pi-ollama-cloud 0.9.0 → 0.10.0

package/CHANGELOG.md

@@ -2,6 +2,15 @@
 
 All notable changes to this project will be documented in this file.
 
+## [Unreleased]
+
+## [0.10.0] - 2026-09-03
+
+- **Breaking:** Adapt to the changed `/api/usage` response shape. The endpoint now returns a single `limits.monthly` bucket (replacing `limits.session` and `limits.weekly`) and adds an `activity.models` array. `UsageData`, `isUsageResponse`, `formatUsage`, and `formatUsageStatusColored` now read the monthly limit; the status bar shows a single `30d` segment instead of `5h`/`7d`.
+- Refreshed the generated catalog from the live API: added `deepseek-v4-pro:0813`, `glm-5.3`, and `glm-5.3-flash`; removed `deepseek-v4-flash:preview` and `deepseek-v4-pro`, which are no longer listed.
+- Source per-token pricing from the official model table on ollama.com/pricing instead of models.dev estimates, which no longer track Ollama's published rates (up to ~13x off per model). `scripts/generate-pricing.ts` now scrapes the pricing page (the table is server-rendered; no JSON endpoint exists) and matches catalog IDs to pricing rows by exact or `:tag`-family match, replacing the `OLLAMA_TO_MODELSDEV` mapping. Regenerated `pricing.generated.ts` with the official rates, including new models (`glm-5.3`, `glm-5.3-flash`, `deepseek-v4-pro:0813`). Fixes #51. Thanks @Hackbard (#52).
+- Probe per-model max output tokens against the live API via `scripts/generate-limits.ts` into `limits.generated.ts`, replacing the fixed 32768 default for known models (unprobed models still fall back to 32768). The probe timeout is 60s so slow first-token models are not dropped from the table. Thanks @f440 (#49).
+
 ## [0.9.0] - 2026-08-11
 
 - Add `/ollama-cloud-usage` command to show Ollama Cloud session (5h) and weekly (7d) usage limits, per-model request counts, and the 4-week activity cost, fetched from the undocumented `/api/usage` endpoint with the already-resolved API key.

package/README.md

@@ -12,7 +12,7 @@ Registers Ollama Cloud as a model provider with dynamically fetched models, and
 - **Automatic model refresh** - On startup, `/model` open, and `pi update --models`, pi calls the extension's `refreshModels` callback to fetch the latest models from the API and persists them through pi's own model store. No manual refresh command.
 - **`ollama_web_search` tool** - Search the web for real-time information using Ollama Cloud's `/api/web_search` endpoint. Returns titles, URLs, and content snippets.
 - **`ollama_web_fetch` tool** - Fetch and extract text content from a web page URL using Ollama Cloud's `/api/web_fetch` endpoint. Returns page title, content, and links.
-- **Estimated cost tracking** - Models are registered with estimated per-token costs sourced from [models.dev](https://models.dev) (the same catalog pi uses), so Pi's `/cost` shows comparable usage. Ollama Cloud is subscription-billed (Free, Pro, Max), so these are equivalent pay-as-you-go estimates, not actual charges. See [ollama.com/pricing](https://ollama.com/pricing) for plan details.
+- **Per-token cost tracking** - Models are registered with the official per-token prices from [ollama.com/pricing](https://ollama.com/pricing), so Pi's `/cost` shows comparable usage. Ollama Cloud is subscription-billed, so these are equivalent pay-as-you-go rates, not actual charges.
 
 ## Prerequisites
 
@@ -135,8 +135,14 @@ Model metadata is derived from the `/api/show` response:
 | `thinkingLevelMap` | [`thinking-levels.ts`](thinking-levels.ts) with 5 maps (DEFAULT, GPT_OSS, QWEN3, GLM_52, NO_OFF) based on API testing |
 | `input` | `["text", "image"]` if `capabilities` includes `"vision"`, else `["text"]` |
 | `contextWindow` | `model_info.*.context_length` (falls back to 128000) |
-| `maxTokens` | Fixed at 32768 |
-| `cost` | Estimated per-1M-token prices from [models.dev](https://models.dev), generated by `scripts/generate-pricing.ts` into `pricing.generated.ts`. Ollama Cloud is subscription-billed, so these are equivalent pay-as-you-go estimates, not actual charges. Unmapped models default to zero. Prices are pinned to the installed package version and only update on a new release, so newly added models register with zero cost until then. |
+| `maxTokens` | Probed per-model limits from [`limits.generated.ts`](limits.generated.ts), generated by `scripts/generate-limits.ts` (requires `OLLAMA_API_KEY`). Models without a probed limit fall back to 32768. |
+| `cost` | Official per-1M-token prices from the [ollama.com/pricing](https://ollama.com/pricing) model table, generated by `scripts/generate-pricing.ts` into `pricing.generated.ts`. Ollama Cloud is subscription-billed, so these are equivalent pay-as-you-go rates, not actual charges. Catalog IDs with no matching pricing row default to zero. Prices are pinned to the installed package version and only update on a new release, so newly added models register with zero cost until then. |
+
+The per-model max output token table (`limits.generated.ts`) is probed against the live API by `scripts/generate-limits.ts`, since `/api/show` does not expose the limit. It needs an API key: `OLLAMA_API_KEY=<key> npm run generate-limits`. Limits ship with the package, so regenerated values take effect on the next release.
+
+The API itself returns no cost data: completion responses report only token counts (`prompt_tokens`/`completion_tokens`/`total_tokens`, including the final usage chunk when streaming), and `/api/show` exposes no pricing fields. The prices above come from the static `/pricing` page table and are only as fresh as the last regeneration.
+
+Cache pricing is informational only: the `/pricing` page lists a "Cached input" column, but the completion API does not report cache token usage (there is no `prompt_tokens_details.cached_tokens` or equivalent in any response, verified against the live API in September 2026), so pi never sees cache hits and `/cost` estimates do not reflect them. `cacheWrite` is always zero because the pricing table has no cache-write column.
 
 ### Thinking level mapping
 
@@ -166,14 +172,14 @@ Both tools use the same Ollama Cloud API key configured for the provider. No loc
 | Command | Description |
 |---|---|
 | `/ollama-webtools [on\|off\|enable\|disable]` | Enable or disable the `ollama_web_search` and `ollama_web_fetch` tools. Toggles if no argument given. |
-| `/ollama-cloud-usage` | Show Ollama Cloud session (5h) and weekly (7d) usage limits, per-model request counts, and the 4-week activity cost. |
+| `/ollama-cloud-usage` | Show Ollama Cloud monthly usage limits, per-model request counts, and the 4-week activity cost. |
 | `/ollama-usage-status [on\|off\|enable\|disable]` | Enable or disable the footer usage status bar. Toggles if no argument given. |
 
 ## Usage status bar
 
 While an `ollama-cloud` model is the active provider, the footer shows a compact
-live usage readout (`5h ▕███░░░░░░░▏ 34% 7d ▕████░░░░░░▏ 45%`) that refreshes
-every 5 minutes and after each agent turn (but no more often than every 5 minutes). Each segment is colored by how close
+live usage readout (`30d ▕███░░░░░░░▏ 34%`) that refreshes
+every 5 minutes and after each agent turn (but no more often than every 5 minutes). It is colored by how close
 it is to the cap: green below 60%, yellow at 60-79%, red at 80%+. It reads the
 same undocumented `/api/usage` endpoint as `/ollama-cloud-usage` and clears
 itself on transient errors or when you switch to a non-Ollama-Cloud provider.
@@ -227,6 +233,7 @@ npm run check        # lint + format + type-check (auto-fix)
 npm run lint         # lint only (no fixes)
 npm run typecheck    # type-check only (tsgo --noEmit)
 npm run format       # format only
+OLLAMA_API_KEY=<key> npm run generate-limits   # probe max output tokens (writes limits.generated.ts)
 ```
 
 The project uses [Biome](https://biomejs.dev/) for linting and formatting (2-space indent, line width 120) and [tsgo](https://github.com/microsoft/typescript-go) for type-checking.
@@ -295,7 +302,8 @@ git push --tags
 Because the model catalog refreshes automatically at runtime, a release is **not** needed to ship new models. Publish only when:
 
 - A model is retired and still listed by the API: add it to `RETIRED_MODEL_IDS` in `scripts/generate-models.ts` (check https://docs.ollama.com/cloud#retirements, then regenerate `models.generated.ts`).
-- Pricing changes: models.dev prices updated, or a new model needs an `OLLAMA_TO_MODELSDEV` mapping line (regenerate `pricing.generated.ts`).
+- Pricing changes: Ollama updates the model pricing table, or a new model needs a pricing row (regenerate `pricing.generated.ts`).
+- Max output token limits changed: run `OLLAMA_API_KEY=<key> npm run generate-limits` locally and commit.
 
 The tag version must match the version in `package.json` - `npm version` handles this automatically. The workflow at `.github/workflows/publish.yml` verifies the match before publishing to npm.
 

package/index.ts

@@ -134,7 +134,7 @@ export default async function (pi: ExtensionAPI) {
   // --- Usage Command ---
 
   pi.registerCommand("ollama-cloud-usage", {
-    description: "Show Ollama Cloud session and weekly usage limits.",
+    description: "Show Ollama Cloud monthly usage limits.",
     handler: async (_args, ctx) => {
       const apiKey = await getCloudApiKey(ctx);
       if (!apiKey) {
@@ -152,7 +152,7 @@ export default async function (pi: ExtensionAPI) {
 
   // --- Usage Status Bar ---
 
-  // Footer status showing live session/weekly usage while ollama-cloud is the
+  // Footer status showing live monthly usage while ollama-cloud is the
   // active provider. Refreshes on a 5-minute timer; agent_end also triggers a
   // refresh but is throttled to the same cooldown so a turn never hammers the
   // undocumented /api/usage endpoint. The quota-bar concept is inspired by

package/limits.generated.ts

@@ -0,0 +1,25 @@
+// Auto-generated by scripts/generate-limits.ts
+// Do not edit manually.
+// Probed models: 19 (0 failed)
+
+export const MODEL_MAX_OUTPUT_TOKENS: Record<string, number> = {
+  "deepseek-v4-flash:0731": 65536,
+  "deepseek-v4-pro:0813": 65536,
+  "gemma4:31b": 262144,
+  "glm-5.1": 131072,
+  "glm-5.2": 131072,
+  "glm-5.3": 524288,
+  "glm-5.3-flash": 524288,
+  "gpt-oss:120b": 131072,
+  "gpt-oss:20b": 131072,
+  "kimi-k2.6": 262144,
+  "kimi-k2.7-code": 262144,
+  "kimi-k3": 524288,
+  "minimax-m2.7": 131072,
+  "minimax-m3": 131072,
+  "mistral-large-3:675b": 262144,
+  "nemotron-3-nano:30b": 131072,
+  "nemotron-3-super": 65536,
+  "nemotron-3-ultra": 65536,
+  "qwen3.5:397b": 65536,
+};

package/models.generated.ts

@@ -1,7 +1,7 @@
 // Auto-generated by scripts/generate-models.ts
 // Do not edit manually.
-// Generated: 2026-08-08T04:19:46.959Z
-// Model count: 18
+// Generated: 2026-09-03T10:12:02.243Z
+// Model count: 19
 
 import type { ProviderModelConfig } from "@earendil-works/pi-coding-agent";
 
@@ -29,13 +29,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 1048576,
     cost: {
-      cacheRead: 0.0028,
+      cacheRead: 0.014,
       cacheWrite: 0,
-      input: 0.14,
-      output: 0.28,
+      input: 0.44,
+      output: 1.32,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -47,8 +47,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "deepseek-v4-flash:preview",
-    name: "deepseek-v4-flash:preview",
+    id: "deepseek-v4-pro:0813",
+    name: "deepseek-v4-pro:0813",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -69,13 +69,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 1048576,
     cost: {
-      cacheRead: 0.0028,
+      cacheRead: 0.044,
       cacheWrite: 0,
-      input: 0.14,
-      output: 0.28,
+      input: 1.32,
+      output: 3.96,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -87,8 +87,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "deepseek-v4-pro",
-    name: "deepseek-v4-pro",
+    id: "gemma4:31b",
+    name: "gemma4:31b",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -107,15 +107,15 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 524288,
+    contextWindow: 262144,
     cost: {
-      cacheRead: 0.003625,
+      cacheRead: 0.05,
       cacheWrite: 0,
-      input: 0.435,
-      output: 0.87,
+      input: 0.14,
+      output: 0.4,
     },
-    input: ["text"],
-    maxTokens: 32768,
+    input: ["text", "image"],
+    maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -127,8 +127,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "gemma4:31b",
-    name: "gemma4:31b",
+    id: "glm-5.1",
+    name: "glm-5.1",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -147,15 +147,15 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 262144,
+    contextWindow: 202752,
     cost: {
-      cacheRead: 0.1,
+      cacheRead: 0.2,
       cacheWrite: 0,
-      input: 0.1,
-      output: 0.34,
+      input: 1,
+      output: 3.2,
     },
-    input: ["text", "image"],
-    maxTokens: 32768,
+    input: ["text"],
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -167,8 +167,8 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
   },
   {
-    id: "glm-5.1",
-    name: "glm-5.1",
+    id: "glm-5.2",
+    name: "glm-5.2",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -187,7 +187,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 202752,
+    contextWindow: 1048576,
     cost: {
       cacheRead: 0.26,
       cacheWrite: 0,
@@ -195,20 +195,20 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 4.4,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
-      low: "low",
-      medium: "medium",
+      low: null,
+      medium: null,
       minimal: null,
       off: "none",
       xhigh: "max",
     },
   },
   {
-    id: "glm-5.2",
-    name: "glm-5.2",
+    id: "glm-5.3",
+    name: "glm-5.3",
     compat: {
       maxTokensField: "max_tokens",
       openRouterRouting: {},
@@ -227,7 +227,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 1000000,
+    contextWindow: 1048576,
     cost: {
       cacheRead: 0.26,
       cacheWrite: 0,
@@ -235,12 +235,52 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 4.4,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 524288,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
-      low: null,
-      medium: null,
+      low: "low",
+      medium: "medium",
+      minimal: null,
+      off: "none",
+      xhigh: "max",
+    },
+  },
+  {
+    id: "glm-5.3-flash",
+    name: "glm-5.3-flash",
+    compat: {
+      maxTokensField: "max_tokens",
+      openRouterRouting: {},
+      requiresAssistantAfterToolResult: false,
+      requiresReasoningContentOnAssistantMessages: false,
+      requiresThinkingAsText: false,
+      requiresToolResultName: false,
+      sendSessionAffinityHeaders: false,
+      supportsDeveloperRole: false,
+      supportsLongCacheRetention: false,
+      supportsReasoningEffort: true,
+      supportsStore: false,
+      supportsStrictMode: false,
+      supportsUsageInStreaming: true,
+      thinkingFormat: "openai",
+      vercelGatewayRouting: {},
+      zaiToolStream: false,
+    },
+    contextWindow: 1048576,
+    cost: {
+      cacheRead: 0.03,
+      cacheWrite: 0,
+      input: 0.15,
+      output: 0.5,
+    },
+    input: ["text", "image"],
+    maxTokens: 524288,
+    reasoning: true,
+    thinkingLevelMap: {
+      high: "high",
+      low: "low",
+      medium: "medium",
       minimal: null,
       off: "none",
       xhigh: "max",
@@ -269,13 +309,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 131072,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.014,
       cacheWrite: 0,
-      input: 0.037,
-      output: 0.17,
+      input: 0.15,
+      output: 0.6,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -309,13 +349,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 131072,
     cost: {
-      cacheRead: 0.03,
+      cacheRead: 0.035,
       cacheWrite: 0,
-      input: 0.03,
-      output: 0.13,
+      input: 0.07,
+      output: 0.3,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -355,7 +395,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 4,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -395,7 +435,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 4,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 262144,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -435,7 +475,7 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       output: 15,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 524288,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -470,12 +510,12 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     contextWindow: 196608,
     cost: {
       cacheRead: 0.06,
-      cacheWrite: 0.375,
+      cacheWrite: 0,
       input: 0.3,
       output: 1.2,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -507,15 +547,15 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
       vercelGatewayRouting: {},
       zaiToolStream: false,
     },
-    contextWindow: 524288,
+    contextWindow: 512000,
     cost: {
-      cacheRead: 0.06,
+      cacheRead: 0.12,
       cacheWrite: 0,
-      input: 0.3,
-      output: 1.2,
+      input: 0.6,
+      output: 2.4,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -549,13 +589,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.5,
       cacheWrite: 0,
       input: 0.5,
       output: 1.5,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 262144,
     reasoning: false,
   },
   {
@@ -581,13 +621,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0.03,
+      cacheRead: 0.06,
       cacheWrite: 0,
-      input: 0.05,
-      output: 0.2,
+      input: 0.06,
+      output: 0.24,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 131072,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -621,13 +661,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.015,
       cacheWrite: 0,
-      input: 0.2,
-      output: 0.8,
+      input: 0.015,
+      output: 0.6,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -661,13 +701,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0.15,
+      cacheRead: 0.1,
       cacheWrite: 0,
-      input: 0.5,
-      output: 2.5,
+      input: 0.1,
+      output: 3,
     },
     input: ["text"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: "high",
@@ -701,13 +741,13 @@ export const GENERATED_MODELS: ProviderModelConfig[] = [
     },
     contextWindow: 262144,
     cost: {
-      cacheRead: 0,
+      cacheRead: 0.6,
       cacheWrite: 0,
       input: 0.6,
       output: 3.6,
     },
     input: ["text", "image"],
-    maxTokens: 32768,
+    maxTokens: 65536,
     reasoning: true,
     thinkingLevelMap: {
       high: null,

package/models.ts

@@ -1,22 +1,34 @@
 import type { RefreshModelsContext } from "@earendil-works/pi-ai";
 import type { ProviderModelConfig } from "@earendil-works/pi-coding-agent";
+import { MODEL_MAX_OUTPUT_TOKENS } from "./limits.generated.ts";
 import { GENERATED_MODELS } from "./models.generated.ts";
 import { MODEL_PRICING, type ModelPrice } from "./pricing.generated.ts";
 import { resolve as resolveThinkingLevelMap } from "./thinking-levels.ts";
 import { concurrentMap, fetchJsonWithTimeout, getContextLength } from "./utils.ts";
 
 // --- Pricing ---
-// Estimated per-1M-token prices are generated from models.dev by
+// Per-1M-token prices are generated from the ollama.com/pricing model table by
 // scripts/generate-pricing.ts (see pricing.generated.ts, do not edit by hand).
 // Ollama Cloud is subscription-billed; these are equivalent pay-as-you-go
-// estimates so /cost shows comparable usage, not actual charges.
+// rates so /cost shows comparable usage, not actual charges.
 
-/** Resolve the estimated price for an Ollama Cloud model ID. Exact match only;
+/** Resolve the price for an Ollama Cloud model ID. Exact match only;
  *  unmapped models return zero. */
 function resolvePrice(id: string): ModelPrice {
   return MODEL_PRICING[id] ?? { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 };
 }
 
+// --- Max output tokens ---
+// Per-model limits are probed against the live API by scripts/generate-limits.ts
+// (see limits.generated.ts, do not edit by hand). /api/show does not expose the
+// limit, so models without a probed value fall back to 32768.
+
+/** Resolve the max output tokens for an Ollama Cloud model ID. Exact match only;
+ *  unmapped models fall back to 32768. */
+function resolveMaxTokens(id: string): number {
+  return MODEL_MAX_OUTPUT_TOKENS[id] ?? 32768;
+}
+
 // --- Constants ---
 const FETCH_TIMEOUT_MS = 10000;
 // How long a stored catalog is considered fresh before the next network refresh
@@ -127,9 +139,7 @@ export function assembleModels(raw: Record<string, OllamaShowResponse>): Provide
       input: (data.capabilities?.includes("vision") ? ["text", "image"] : ["text"]) as ("text" | "image")[],
       cost: resolvePrice(id),
       contextWindow: getContextLength(data.model_info ?? {}),
-      // No per-model limit exposed by the API (https://docs.ollama.com/api-reference/show-model-details,
-      // https://github.com/ollama/ollama/issues/7222). 32768 matches most Ollama Cloud context windows.
-      maxTokens: 32768,
+      maxTokens: resolveMaxTokens(id),
       compat: buildCompat(),
     }));
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-ollama-cloud",
-  "version": "0.9.0",
+  "version": "0.10.0",
   "type": "module",
   "keywords": [
     "pi-package"
@@ -8,6 +8,7 @@
   "files": [
     "index.ts",
     "config.ts",
+    "limits.generated.ts",
     "models.ts",
     "models.generated.ts",
     "pricing.generated.ts",
@@ -30,7 +31,8 @@
     "format": "biome format --write .",
     "test": "vitest run",
     "smoke:web-tools": "tsx scripts/smoke-web-tools.ts",
-    "generate-models": "tsx scripts/generate-pricing.ts && tsx scripts/generate-models.ts && biome format --write models.generated.ts pricing.generated.ts"
+    "generate-models": "tsx scripts/generate-pricing.ts && tsx scripts/generate-models.ts && biome format --write models.generated.ts pricing.generated.ts",
+    "generate-limits": "tsx scripts/generate-limits.ts && biome format --write limits.generated.ts"
   },
   "pi": {
     "extensions": [

package/pricing.generated.ts

@@ -1,7 +1,7 @@
 // Auto-generated by scripts/generate-pricing.ts
 // Do not edit manually.
-// Generated: 2026-08-08T04:19:45.594Z
-// Model count: 18
+// Generated: 2026-09-03T10:12:00.135Z
+// Model count: 19
 
 export interface ModelPrice {
   input: number;
@@ -11,22 +11,23 @@ export interface ModelPrice {
 }
 
 export const MODEL_PRICING: Record<string, ModelPrice> = {
-  "deepseek-v4-flash:0731": { input: 0.14, output: 0.28, cacheRead: 0.0028, cacheWrite: 0 },
-  "deepseek-v4-flash:preview": { input: 0.14, output: 0.28, cacheRead: 0.0028, cacheWrite: 0 },
-  "deepseek-v4-pro": { input: 0.435, output: 0.87, cacheRead: 0.003625, cacheWrite: 0 },
-  "gemma4:31b": { input: 0.1, output: 0.34, cacheRead: 0.1, cacheWrite: 0 },
-  "glm-5.1": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
+  "deepseek-v4-flash:0731": { input: 0.44, output: 1.32, cacheRead: 0.014, cacheWrite: 0 },
+  "deepseek-v4-pro:0813": { input: 1.32, output: 3.96, cacheRead: 0.044, cacheWrite: 0 },
+  "gemma4:31b": { input: 0.14, output: 0.4, cacheRead: 0.05, cacheWrite: 0 },
+  "glm-5.1": { input: 1, output: 3.2, cacheRead: 0.2, cacheWrite: 0 },
   "glm-5.2": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
-  "gpt-oss:120b": { input: 0.037, output: 0.17, cacheRead: 0, cacheWrite: 0 },
-  "gpt-oss:20b": { input: 0.03, output: 0.13, cacheRead: 0.03, cacheWrite: 0 },
+  "glm-5.3": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
+  "glm-5.3-flash": { input: 0.15, output: 0.5, cacheRead: 0.03, cacheWrite: 0 },
+  "gpt-oss:120b": { input: 0.15, output: 0.6, cacheRead: 0.014, cacheWrite: 0 },
+  "gpt-oss:20b": { input: 0.07, output: 0.3, cacheRead: 0.035, cacheWrite: 0 },
   "kimi-k2.6": { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 },
   "kimi-k2.7-code": { input: 0.95, output: 4, cacheRead: 0.19, cacheWrite: 0 },
   "kimi-k3": { input: 3, output: 15, cacheRead: 0.3, cacheWrite: 0 },
-  "minimax-m2.7": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0.375 },
-  "minimax-m3": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
-  "mistral-large-3:675b": { input: 0.5, output: 1.5, cacheRead: 0, cacheWrite: 0 },
-  "nemotron-3-nano:30b": { input: 0.05, output: 0.2, cacheRead: 0.03, cacheWrite: 0 },
-  "nemotron-3-super": { input: 0.2, output: 0.8, cacheRead: 0, cacheWrite: 0 },
-  "nemotron-3-ultra": { input: 0.5, output: 2.5, cacheRead: 0.15, cacheWrite: 0 },
-  "qwen3.5:397b": { input: 0.6, output: 3.6, cacheRead: 0, cacheWrite: 0 },
+  "minimax-m2.7": { input: 0.3, output: 1.2, cacheRead: 0.06, cacheWrite: 0 },
+  "minimax-m3": { input: 0.6, output: 2.4, cacheRead: 0.12, cacheWrite: 0 },
+  "mistral-large-3:675b": { input: 0.5, output: 1.5, cacheRead: 0.5, cacheWrite: 0 },
+  "nemotron-3-nano:30b": { input: 0.06, output: 0.24, cacheRead: 0.06, cacheWrite: 0 },
+  "nemotron-3-super": { input: 0.015, output: 0.6, cacheRead: 0.015, cacheWrite: 0 },
+  "nemotron-3-ultra": { input: 0.1, output: 3, cacheRead: 0.1, cacheWrite: 0 },
+  "qwen3.5:397b": { input: 0.6, output: 3.6, cacheRead: 0.6, cacheWrite: 0 },
 };

package/usage.ts

@@ -38,12 +38,12 @@ export interface UsageActivity {
     starting_at?: string;
     ending_at?: string;
   };
+  models?: UsageModel[];
 }
 
 export interface UsageData {
   limits: {
-    session: UsageLimit;
-    weekly: UsageLimit;
+    monthly: UsageLimit;
   };
   activity?: UsageActivity;
 }
@@ -71,13 +71,11 @@ export function isUsageLimit(data: unknown): data is UsageLimit {
   );
 }
 
-/** Validate a parsed /api/usage response: must have session and weekly limits. */
+/** Validate a parsed /api/usage response: must have a monthly limit. */
 export function isUsageResponse(data: unknown): data is UsageData {
   if (data == null || typeof data !== "object") return false;
   const d = data as UsageData;
-  return (
-    d.limits != null && typeof d.limits === "object" && isUsageLimit(d.limits.session) && isUsageLimit(d.limits.weekly)
-  );
+  return d.limits != null && typeof d.limits === "object" && isUsageLimit(d.limits.monthly);
 }
 
 // --- Fetch ---
@@ -127,15 +125,9 @@ function usagePercent(usage: number): number {
 export function formatUsage(data: UsageData): string {
   const lines: string[] = ["Ollama Cloud usage:"];
 
-  const sessionPct = usagePercent(data.limits.session.usage);
-  lines.push(`  Session (5h): ${sessionPct}%`);
-  for (const m of data.limits.session.models) {
-    lines.push(`    - ${m.name}: ${m.request_count} request${m.request_count === 1 ? "" : "s"}`);
-  }
-
-  const weeklyPct = usagePercent(data.limits.weekly.usage);
-  lines.push(`  Weekly (7d): ${weeklyPct}%`);
-  for (const m of data.limits.weekly.models) {
+  const monthlyPct = usagePercent(data.limits.monthly.usage);
+  lines.push(`  Monthly (30d): ${monthlyPct}%`);
+  for (const m of data.limits.monthly.models) {
     lines.push(`    - ${m.name}: ${m.request_count} request${m.request_count === 1 ? "" : "s"}`);
   }
 
@@ -160,11 +152,10 @@ function colorSegment(theme: Theme, label: string, pct: number): string {
 
 /**
  * Compact one-line usage for the footer status bar, colored by usage level.
- * The endpoint exposes reset periods (5h/7d) but not exact timestamps, so the
- * color reflects the usage fraction rather than pace.
+ * The endpoint exposes a monthly reset period but not an exact timestamp, so
+ * the color reflects the usage fraction rather than pace.
  */
 export function formatUsageStatusColored(theme: Theme, data: UsageData): string {
-  const session = usagePercent(data.limits.session.usage);
-  const weekly = usagePercent(data.limits.weekly.usage);
-  return `${colorSegment(theme, "5h", session)} ${colorSegment(theme, "7d", weekly)}`;
+  const monthly = usagePercent(data.limits.monthly.usage);
+  return colorSegment(theme, "30d", monthly);
 }