pi-baseten-provider 1.0.11 → 1.0.13

package/README.md

@@ -67,21 +67,23 @@ pi
 
 ## Available Models
 
-| Model | Context | Vision | Reasoning | Input $/M | Output $/M |
-|-------|---------|--------|-----------|-----------|------------|
-| Deepseek V4 Flash 0731 | 1.0M | ❌ | ✅ | $0.13 | $0.26 |
-| Deepseek V4 Pro | 262K | ❌ | ✅ | $1.74 | $3.48 |
-| Deepseek V4 Pro 0813 | 1.0M | ❌ | ✅ | $1.32 | $3.96 |
-| GLM 4.7 | 200K | ❌ | ✅ | $0.60 | $2.20 |
-| GLM 5.2 | 1.0M | ❌ | ✅ | $1.40 | $4.40 |
-| GLM 5.2 Fast | 1.0M | ❌ | ✅ | $2.10 | $6.60 |
-| Inkling | 1.0M | ✅ | ✅ | $1.00 | $4.05 |
-| Inkling Small | 1.0M | ✅ | ✅ | $0.50 | $1.20 |
-| Kimi K2.6 | 262K | ✅ | ✅ | $0.95 | $4.00 |
-| Kimi K2.7 Code | 262K | ✅ | ✅ | $0.95 | $4.00 |
-| Kimi K3 | 1.0M | ✅ | ✅ | $3.00 | $15.00 |
-| Nemotron Ultra | 203K | ❌ | ✅ | $0.60 | $2.40 |
-| OpenAI GPT 120B | 128K | ❌ | ✅ | $0.10 | $0.50 |
+| Model | Context | Vision | Reasoning | Input $/M | Cache Read $/M | Output $/M |
+|-------|---------|--------|-----------|-----------|-----------------|------------|
+| Deepseek V4 Flash 0731 | 1.0M | ❌ | ✅ | $0.13 | $0.03 | $0.26 |
+| Deepseek V4 Pro | 1.0M | ❌ | ✅ | $1.74 | $0.14 | $3.48 |
+| Deepseek V4 Pro 0813 | 1.0M | ❌ | ✅ | $1.32 | $0.13 | $3.96 |
+| GLM 4.7 | 200K | ❌ | ✅ | $0.60 | $0.12 | $2.20 |
+| GLM 5.2 | 1.0M | ✅ | ✅ | $1.40 | $0.14 | $4.40 |
+| GLM 5.2 Fast | 1.0M | ✅ | ✅ | $2.10 | $0.21 | $6.60 |
+| GLM 5.3 | 1.0M | ❌ | ✅ | $1.40 | $0.14 | $4.40 |
+| GLM 5.3 Flash | 1.0M | ✅ | ✅ | $0.15 | $0.03 | $0.50 |
+| Inkling | 1.0M | ✅ | ✅ | $1.00 | $0.17 | $4.05 |
+| Inkling Small | 1.0M | ✅ | ✅ | $0.50 | $0.10 | $1.20 |
+| Kimi K2.6 | 262K | ✅ | ✅ | $0.95 | $0.16 | $4.00 |
+| Kimi K2.7 Code | 262K | ✅ | ✅ | $0.95 | $0.16 | $4.00 |
+| Kimi K3 | 1.0M | ✅ | ✅ | $3.00 | $0.30 | $15.00 |
+| Nemotron Ultra | 203K | ❌ | ✅ | $0.60 | $0.12 | $2.40 |
+| OpenAI GPT 120B | 128K | ❌ | ✅ | $0.10 | $0.10 | $0.50 |
 
 *Costs are per million tokens. Prices subject to change — check [baseten.co/pricing](https://www.baseten.co/pricing/) for current pricing.*
 

package/deprecated-models.json

@@ -1,48 +1 @@
-{
-  "inception/mercury-2": {
-    "id": "inception/mercury-2",
-    "name": "Mercury 2",
-    "reasoning": true,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0,
-      "output": 0,
-      "cacheRead": 0,
-      "cacheWrite": 0
-    },
-    "contextWindow": 8192,
-    "maxTokens": 5000,
-    "compat": {
-      "supportsDeveloperRole": true,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens",
-      "thinkingFormat": "openai"
-    },
-    "deprecatedAt": "2026-08-05T02:00:12.114Z"
-  },
-  "sid/sid-1": {
-    "id": "sid/sid-1",
-    "name": "SID-1",
-    "reasoning": true,
-    "input": [
-      "text"
-    ],
-    "cost": {
-      "input": 0,
-      "output": 0,
-      "cacheRead": 0,
-      "cacheWrite": 0
-    },
-    "contextWindow": 32768,
-    "maxTokens": 5000,
-    "compat": {
-      "supportsDeveloperRole": true,
-      "supportsStore": false,
-      "maxTokensField": "max_completion_tokens",
-      "thinkingFormat": "openai"
-    },
-    "deprecatedAt": "2026-08-05T02:00:12.114Z"
-  }
-}
+{}

package/models.json

@@ -13,7 +13,7 @@
       "cacheWrite": 0
     },
     "contextWindow": 1048576,
-    "maxTokens": 1048576,
+    "maxTokens": 384000,
     "compat": {
       "supportsDeveloperRole": true,
       "supportsStore": false,
@@ -34,7 +34,7 @@
       "cacheRead": 0.145,
       "cacheWrite": 0
     },
-    "contextWindow": 262144,
+    "contextWindow": 1048576,
     "maxTokens": 262144,
     "compat": {
       "supportsDeveloperRole": true,
@@ -56,7 +56,7 @@
       "cacheRead": 0.132,
       "cacheWrite": 0
     },
-    "contextWindow": 1000000,
+    "contextWindow": 1048576,
     "maxTokens": 262144,
     "compat": {
       "supportsDeveloperRole": true,
@@ -92,7 +92,8 @@
     "name": "GLM 5.2",
     "reasoning": true,
     "input": [
-      "text"
+      "text",
+      "image"
     ],
     "cost": {
       "input": 1.4,
@@ -114,7 +115,8 @@
     "name": "GLM 5.2 Fast",
     "reasoning": true,
     "input": [
-      "text"
+      "text",
+      "image"
     ],
     "cost": {
       "input": 2.1,
@@ -131,6 +133,51 @@
       "thinkingFormat": "openai"
     }
   },
+  {
+    "id": "zai-org/GLM-5.3",
+    "name": "GLM 5.3",
+    "reasoning": true,
+    "input": [
+      "text"
+    ],
+    "cost": {
+      "input": 1.4,
+      "output": 4.4,
+      "cacheRead": 0.14,
+      "cacheWrite": 0
+    },
+    "contextWindow": 1048576,
+    "maxTokens": 262144,
+    "compat": {
+      "supportsDeveloperRole": true,
+      "supportsStore": false,
+      "maxTokensField": "max_completion_tokens",
+      "thinkingFormat": "openai"
+    }
+  },
+  {
+    "id": "zai-org/GLM-5.3-Flash",
+    "name": "GLM 5.3 Flash",
+    "reasoning": true,
+    "input": [
+      "text",
+      "image"
+    ],
+    "cost": {
+      "input": 0.15,
+      "output": 0.5,
+      "cacheRead": 0.03,
+      "cacheWrite": 0
+    },
+    "contextWindow": 1048576,
+    "maxTokens": 131072,
+    "compat": {
+      "supportsDeveloperRole": true,
+      "supportsStore": false,
+      "maxTokensField": "max_completion_tokens",
+      "thinkingFormat": "openai"
+    }
+  },
   {
     "id": "thinkingmachines/inkling",
     "name": "Inkling",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-baseten-provider",
-  "version": "1.0.11",
+  "version": "1.0.13",
   "description": "Baseten provider extension for pi - Access DeepSeek, Kimi, GLM, MiniMax, Nemotron, and GPT-OSS models through the Baseten Model API",
   "author": "monotykamary",
   "homepage": "https://github.com/monotykamary/pi-baseten-provider#readme",
@@ -33,7 +33,9 @@
     "deprecated-models.json",
     "custom-models.json",
     "patch.json",
-    "scripts/update-models.js"
+    "scripts/update-models.js",
+    "README.md",
+    "LICENSE"
   ],
   "pi": {
     "extensions": [

package/scripts/update-models.js

@@ -340,15 +340,15 @@ function formatContext(n) {
 }
 
 function formatCost(cost) {
-  if (cost === 0) return 'Free';
-  if (cost === null || cost === undefined) return '-';
-  return `$${cost.toFixed(2)}`;
+  if (cost === 0) return '—';
+  if (cost === null || cost === undefined) return '—';
+  return '$' + cost.toFixed(2);
 }
 
 function generateReadmeTable(models) {
   const lines = [
-    '| Model | Context | Vision | Reasoning | Input $/M | Output $/M |',
-    '|-------|---------|--------|-----------|-----------|------------|',
+    '| Model | Context | Vision | Reasoning | Input $/M | Cache Read $/M | Output $/M |',
+    '|-------|---------|--------|-----------|-----------|-----------------|------------|',
   ];
 
   for (const model of models) {
@@ -356,9 +356,10 @@ function generateReadmeTable(models) {
     const vision = model.input.includes('image') ? '✅' : '❌';
     const reasoning = model.reasoning ? '✅' : '❌';
     const inputCost = formatCost(model.cost.input);
+    const cacheReadCost = formatCost(model.cost.cacheRead);
     const outputCost = formatCost(model.cost.output);
 
-    lines.push(`| ${model.name} | ${context} | ${vision} | ${reasoning} | ${inputCost} | ${outputCost} |`);
+    lines.push(`| ${model.name} | ${context} | ${vision} | ${reasoning} | ${inputCost} | ${cacheReadCost} | ${outputCost} |`);
   }
 
   return lines.join('\n');
@@ -442,6 +443,32 @@ function updateDeprecatedModels(modelsJsonPath, newModels) {
   }
 }
 
+/**
+ * Grace-period deprecated models (deprecatedAt within TTL) with metadata stripped.
+ * Keeps the README table serving models that are delisted but still within their
+ * 14-day grace window.
+ */
+function withDeprecatedForReadme(models) {
+  const deprecatedPath = path.join(path.dirname(MODELS_JSON_PATH), 'deprecated-models.json');
+  let deprecated = {};
+  try {
+    const parsed = JSON.parse(fs.readFileSync(deprecatedPath, 'utf8'));
+    if (parsed && typeof parsed === 'object' && !Array.isArray(parsed)) deprecated = parsed;
+  } catch { /* no graveyard yet */ }
+  const now = Date.now();
+  const seen = new Set(models.map(m => m.id));
+  const extras = [];
+  for (const entry of Object.values(deprecated)) {
+    if (!entry || !entry.id || seen.has(entry.id)) continue;
+    const removedAt = Date.parse(entry.deprecatedAt || '');
+    if (Number.isNaN(removedAt) || now - removedAt > DEPRECATED_MODEL_TTL_MS) continue;
+    const m = { ...entry };
+    delete m.deprecatedAt;
+    extras.push(m);
+  }
+  return extras.length > 0 ? [...models, ...extras] : models;
+}
+
 async function main() {
   try {
     const apiModels = await fetchModels();
@@ -469,10 +496,13 @@ async function main() {
     updateDeprecatedModels(MODELS_JSON_PATH, models);
     saveJson(MODELS_JSON_PATH, models);
 
-    // Build full model list for README: base → patch → custom
+    // Build full model list for README: (base + grace-period deprecated) → patch → custom.
+    // Including active deprecated models keeps temporarily-delisted models listed until they
+    // are evicted permanently (mirrors the runtime withDeprecated grace window).
     const patchData = loadJson(PATCH_JSON_PATH);
     const customModels = loadJson(CUSTOM_MODELS_JSON_PATH);
-    const readmeModels = buildModels(models, Array.isArray(customModels) ? customModels : [], patchData);
+    const readmeBase = withDeprecatedForReadme(models);
+    const readmeModels = buildModels(readmeBase, Array.isArray(customModels) ? customModels : [], patchData);
     readmeModels.sort((a, b) => a.name.localeCompare(b.name));
 
     // Update README