19,15 @@ export interface OpenAIImagesOptions extends ImagesOptions {
     /** 0-100 compression for jpeg/webp output only. */
     outputCompression?: number;
     moderation?: OpenAIImageModeration;
+    /** GPT Image 2.6 only; older models reject the field, so omit it for them. */
+    complexity?: OpenAIImageComplexity;
     /** Inpainting mask applied to the first input image; requires at least one image input. */
     mask?: ImageContent;
 }
 export type OpenAIImageParams = Omit<ImageGenerateParamsNonStreaming, "size" | "quality"> & {
     size?: OpenAIImageSize;
     quality?: OpenAIImageQuality;
+    complexity?: OpenAIImageComplexity;
     image?: Uploadable[];
     mask?: Uploadable;
 };

package/dist/api/openai-images-params.js

@@ -85,6 +85,7 @@ export function buildParams(model, context, options) {
         ...(options?.background === undefined ? {} : { background: options.background }),
         ...(options?.outputCompression === undefined ? {} : { output_compression: options.outputCompression }),
         ...(options?.moderation === undefined ? {} : { moderation: options.moderation }),
+        ...(options?.complexity === undefined ? {} : { complexity: options.complexity }),
     };
 }
 export function isImageParams(value) {

package/dist/api/warm-prompt-cache.js

@@ -1,6 +1,6 @@
 import { withGzipRequestBodies } from "../utils/gzip-request-body.js";
 import { providerHeadersToRecord } from "../utils/headers.js";
-import { getAnthropicCompat, isAnthropicApiBaseUrl } from "../utils/prompt-cache-ttl.js";
+import { getAnthropicCompat, supportsAnthropicCacheWarming } from "../utils/prompt-cache-ttl.js";
 import { isOpenAIResponsesPromptCacheModel } from "./openai-responses-prompt-cache.js";
 import { getPromptCacheWarmer } from "./prompt-cache-warmers.js";
 export async function warmPromptCache(model, context, options = {}) {
@@ -24,10 +24,11 @@ export async function warmPromptCache(model, context, options = {}) {
             usageRaw,
         };
     }
-    if (model.api !== "anthropic-messages" || !isAnthropicApiBaseUrl(model.baseUrl)) {
+    if (model.api !== "anthropic-messages")
         return { supported: false };
-    }
     const anthropicModel = model;
+    if (!supportsAnthropicCacheWarming(anthropicModel))
+        return { supported: false };
     // Loaded lazily: a static import would pull the Anthropic SDK into the root
     // barrel and break the lazy provider-loading contract (lazy-module-load.test.ts).
     const [{ default: Anthropic }, { buildAnthropicWarmPromptCacheParams }] = await Promise.all([

package/dist/auth/pool/slots.d.ts

@@ -77,6 +77,15 @@ export declare class EmptyApiKeyError extends Error {
     readonly name = "EmptyApiKeyError";
     constructor();
 }
+/**
+ * A reauthorization signed in a different ChatGPT account than the saved one it was started for (#5003). Nothing
+ * is written: the selected account keeps its registration and the other sign-in is not silently swapped in.
+ */
+export declare class ReauthorizeAccountMismatchError extends Error {
+    readonly name = "ReauthorizeAccountMismatchError";
+    readonly slotName: string;
+    constructor(slotName: string);
+}
 /** Drops a blank or missing `key` from an API-key credential; used only for providers that declare `keyOptional`. */
 export declare function withoutBlankKey(credential: Credential): Credential;
 /**
@@ -111,6 +120,8 @@ export type AppendLoginSlotOptions = {
     accountIdentity?: (credential: {
         access: string;
     }) => string | undefined;
+    /** `LoginOptions.reauthorizeSlot`: the saved account this login reauthorizes. */
+    reauthorizeSlot?: string;
 };
 /**
  * Material a provider writes into the flat credential when the real token lives

package/dist/auth/pool/slots.js

@@ -318,6 +318,17 @@ export class EmptyApiKeyError extends Error {
         this.name = "EmptyApiKeyError";
     }
 }
+/**
+ * A reauthorization signed in a different ChatGPT account than the saved one it was started for (#5003). Nothing
+ * is written: the selected account keeps its registration and the other sign-in is not silently swapped in.
+ */
+export class ReauthorizeAccountMismatchError extends Error {
+    constructor(slotName) {
+        super(`Signed in to a different ChatGPT account than '${slotName}'; nothing was changed. Sign in as that account, or add the other one as a new account.`);
+        this.name = "ReauthorizeAccountMismatchError";
+        this.slotName = slotName;
+    }
+}
 /** True when an API-key credential names a `key` that is blank, whitespace or not a string. */
 function hasBlankKey(credential) {
     if (credential.type !== "api_key" || !Object.hasOwn(credential, "key"))
@@ -380,6 +391,11 @@ export function appendLoginSlot(stored, flat, onAllocated, options) {
             onAllocated?.(DEFAULT_SLOT_NAME, "generated");
         return flat;
     }
+    const target = provided || options?.reauthorizeSlot === undefined ? undefined : findSlot(current, options.reauthorizeSlot);
+    if (target) {
+        assertSameReauthorizedAccount(target, flat, options?.accountIdentity);
+        return restoreReauthorizedSlot(current, target, flat, onAllocated);
+    }
     const storedAccounts = Array.isArray(current.accounts) ? current.accounts : undefined;
     if (!provided && "signedOut" in current && current.signedOut === true) {
         // Sign-out keeps only the registration for a later sign-in (senpi#5003 W7). That sign-in takes over
@@ -428,6 +444,62 @@ export function appendLoginSlot(stored, flat, onAllocated, options) {
     onAllocated?.(name, "generated");
     return next;
 }
+/**
+ * A reauthorization of a named saved account rewrites that account and nothing else (#5003). A signed-out account
+ * holds blank tokens, so neither the token-identity match nor the sign-in takeover can find it, and both used to
+ * append a duplicate `login-N`. The account keeps its name, label and source and drops `signedOut`; the flat
+ * projection moves to it when it carried that account or when the whole credential was signed out.
+ */
+/**
+ * The identity a reauthorization must keep. SIWC names an account by issuer, subject and issued client ID, which a
+ * sign-out keeps. A legacy Codex account is named by its token identity, or, once signed out and without a token,
+ * by its workspace (`accountId`). A field the saved account never recorded cannot be compared and is not checked.
+ */
+function assertSameReauthorizedAccount(target, flat, accountIdentity) {
+    if (flat.type !== "oauth")
+        return;
+    const saved = target;
+    const fresh = flat;
+    const differs = (field) => typeof saved[field] === "string" &&
+        saved[field] !== "" &&
+        typeof fresh[field] === "string" &&
+        saved[field] !== fresh[field];
+    if ((saved.route ?? "codex") !== (flat.route ?? "codex"))
+        throw new ReauthorizeAccountMismatchError(target.name);
+    if (flat.route === "siwc") {
+        if (["issuer", "subject", "clientId"].some(differs))
+            throw new ReauthorizeAccountMismatchError(target.name);
+        return;
+    }
+    const savedIdentity = accountIdentity && typeof target.access === "string" && target.access !== ""
+        ? accountIdentity({ access: target.access })
+        : undefined;
+    const freshIdentity = accountIdentity?.(flat);
+    if (savedIdentity !== undefined && freshIdentity !== undefined) {
+        if (savedIdentity !== freshIdentity)
+            throw new ReauthorizeAccountMismatchError(target.name);
+        return;
+    }
+    if (differs("accountId"))
+        throw new ReauthorizeAccountMismatchError(target.name);
+}
+function restoreReauthorizedSlot(current, target, flat, onAllocated) {
+    onAllocated?.(target.name, "generated");
+    if (!Array.isArray(current.accounts) || current.accounts.length === 0)
+        return flat;
+    const fresh = {
+        ...slotFromFlatCredentialNamed(flat, target.name),
+        ...(target.displayName === undefined ? {} : { displayName: target.displayName }),
+        ...(target.source === undefined ? {} : { source: target.source }),
+    };
+    const accounts = listSlots(current).map((slot) => (slot.name === target.name ? fresh : slot));
+    const wholeSignedOut = "signedOut" in current && current.signedOut === true;
+    const reproject = wholeSignedOut || slotMirrorsFlat(current, target);
+    const next = { ...(reproject ? projectFlatFields(current, fresh) : current), accounts };
+    if (reproject)
+        Reflect.deleteProperty(next, "signedOut");
+    return next;
+}
 /**
  * A login of an account that is already saved rewrites that account instead of
  * appending another `login-N` copy of it. Appending kept the old copy, and once the

package/dist/auth/types.d.ts

@@ -274,6 +274,11 @@ export interface LoginOptions {
      * an account; callers must not infer this from the provider's active credential.
      */
     reauthorize?: OAuthCredential;
+    /**
+     * The saved account name of `reauthorize`. The login then restores that account in place, signed-out ones
+     * included, instead of matching by token or appending another `login-N` copy of it.
+     */
+    reauthorizeSlot?: string;
     /**
      * Returns the stable ID of this app installation, e.g. sent to OpenAI as its
      * agent host ID. Called only by login flows that need it, so apps can create

package/dist/index.d.ts

@@ -58,7 +58,7 @@ export * from "./utils/event-stream.ts";
 export * from "./utils/json-parse.ts";
 export * from "./utils/overflow.ts";
 export * from "./utils/provider-error.ts";
-export { isAnthropicApiBaseUrl, PROMPT_CACHE_TTL_LONG_SECONDS, PROMPT_CACHE_TTL_OPENAI_EXTENDED_SECONDS, PROMPT_CACHE_TTL_SHORT_SECONDS, type PromptCacheLifetime, resolvePromptCacheLifetime, resolvePromptCacheTtlSeconds, } from "./utils/prompt-cache-ttl.ts";
+export { isAnthropicApiBaseUrl, PROMPT_CACHE_TTL_LONG_SECONDS, PROMPT_CACHE_TTL_OPENAI_EXTENDED_SECONDS, PROMPT_CACHE_TTL_SHORT_SECONDS, type PromptCacheLifetime, resolvePromptCacheLifetime, resolvePromptCacheTtlSeconds, supportsAnthropicCacheWarming, } from "./utils/prompt-cache-ttl.ts";
 export * from "./utils/provider-failure-description.ts";
 export * from "./utils/retry.ts";
 export * from "./utils/server-fallback-receipt.ts";

package/dist/index.js

@@ -44,7 +44,7 @@ export * from "./utils/event-stream.js";
 export * from "./utils/json-parse.js";
 export * from "./utils/overflow.js";
 export * from "./utils/provider-error.js";
-export { isAnthropicApiBaseUrl, PROMPT_CACHE_TTL_LONG_SECONDS, PROMPT_CACHE_TTL_OPENAI_EXTENDED_SECONDS, PROMPT_CACHE_TTL_SHORT_SECONDS, resolvePromptCacheLifetime, resolvePromptCacheTtlSeconds, } from "./utils/prompt-cache-ttl.js";
+export { isAnthropicApiBaseUrl, PROMPT_CACHE_TTL_LONG_SECONDS, PROMPT_CACHE_TTL_OPENAI_EXTENDED_SECONDS, PROMPT_CACHE_TTL_SHORT_SECONDS, resolvePromptCacheLifetime, resolvePromptCacheTtlSeconds, supportsAnthropicCacheWarming, } from "./utils/prompt-cache-ttl.js";
 export * from "./utils/provider-failure-description.js";
 export * from "./utils/retry.js";
 export * from "./utils/server-fallback-receipt.js";

package/dist/models.js

@@ -2,7 +2,7 @@ import { lazyStream } from "./api/lazy.js";
 import { defaultProviderAuthContext as defaultAuthContext } from "./auth/context.js";
 import { InMemoryCredentialStore, revokeStoredOAuth } from "./auth/credential-store.js";
 import { stampLogin } from "./auth/pool/login-id.js";
-import { appendLoginSlot, assertLoginKeyPresent, removeSlot, withoutBlankKey } from "./auth/pool/slots.js";
+import { appendLoginSlot, assertLoginKeyPresent, ReauthorizeAccountMismatchError, removeSlot, withoutBlankKey, } from "./auth/pool/slots.js";
 import { resolveRefreshCredential } from "./auth/refresh-credential.js";
 import { ModelsError, providerNotConfiguredMessage, resolveProviderAuth, } from "./auth/resolve.js";
 import { inferGoogleThinkingLevelMap } from "./google-thinking-generation.js";
@@ -385,7 +385,7 @@ class ModelsImpl {
             return stampLogin(appendLoginSlot(current, credential, (name, origin) => {
                 committedName = name;
                 committedOrigin = origin;
-            }, { accountIdentity: provider.auth.oauth?.accountIdentity }));
+            }, { accountIdentity: provider.auth.oauth?.accountIdentity, reauthorizeSlot: options?.reauthorizeSlot }));
         }, { signal });
         void mutation.catch(() => { });
         try {
@@ -409,6 +409,9 @@ class ModelsImpl {
         }
         catch (error) {
             signal.throwIfAborted();
+            // The user must see why a reauthorization changed nothing, not a storage failure.
+            if (error instanceof ReauthorizeAccountMismatchError)
+                throw error;
             throw new ModelsError("auth", `Credential store modify failed for ${providerId}`, { cause: error });
         }
         if (committedName !== undefined && committedOrigin !== undefined) {

package/dist/providers/chatgpt-subscription.js

@@ -33,6 +33,11 @@ export function chatgptSubscriptionProvider() {
                 ...legacy,
                 loginLabel: "Continue with ChatGPT",
                 login: async (interaction, options) => {
+                    if (options?.reauthorize) {
+                        return options.reauthorize.route === "siwc"
+                            ? { ...(await siwc.login(interaction, options)), route: "siwc" }
+                            : legacy.login(interaction, options);
+                    }
                     const route = await interaction.prompt({
                         type: "select",
                         message: "Sign in to ChatGPT Subscription:",
@@ -50,6 +55,12 @@ export function chatgptSubscriptionProvider() {
                 refresh: async (credential, signal) => credential.route === "siwc"
                     ? { ...credential, ...(await siwc.refresh(credential, signal)), route: "siwc" }
                     : legacy.refresh(credential, signal),
+                revoke: async (credential, options) => {
+                    const flow = await (credential.route === "siwc"
+                        ? loadOpenAIChatGPTOAuth()
+                        : loadChatGptSubscriptionOAuth());
+                    return flow.revoke?.(credential, options) ?? { status: "remote_revocation_unconfirmed" };
+                },
                 toAuth: async (credential) => credential.route === "siwc"
                     ? {
                         ...(await siwc.toAuth(credential)),

package/dist/providers/data/.manifest.json

@@ -1 +1 @@
-{"schemaVersion":6,"generatedAt":"2026-11-05T15:53:47.603Z","structureHash":"10c238ccbbb6c7533c39e840770548c3d3eb1e510093c53c9feed0319e502344","files":{"alibaba-token-plan.json":"9f4d42cc765b2a875bcdcaa392bfdc1323c88968309baf9db9f611a26c595c73","amazon-bedrock.json":"a7e20838b095788cb9d5acbde49664b7f2868fad9b10fb4bbbd66635085bca2d","ant-ling.json":"628feab3ef6c7d80ce96f75999804e1d9f05fec3851e5302e30fff3b69db90f6","anthropic.json":"111384e9f5845e0247bd34edf2400ef7720fcbdac140b944cf8878192d8bd6ab","azure-openai-responses.json":"fd64c6a2a99fa87d768ed2f75f5c7813876df1dbe2f0d1776f7d9bd7ce2e61e4","bai.json":"7e6861aaf27d8af34e1771c6092602194fcec0a0046e6adfab9c3ee54d32b99f","baseten.json":"df8e6ea3c7bb4dfc08c234bbf42a0473cfb7985e0aee06ace4c77495547d98ab","cerebras.json":"2eb969b2956844f9a641d3de52c19f1791293c58f607282fb3b0ebfe85ff66f8","chatgpt-subscription.json":"98320f1d51709d26ca047b3d6e3191cfe2f192f1b27897cbb492f47b0e5a5030","cloudflare-ai-gateway.json":"ac281b8cc18eb84ba61f215eff3234d14732cd66239617fb59d6812b13d6473f","cloudflare-workers-ai.json":"1b9ad4360bde817f0ea358431020308f1052840e2278a57a93629f1790072d2e","deepseek.json":"10a296fb3e898f7715c80890c8af0af4f5fd58f22dbcd6612fdc5d762157ccdc","fireworks.json":"56c557eb97573028e871c211cb17e1d60665eb12d67a712615db4bb255bc9253","github-copilot.json":"474fa92eb88ef242208ca93709ebe6d7f21754917d0cad6210bd1edf2b99a87e","google-vertex.json":"8f986b4aca8c685b0f3481bd252bda21e4858bf9015ad37fc5bcc44b7f01d076","google.json":"d25613a7377e81d785d571be514d67b35436511ce6946247dc66f8674e2a5035","groq.json":"087df37206e9eed8b10f1e558e4c496289bef60074b7e8afba4f20fb102b4ec2","huggingface.json":"209cdcf205961ef2ff203486da614232a86a069ebe0e98266189a14a235fac8f","meta.json":"563f5ec07973f52ab8c3eb26ef91a36ad8a79e950b37174935666cdcb624bf35","minimax-cn.json":"70df757e95e9ea2275bf451956b58a746020835f6cbcbd1a644d7fad5b9941d3","minimax.json":"747038b05f4fc24e41405e8bc810f893d7d5121e214e35e6f812f775769a3806","mistral.json":"aafecc66686645b1baa8c90e81c02856115f09999ff507f9bee004d2e1c77a28","moonshotai-cn.json":"a953eace729ef96c91195d477c63c776a1c40aa36085b61236ca1be0fe5b9337","moonshotai.json":"0435f9dc4e532c0764b6d33d8dfa83ce5fccdbcab54224c5ae74ec2d965290f5","nvidia.json":"078fae404fc622ca6461f16a74791fedafe44976a6c3323b6ba779729823d4ff","openai.json":"d61200cdd22d931dfff8181a5ed8d636c89fb34637dcec80f07ec24f8c2ef5c6","opencode-go.json":"bff6f9062f046c04daf313ed7cf237cd211fe1650ed88eb374b320844ddd4a55","opencode.json":"ff443ac2d4230e4fb0694c827a08dcb63421ae46b8b708141c1609189af536f5","opengateway.json":"c39301d5db2d88aee71705143a6039ebfce2513ef4648979125def43ef409d49","openrouter.json":"7e0143b40e93ff0df86f2d27f02a60d5ff64f535c6fce0111ddcf31f60f3e547","qwen-token-plan-cn.json":"751b18bd443fceb16659ea33013fed90fbf3bbdb4e0ffd7607c93cee2b4cf40d","qwen-token-plan-individual.json":"35ffb0ba1a1ce3f68fc73262dd5e07fbcb5bf5911ad1e6e17bc0621e2894676a","qwen-token-plan.json":"e59b0a45e238578f80d0eea937a093b9cec7cb93751ae20a9e88b16c09eb5cdd","radius.json":"1e4868b8cef7b63d822584e7b8634111891fd6746983a758660ee8f44fad3400","together.json":"8b241bf22b25d8a4bf6d8effe45cebadd193a25a9f0ecc68039d395bf8c6e3bf","typesafe.json":"83409437dbf4c353ac413c0db4e7cf29902fc35e0e0197bdb4eeda2d7f3b07cd","venice.json":"ac2c830fd15de54d1b47e01d776f4032e897b4c13fc86fef44e915f5e03cb21b","vercel-ai-gateway.json":"eaad17194541263e2f0d7d7fbda22130bf848765fff943c7f2ea99e08ae231b3","xai.json":"cf3f475fe5a13625f858171900ba3456c4d95ebb0bac5060cc25e29bb31d3457","xiaomi-token-plan-ams.json":"7fa339ba5675460b1ff4e5bca9e8ad0aa60b0277d75a989b1c196aa6ca2af34d","xiaomi-token-plan-cn.json":"ef7917c6ea0d3edc655c8a52082ee5f1330658aa6f10199d8f164eb4605ef0a0","xiaomi-token-plan-sgp.json":"addda93f6b70ba879db97e3cfd2e4f2efc7cda47d7daa78c23c5b0e51162de5c","xiaomi.json":"5a42caf49d3e4d7946d60386e9899c2146bf8e3cbaff4c576ee4f49b398cc11c","zai-coding-cn.json":"2b6f85e04b5c568e320b1bde25b1c1614af9342e4c1ba0e1d5bb248aaf50cfe9","zai.json":"e9cc408e1756de8abc70148d63d89d11a63c65b7ef06ad0661cd1328e4209ba3"}}
+{"schemaVersion":6,"generatedAt":"2026-11-07T23:48:19.254Z","structureHash":"4187054e5eb70da209409c5f22a4a5074812b2fbffb0c805f3cbb44064c6f22c","files":{"alibaba-token-plan.json":"9f4d42cc765b2a875bcdcaa392bfdc1323c88968309baf9db9f611a26c595c73","amazon-bedrock.json":"a7e20838b095788cb9d5acbde49664b7f2868fad9b10fb4bbbd66635085bca2d","ant-ling.json":"628feab3ef6c7d80ce96f75999804e1d9f05fec3851e5302e30fff3b69db90f6","anthropic.json":"111384e9f5845e0247bd34edf2400ef7720fcbdac140b944cf8878192d8bd6ab","azure-openai-responses.json":"fd64c6a2a99fa87d768ed2f75f5c7813876df1dbe2f0d1776f7d9bd7ce2e61e4","bai.json":"7e6861aaf27d8af34e1771c6092602194fcec0a0046e6adfab9c3ee54d32b99f","baseten.json":"47d10c8050601eb88757def4fc957cdba769dacec4aeb3b0c3f39c41e442330e","cerebras.json":"2eb969b2956844f9a641d3de52c19f1791293c58f607282fb3b0ebfe85ff66f8","chatgpt-subscription.json":"98320f1d51709d26ca047b3d6e3191cfe2f192f1b27897cbb492f47b0e5a5030","cloudflare-ai-gateway.json":"ac281b8cc18eb84ba61f215eff3234d14732cd66239617fb59d6812b13d6473f","cloudflare-workers-ai.json":"1b9ad4360bde817f0ea358431020308f1052840e2278a57a93629f1790072d2e","deepseek.json":"10a296fb3e898f7715c80890c8af0af4f5fd58f22dbcd6612fdc5d762157ccdc","fireworks.json":"2172353d75f4d9fa1af5a1721ac28fb72dd7daa6699a57ede6bbf25d1d500df3","github-copilot.json":"474fa92eb88ef242208ca93709ebe6d7f21754917d0cad6210bd1edf2b99a87e","google-vertex.json":"8f986b4aca8c685b0f3481bd252bda21e4858bf9015ad37fc5bcc44b7f01d076","google.json":"d25613a7377e81d785d571be514d67b35436511ce6946247dc66f8674e2a5035","groq.json":"087df37206e9eed8b10f1e558e4c496289bef60074b7e8afba4f20fb102b4ec2","huggingface.json":"209cdcf205961ef2ff203486da614232a86a069ebe0e98266189a14a235fac8f","meta.json":"563f5ec07973f52ab8c3eb26ef91a36ad8a79e950b37174935666cdcb624bf35","minimax-cn.json":"70df757e95e9ea2275bf451956b58a746020835f6cbcbd1a644d7fad5b9941d3","minimax.json":"747038b05f4fc24e41405e8bc810f893d7d5121e214e35e6f812f775769a3806","mistral.json":"aafecc66686645b1baa8c90e81c02856115f09999ff507f9bee004d2e1c77a28","moonshotai-cn.json":"a953eace729ef96c91195d477c63c776a1c40aa36085b61236ca1be0fe5b9337","moonshotai.json":"0435f9dc4e532c0764b6d33d8dfa83ce5fccdbcab54224c5ae74ec2d965290f5","nvidia.json":"078fae404fc622ca6461f16a74791fedafe44976a6c3323b6ba779729823d4ff","openai.json":"80845240dd2e4cac670f8040ea7bdda867ca84cc0e4943b6b1b88a1676c0dbc7","opencode-go.json":"ae86439dff010c7ff156c4941aed5db6c1aa817c36dcbfbe893a3600bd4564f0","opencode.json":"2dfec265a63ae4e6bb76fe68b5ad4f27e245ef5bac371422709d25dbb6c19901","opengateway.json":"c39301d5db2d88aee71705143a6039ebfce2513ef4648979125def43ef409d49","openrouter.json":"b25d0c071b920a69f8cbffdf0de0dca020c0fe3a8c3153b83dbb344c35548a9c","qwen-token-plan-cn.json":"751b18bd443fceb16659ea33013fed90fbf3bbdb4e0ffd7607c93cee2b4cf40d","qwen-token-plan-individual.json":"35ffb0ba1a1ce3f68fc73262dd5e07fbcb5bf5911ad1e6e17bc0621e2894676a","qwen-token-plan.json":"e59b0a45e238578f80d0eea937a093b9cec7cb93751ae20a9e88b16c09eb5cdd","radius.json":"1e4868b8cef7b63d822584e7b8634111891fd6746983a758660ee8f44fad3400","together.json":"8b241bf22b25d8a4bf6d8effe45cebadd193a25a9f0ecc68039d395bf8c6e3bf","typesafe.json":"83409437dbf4c353ac413c0db4e7cf29902fc35e0e0197bdb4eeda2d7f3b07cd","venice.json":"ebb7b5378f2daf1dc73611a77ea9212fcf702d0e92a2d18698204828c6e55820","vercel-ai-gateway.json":"e961f61d02a9600a735e8cdb9869906fe2613d0f56ac3a8d4e0cb44ec3f68b58","xai.json":"cf3f475fe5a13625f858171900ba3456c4d95ebb0bac5060cc25e29bb31d3457","xiaomi-token-plan-ams.json":"7fa339ba5675460b1ff4e5bca9e8ad0aa60b0277d75a989b1c196aa6ca2af34d","xiaomi-token-plan-cn.json":"ef7917c6ea0d3edc655c8a52082ee5f1330658aa6f10199d8f164eb4605ef0a0","xiaomi-token-plan-sgp.json":"addda93f6b70ba879db97e3cfd2e4f2efc7cda47d7daa78c23c5b0e51162de5c","xiaomi.json":"5a42caf49d3e4d7946d60386e9899c2146bf8e3cbaff4c576ee4f49b398cc11c","zai-coding-cn.json":"2b6f85e04b5c568e320b1bde25b1c1614af9342e4c1ba0e1d5bb248aaf50cfe9","zai.json":"e9cc408e1756de8abc70148d63d89d11a63c65b7ef06ad0661cd1328e4209ba3"}}

package/dist/providers/data/baseten.json

@@ -1 +1 @@
-{"openai-completions":{"chat:deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":0.13,"output":0.26,"cacheRead":0.028,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":384000,"type":"chat"},"chat:deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":1.32,"output":3.96,"cacheRead":0.132,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.3,"output":1.2,"cacheRead":0.007,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-1017":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek V4.1 Flash 1017","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.3,"output":1.2,"cacheRead":0.007,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast","name":"DeepSeek V4.1 Flash 1017 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.014,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-Fast":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-Fast","name":"DeepSeek V4.1 Flash Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.014,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":3,"output":15,"cacheRead":0.3,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/Kimi-K3.1-Pro":{"id":"moonshotai/Kimi-K3.1-Pro","name":"Kimi K3.1 Pro","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"input":["text","image"],"cost":{"input":2,"output":10,"cacheRead":0.2,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false},"contextWindow":1000000,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"Nemotron Ultra","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},"input":["text"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.12,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":202800,"maxTokens":202800,"type":"chat"},"chat:openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"OpenAI GPT 120B","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":"minimal","low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},"input":["text"],"cost":{"input":0.1,"output":0.5,"cacheRead":0.1,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":128072,"maxTokens":128072,"type":"chat"},"chat:zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM 5.2","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":1.4,"output":4.4,"cacheRead":0.14,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"baseten","chatTemplateArgs":{"enable_thinking":{"$var":"thinking.enabled"}}},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:zai-org/GLM-5.2-Fast":{"id":"zai-org/GLM-5.2-Fast","name":"GLM 5.2 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":2.1,"output":6.6,"cacheRead":0.21,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"baseten","chatTemplateArgs":{"enable_thinking":{"$var":"thinking.enabled"}}},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:zai-org/GLM-5.3":{"id":"zai-org/GLM-5.3","name":"GLM 5.3","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":1.4,"output":4.4,"cacheRead":0.14,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:zai-org/GLM-5.3-Fast":{"id":"zai-org/GLM-5.3-Fast","name":"GLM 5.3 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":2.1,"output":6.6,"cacheRead":0.21,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:zai-org/GLM-5.3-Flash":{"id":"zai-org/GLM-5.3-Flash","name":"GLM 5.3 Flash","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.15,"output":0.5,"cacheRead":0.03,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"}}}
+{"openai-completions":{"chat:deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":0.13,"output":0.26,"cacheRead":0.028,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":384000,"type":"chat"},"chat:deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":1.32,"output":3.96,"cacheRead":0.132,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.3,"output":1.2,"cacheRead":0.007,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-1017":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek V4.1 Flash 1017","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.3,"output":1.2,"cacheRead":0.007,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast","name":"DeepSeek V4.1 Flash 1017 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.014,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-Fast":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-Fast","name":"DeepSeek V4.1 Flash Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.014,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":3,"output":15,"cacheRead":0.3,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/Kimi-K3.1-Pro":{"id":"moonshotai/Kimi-K3.1-Pro","name":"Kimi K3.1 Pro","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"input":["text","image"],"cost":{"input":2,"output":10,"cacheRead":0.2,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false},"contextWindow":1000000,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"Nemotron 3 Ultra","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},"input":["text"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.12,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":202800,"maxTokens":202800,"type":"chat"},"chat:openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"OpenAI GPT 120B","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":"minimal","low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},"input":["text"],"cost":{"input":0.1,"output":0.5,"cacheRead":0.1,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":128072,"maxTokens":128072,"type":"chat"},"chat:zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM 5.2","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":1.4,"output":4.4,"cacheRead":0.14,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"baseten","chatTemplateArgs":{"enable_thinking":{"$var":"thinking.enabled"}}},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:zai-org/GLM-5.2-Fast":{"id":"zai-org/GLM-5.2-Fast","name":"GLM 5.2 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":2.1,"output":6.6,"cacheRead":0.21,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"baseten","chatTemplateArgs":{"enable_thinking":{"$var":"thinking.enabled"}}},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:zai-org/GLM-5.3":{"id":"zai-org/GLM-5.3","name":"GLM 5.3","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":1.4,"output":4.4,"cacheRead":0.14,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:zai-org/GLM-5.3-Fast":{"id":"zai-org/GLM-5.3-Fast","name":"GLM 5.3 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":2.1,"output":6.6,"cacheRead":0.21,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:zai-org/GLM-5.3-Flash":{"id":"zai-org/GLM-5.3-Flash","name":"GLM 5.3 Flash","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.15,"output":0.5,"cacheRead":0.03,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"}}}