@oh-my-pi/pi-catalog 16.3.3 → 16.3.4

package/CHANGELOG.md

@@ -2,6 +2,22 @@
 
 ## [Unreleased]
 
+## [16.3.4] - 2026-07-03
+
+### Added
+
+- Added Baseten as a supported model provider
+- Added support for new models from Baseten, including DeepSeek V4 Pro and Kimi series
+- Added new Devin agent models: Claude 5 Fable variants
+- Added new Github Copilot models: Kimi K2.7 Code and MAI-Code-1-Flash
+- Added Poolside Laguna XS 2.1 models via Kilo and OpenRouter providers
+- Added support for Claude Fable 5 (Free) via Zenmux provider
+
+### Changed
+
+- Updated priority ordering to include Baseten
+- Updated pricing and limits for various existing models in the catalog
+
 ## [16.3.3] - 2026-07-02
 
 ### Fixed

package/dist/types/hosts.d.ts

@@ -86,6 +86,10 @@ export declare const KNOWN_HOSTS: {
         readonly providers: readonly ["together"];
         readonly urlMarkers: readonly ["api.together.xyz"];
     };
+    readonly baseten: {
+        readonly providers: readonly ["baseten"];
+        readonly urlMarkers: readonly ["baseten.co"];
+    };
     /** URL-only on purpose: the `fireworks`/`firepass` providers route per-model and not every model is Fireworks-shaped. */
     readonly fireworks: {
         readonly urlMarkers: readonly ["fireworks.ai"];

package/dist/types/provider-models/descriptors.d.ts

@@ -23,6 +23,15 @@ export declare const CATALOG_PROVIDERS: readonly [{
     readonly catalogDiscovery: {
         readonly label: "Alibaba Coding Plan";
     };
+}, {
+    readonly id: "baseten";
+    readonly defaultModel: "moonshotai/Kimi-K2.7-Code";
+    readonly envVars: readonly ["BASETEN_API_KEY"];
+    readonly createModelManagerOptions: (config: ModelManagerConfig) => import("..").ModelManagerOptions<"openai-completions", unknown>;
+    readonly dynamicModelsAuthoritative: true;
+    readonly catalogDiscovery: {
+        readonly label: "Baseten";
+    };
 }, {
     readonly id: "amazon-bedrock";
     readonly defaultModel: "us.anthropic.claude-opus-4-8";

package/dist/types/provider-models/openai-compat.d.ts

@@ -303,6 +303,12 @@ export interface VeniceModelManagerConfig {
     fetch?: FetchImpl;
 }
 export declare function veniceModelManagerOptions(config?: VeniceModelManagerConfig): ModelManagerOptions<"openai-completions">;
+export interface BasetenModelManagerConfig {
+    apiKey?: string;
+    baseUrl?: string;
+    fetch?: FetchImpl;
+}
+export declare function basetenModelManagerOptions(config?: BasetenModelManagerConfig): ModelManagerOptions<"openai-completions">;
 export interface TogetherModelManagerConfig {
     apiKey?: string;
     baseUrl?: string;

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@oh-my-pi/pi-catalog",
-	"version": "16.3.3",
+	"version": "16.3.4",
 	"description": "Model catalog for omp: bundled model database, provider discovery descriptors, model identity, classification, and equivalence",
 	"homepage": "https://omp.sh",
 	"author": "Can Boluk",
@@ -34,12 +34,12 @@
 	},
 	"dependencies": {
 		"@bufbuild/protobuf": "^2.12.0",
-		"@oh-my-pi/pi-utils": "16.3.3",
+		"@oh-my-pi/pi-utils": "16.3.4",
 		"arktype": "^2.2.0",
 		"zod": "^4"
 	},
 	"devDependencies": {
-		"@oh-my-pi/pi-ai": "16.3.3",
+		"@oh-my-pi/pi-ai": "16.3.4",
 		"@types/bun": "^1.3.14"
 	},
 	"engines": {

package/src/hosts.ts

@@ -47,6 +47,7 @@ export const KNOWN_HOSTS = {
 	xai: { providers: ["xai"], urlMarkers: ["api.x.ai"] },
 	mistral: { providers: ["mistral"], urlMarkers: ["mistral.ai"] },
 	together: { providers: ["together"], urlMarkers: ["api.together.xyz"] },
+	baseten: { providers: ["baseten"], urlMarkers: ["baseten.co"] },
 	/** URL-only on purpose: the `fireworks`/`firepass` providers route per-model and not every model is Fireworks-shaped. */
 	fireworks: { urlMarkers: ["fireworks.ai"] },
 	groq: { providers: ["groq"], urlMarkers: ["api.groq.com"] },

package/src/identity/priority.ts

@@ -20,6 +20,7 @@ const DEFAULT_MODEL_PROVIDER_ORDER = [
 	// High-quality aggregators / hosted inference providers.
 	"fireworks",
 	"cerebras",
+	"baseten",
 	"openrouter",
 	"aimlapi",
 	"together",

package/src/models.json

@@ -10999,6 +10999,7 @@
 			},
 			"compat": {
 				"officialEndpoint": true,
+				"signingEndpoint": true,
 				"disableAdaptiveThinking": false,
 				"supportsEagerToolInputStreaming": true,
 				"supportsLongCacheRetention": true,
@@ -11052,6 +11053,7 @@
 			"maxTokens": 4096,
 			"compat": {
 				"officialEndpoint": true,
+				"signingEndpoint": true,
 				"disableAdaptiveThinking": false,
 				"supportsEagerToolInputStreaming": true,
 				"supportsLongCacheRetention": true,
@@ -11085,6 +11087,7 @@
 			"maxTokens": 4096,
 			"compat": {
 				"officialEndpoint": true,
+				"signingEndpoint": true,
 				"disableAdaptiveThinking": false,
 				"supportsEagerToolInputStreaming": true,
 				"supportsLongCacheRetention": true,
@@ -12655,6 +12658,335 @@
 			}
 		}
 	},
+	"baseten": {
+		"deepseek-ai/DeepSeek-V4-Pro": {
+			"id": "deepseek-ai/DeepSeek-V4-Pro",
+			"name": "Deepseek V4 Pro",
+			"api": "openai-completions",
+			"provider": "baseten",
+			"baseUrl": "https://inference.baseten.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 1.74,
+				"output": 3.48,
+				"cacheRead": 0.145,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 262144,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				],
+				"effortMap": {
+					"minimal": "high",
+					"low": "high",
+					"medium": "high",
+					"high": "high",
+					"xhigh": "max"
+				}
+			}
+		},
+		"moonshotai/Kimi-K2.5": {
+			"id": "moonshotai/Kimi-K2.5",
+			"name": "Kimi K2.5",
+			"api": "openai-completions",
+			"provider": "baseten",
+			"baseUrl": "https://inference.baseten.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.6,
+				"output": 3,
+				"cacheRead": 0.12,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262000,
+			"maxTokens": 262000,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"moonshotai/Kimi-K2.6": {
+			"id": "moonshotai/Kimi-K2.6",
+			"name": "Kimi K2.6",
+			"api": "openai-completions",
+			"provider": "baseten",
+			"baseUrl": "https://inference.baseten.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.95,
+				"output": 4,
+				"cacheRead": 0.16,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262000,
+			"maxTokens": 262000,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"moonshotai/Kimi-K2.7-Code": {
+			"id": "moonshotai/Kimi-K2.7-Code",
+			"name": "Kimi K2.7 Code",
+			"api": "openai-completions",
+			"provider": "baseten",
+			"baseUrl": "https://inference.baseten.co/v1",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.95,
+				"output": 4,
+				"cacheRead": 0.16,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262000,
+			"maxTokens": 262000,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"nvidia/Nemotron-120B-A12B": {
+			"id": "nvidia/Nemotron-120B-A12B",
+			"name": "Nemotron Super",
+			"api": "openai-completions",
+			"provider": "baseten",
+			"baseUrl": "https://inference.baseten.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.3,
+				"output": 0.75,
+				"cacheRead": 0.06,
+				"cacheWrite": 0
+			},
+			"contextWindow": 202800,
+			"maxTokens": 202800,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"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,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.6,
+				"output": 2.4,
+				"cacheRead": 0.12,
+				"cacheWrite": 0
+			},
+			"contextWindow": 202800,
+			"maxTokens": 202800,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"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,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.09999999999999999,
+				"output": 0.5,
+				"cacheRead": 0.09999999999999999,
+				"cacheWrite": 0
+			},
+			"contextWindow": 128072,
+			"maxTokens": 128072,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"zai-org/GLM-4.7": {
+			"id": "zai-org/GLM-4.7",
+			"name": "GLM 4.7",
+			"api": "openai-completions",
+			"provider": "baseten",
+			"baseUrl": "https://inference.baseten.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.6,
+				"output": 2.2,
+				"cacheRead": 0.12,
+				"cacheWrite": 0
+			},
+			"contextWindow": 200000,
+			"maxTokens": 200000,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"zai-org/GLM-5": {
+			"id": "zai-org/GLM-5",
+			"name": "GLM 5",
+			"api": "openai-completions",
+			"provider": "baseten",
+			"baseUrl": "https://inference.baseten.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.95,
+				"output": 3.15,
+				"cacheRead": 0.19999999999999998,
+				"cacheWrite": 0
+			},
+			"contextWindow": 202800,
+			"maxTokens": 202800,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"zai-org/GLM-5.1": {
+			"id": "zai-org/GLM-5.1",
+			"name": "GLM 5.1",
+			"api": "openai-completions",
+			"provider": "baseten",
+			"baseUrl": "https://inference.baseten.co/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 1.3,
+				"output": 4.300000000000001,
+				"cacheRead": 0.26,
+				"cacheWrite": 0
+			},
+			"contextWindow": 202800,
+			"maxTokens": 202800,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		},
+		"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,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 1.4,
+				"output": 4.4,
+				"cacheRead": 0.26,
+				"cacheWrite": 0
+			},
+			"contextWindow": 202720,
+			"maxTokens": 202720,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				]
+			}
+		}
+	},
 	"cerebras": {
 		"gemma-4-31b": {
 			"id": "gemma-4-31b",
@@ -15785,6 +16117,111 @@
 		}
 	},
 	"devin": {
+		"claude-5-fable-high": {
+			"id": "claude-5-fable-high",
+			"name": "Claude Fable 5 High",
+			"api": "devin-agent",
+			"provider": "devin",
+			"baseUrl": "https://server.codeium.com",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"supportsTools": true,
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 64000
+		},
+		"claude-5-fable-low": {
+			"id": "claude-5-fable-low",
+			"name": "Claude Fable 5 Low",
+			"api": "devin-agent",
+			"provider": "devin",
+			"baseUrl": "https://server.codeium.com",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"supportsTools": true,
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 64000
+		},
+		"claude-5-fable-max": {
+			"id": "claude-5-fable-max",
+			"name": "Claude Fable 5 Max",
+			"api": "devin-agent",
+			"provider": "devin",
+			"baseUrl": "https://server.codeium.com",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"supportsTools": true,
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 64000
+		},
+		"claude-5-fable-medium": {
+			"id": "claude-5-fable-medium",
+			"name": "Claude Fable 5 Medium",
+			"api": "devin-agent",
+			"provider": "devin",
+			"baseUrl": "https://server.codeium.com",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"supportsTools": true,
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 64000
+		},
+		"claude-5-fable-xhigh": {
+			"id": "claude-5-fable-xhigh",
+			"name": "Claude Fable 5 XHigh",
+			"api": "devin-agent",
+			"provider": "devin",
+			"baseUrl": "https://server.codeium.com",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"supportsTools": true,
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 64000
+		},
 		"claude-opus-4-6": {
 			"id": "claude-opus-4-6",
 			"name": "Claude Opus 4.6",
@@ -18854,6 +19291,81 @@
 				]
 			}
 		},
+		"kimi-k2.7-code": {
+			"id": "kimi-k2.7-code",
+			"name": "Kimi K2.7 Code",
+			"api": "openai-completions",
+			"provider": "github-copilot",
+			"baseUrl": "https://api.githubcopilot.com",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0.95,
+				"output": 4,
+				"cacheRead": 0.19,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 32000,
+			"headers": {
+				"User-Agent": "opencode/1.3.15",
+				"X-GitHub-Api-Version": "2026-06-01"
+			},
+			"compat": {
+				"supportsStore": false,
+				"supportsDeveloperRole": false,
+				"supportsReasoningEffort": false
+			},
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"mai-code-1-flash-picker": {
+			"id": "mai-code-1-flash-picker",
+			"name": "MAI-Code-1-Flash",
+			"api": "openai-completions",
+			"provider": "github-copilot",
+			"baseUrl": "https://api.githubcopilot.com",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.75,
+				"output": 4.5,
+				"cacheRead": 0.075,
+				"cacheWrite": 0
+			},
+			"contextWindow": 256000,
+			"maxTokens": 128000,
+			"headers": {
+				"User-Agent": "opencode/1.3.15",
+				"X-GitHub-Api-Version": "2026-06-01"
+			},
+			"compat": {
+				"supportsStore": false,
+				"supportsDeveloperRole": false,
+				"supportsReasoningEffort": false
+			},
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
 		"raptor-mini": {
 			"id": "raptor-mini",
 			"name": "Raptor mini",
@@ -31341,6 +31853,44 @@
 				]
 			}
 		},
+		"poolside/laguna-xs-2.1": {
+			"id": "poolside/laguna-xs-2.1",
+			"name": "Laguna XS 2.1",
+			"api": "openai-completions",
+			"provider": "kilo",
+			"baseUrl": "https://api.kilo.ai/api/gateway",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 32768
+		},
+		"poolside/laguna-xs-2.1:free": {
+			"id": "poolside/laguna-xs-2.1:free",
+			"name": "Laguna XS 2.1 (free)",
+			"api": "openai-completions",
+			"provider": "kilo",
+			"baseUrl": "https://api.kilo.ai/api/gateway",
+			"reasoning": false,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 32768
+		},
 		"poolside/laguna-xs.2": {
 			"id": "poolside/laguna-xs.2",
 			"name": "Laguna XS.2",
@@ -59027,6 +59577,11 @@
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
+			"remoteCompaction": {
+				"enabled": true,
+				"api": "openai-codex-responses",
+				"v2StreamingEnabled": true
+			},
 			"contextWindow": 272000,
 			"maxTokens": 128000,
 			"preferWebsockets": true,
@@ -59408,6 +59963,11 @@
 				"cacheRead": 0.25,
 				"cacheWrite": 0
 			},
+			"remoteCompaction": {
+				"enabled": true,
+				"api": "openai-codex-responses",
+				"v2StreamingEnabled": true
+			},
 			"contextWindow": 272000,
 			"maxTokens": 128000,
 			"preferWebsockets": true,
@@ -59440,6 +60000,11 @@
 				"cacheRead": 0.075,
 				"cacheWrite": 0
 			},
+			"remoteCompaction": {
+				"enabled": true,
+				"api": "openai-codex-responses",
+				"v2StreamingEnabled": true
+			},
 			"contextWindow": 272000,
 			"maxTokens": 128000,
 			"preferWebsockets": true,
@@ -59504,6 +60069,11 @@
 				"cacheRead": 0.5,
 				"cacheWrite": 0
 			},
+			"remoteCompaction": {
+				"enabled": true,
+				"api": "openai-codex-responses",
+				"v2StreamingEnabled": true
+			},
 			"contextWindow": 272000,
 			"maxTokens": 128000,
 			"preferWebsockets": true,
@@ -62458,9 +63028,9 @@
 				"image"
 			],
 			"cost": {
-				"input": 0.55,
-				"output": 3.1999999999999997,
-				"cacheRead": 0.11,
+				"input": 0.66,
+				"output": 3.41,
+				"cacheRead": 0.14,
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
@@ -64084,13 +64654,13 @@
 				"text"
 			],
 			"cost": {
-				"input": 0.08900000000000001,
+				"input": 0.09,
 				"output": 0.18,
 				"cacheRead": 0.018,
 				"cacheWrite": 0
 			},
 			"contextWindow": 1048576,
-			"maxTokens": 65536,
+			"maxTokens": 16384,
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -66146,9 +66716,9 @@
 				"image"
 			],
 			"cost": {
-				"input": 0.55,
-				"output": 3.1999999999999997,
-				"cacheRead": 0.11,
+				"input": 0.66,
+				"output": 3.41,
+				"cacheRead": 0.14,
 				"cacheWrite": 0
 			},
 			"contextWindow": 262144,
@@ -68432,6 +69002,62 @@
 				]
 			}
 		},
+		"poolside/laguna-xs-2.1": {
+			"id": "poolside/laguna-xs-2.1",
+			"name": "Laguna XS 2.1",
+			"api": "openrouter",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0.06,
+				"output": 0.12,
+				"cacheRead": 0.03,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 32768,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
+		"poolside/laguna-xs-2.1:free": {
+			"id": "poolside/laguna-xs-2.1:free",
+			"name": "Laguna XS 2.1 (free)",
+			"api": "openrouter",
+			"provider": "openrouter",
+			"baseUrl": "https://openrouter.ai/api/v1",
+			"reasoning": true,
+			"input": [
+				"text"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 262144,
+			"maxTokens": 32768,
+			"thinking": {
+				"mode": "effort",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high"
+				]
+			}
+		},
 		"poolside/laguna-xs.2": {
 			"id": "poolside/laguna-xs.2",
 			"name": "Laguna XS.2",
@@ -69350,8 +69976,8 @@
 				"image"
 			],
 			"cost": {
-				"input": 0.08,
-				"output": 0.5,
+				"input": 0.117,
+				"output": 0.45499999999999996,
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
@@ -71131,13 +71757,13 @@
 				"text"
 			],
 			"cost": {
-				"input": 0.975,
-				"output": 4.300000000000001,
-				"cacheRead": 0.182,
+				"input": 0.966,
+				"output": 3.036,
+				"cacheRead": 0.1794,
 				"cacheWrite": 0
 			},
 			"contextWindow": 202752,
-			"maxTokens": 65535,
+			"maxTokens": 128000,
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -71381,7 +72007,7 @@
 	"synthetic": {
 		"hf:MiniMaxAI/MiniMax-M3": {
 			"id": "hf:MiniMaxAI/MiniMax-M3",
-			"name": "MiniMax-M3",
+			"name": "MiniMaxAI/MiniMax-M3",
 			"api": "openai-completions",
 			"provider": "synthetic",
 			"baseUrl": "https://api.synthetic.new/openai/v1",
@@ -71396,36 +72022,6 @@
 				"cacheRead": 0.6,
 				"cacheWrite": 0
 			},
-			"contextWindow": 524288,
-			"maxTokens": 65536,
-			"thinking": {
-				"mode": "effort",
-				"efforts": [
-					"minimal",
-					"low",
-					"medium",
-					"high",
-					"xhigh"
-				]
-			}
-		},
-		"hf:moonshotai/Kimi-K2.6": {
-			"id": "hf:moonshotai/Kimi-K2.6",
-			"name": "moonshotai/Kimi-K2.6",
-			"api": "openai-completions",
-			"provider": "synthetic",
-			"baseUrl": "https://api.synthetic.new/openai/v1",
-			"reasoning": true,
-			"input": [
-				"text",
-				"image"
-			],
-			"cost": {
-				"input": 0.95,
-				"output": 4,
-				"cacheRead": 0.95,
-				"cacheWrite": 0
-			},
 			"contextWindow": 262144,
 			"maxTokens": 65536,
 			"thinking": {
@@ -71441,7 +72037,7 @@
 		},
 		"hf:moonshotai/Kimi-K2.7-Code": {
 			"id": "hf:moonshotai/Kimi-K2.7-Code",
-			"name": "Kimi K2.7 Code",
+			"name": "moonshotai/Kimi-K2.7-Code",
 			"api": "openai-completions",
 			"provider": "synthetic",
 			"baseUrl": "https://api.synthetic.new/openai/v1",
@@ -71471,7 +72067,7 @@
 		},
 		"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4": {
 			"id": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
-			"name": "Nemotron 3 Super 120B A12B",
+			"name": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
 			"api": "openai-completions",
 			"provider": "synthetic",
 			"baseUrl": "https://api.synthetic.new/openai/v1",
@@ -71500,7 +72096,7 @@
 		},
 		"hf:openai/gpt-oss-120b": {
 			"id": "hf:openai/gpt-oss-120b",
-			"name": "GPT OSS 120B",
+			"name": "openai/gpt-oss-120b",
 			"api": "openai-completions",
 			"provider": "synthetic",
 			"baseUrl": "https://api.synthetic.new/openai/v1",
@@ -71527,7 +72123,7 @@
 		},
 		"hf:Qwen/Qwen3.6-27B": {
 			"id": "hf:Qwen/Qwen3.6-27B",
-			"name": "Qwen3.6 27B",
+			"name": "Qwen/Qwen3.6-27B",
 			"api": "openai-completions",
 			"provider": "synthetic",
 			"baseUrl": "https://api.synthetic.new/openai/v1",
@@ -71556,7 +72152,7 @@
 		},
 		"hf:zai-org/GLM-4.7-Flash": {
 			"id": "hf:zai-org/GLM-4.7-Flash",
-			"name": "GLM-4.7-Flash",
+			"name": "zai-org/GLM-4.7-Flash",
 			"api": "openai-completions",
 			"provider": "synthetic",
 			"baseUrl": "https://api.synthetic.new/openai/v1",
@@ -71583,38 +72179,9 @@
 				]
 			}
 		},
-		"hf:zai-org/GLM-5.1": {
-			"id": "hf:zai-org/GLM-5.1",
-			"name": "zai-org/GLM-5.1",
-			"api": "openai-completions",
-			"provider": "synthetic",
-			"baseUrl": "https://api.synthetic.new/openai/v1",
-			"reasoning": true,
-			"input": [
-				"text"
-			],
-			"cost": {
-				"input": 1,
-				"output": 3,
-				"cacheRead": 1,
-				"cacheWrite": 0
-			},
-			"contextWindow": 196608,
-			"maxTokens": 65536,
-			"thinking": {
-				"mode": "effort",
-				"efforts": [
-					"minimal",
-					"low",
-					"medium",
-					"high",
-					"xhigh"
-				]
-			}
-		},
 		"hf:zai-org/GLM-5.2": {
 			"id": "hf:zai-org/GLM-5.2",
-			"name": "GLM-5.2",
+			"name": "zai-org/GLM-5.2",
 			"api": "openai-completions",
 			"provider": "synthetic",
 			"baseUrl": "https://api.synthetic.new/openai/v1",
@@ -71925,8 +72492,8 @@
 				"text"
 			],
 			"cost": {
-				"input": 0.88,
-				"output": 0.88,
+				"input": 1.04,
+				"output": 1.04,
 				"cacheRead": 0,
 				"cacheWrite": 0
 			},
@@ -81342,12 +81909,12 @@
 				"text"
 			],
 			"cost": {
-				"input": 1.5,
-				"output": 4.5,
-				"cacheRead": 0.3,
+				"input": 1.4,
+				"output": 4.4,
+				"cacheRead": 0.26,
 				"cacheWrite": 0
 			},
-			"contextWindow": 1000000,
+			"contextWindow": 1040000,
 			"maxTokens": 128000,
 			"thinking": {
 				"mode": "budget",
@@ -82388,14 +82955,6 @@
 			},
 			"contextWindow": 2000000,
 			"maxTokens": 2000000,
-			"compat": {
-				"reasoningEffortMap": {
-					"minimal": "low"
-				},
-				"includeEncryptedReasoning": false,
-				"filterReasoningHistory": true,
-				"omitReasoningEffort": false
-			},
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -82408,6 +82967,14 @@
 				"effortMap": {
 					"minimal": "low"
 				}
+			},
+			"compat": {
+				"reasoningEffortMap": {
+					"minimal": "low"
+				},
+				"includeEncryptedReasoning": false,
+				"filterReasoningHistory": true,
+				"omitReasoningEffort": false
 			}
 		},
 		"grok-4.3": {
@@ -82429,14 +82996,6 @@
 			},
 			"contextWindow": 1000000,
 			"maxTokens": 1000000,
-			"compat": {
-				"reasoningEffortMap": {
-					"minimal": "low"
-				},
-				"includeEncryptedReasoning": false,
-				"filterReasoningHistory": true,
-				"omitReasoningEffort": false
-			},
 			"thinking": {
 				"mode": "effort",
 				"efforts": [
@@ -82449,6 +83008,14 @@
 				"effortMap": {
 					"minimal": "low"
 				}
+			},
+			"compat": {
+				"reasoningEffortMap": {
+					"minimal": "low"
+				},
+				"includeEncryptedReasoning": false,
+				"filterReasoningHistory": true,
+				"omitReasoningEffort": false
 			}
 		},
 		"grok-build": {
@@ -83619,6 +84186,44 @@
 				"supportsDisplay": true
 			}
 		},
+		"anthropic/claude-fable-5-free": {
+			"id": "anthropic/claude-fable-5-free",
+			"name": "Claude Fable 5 (Free)",
+			"api": "anthropic-messages",
+			"provider": "zenmux",
+			"baseUrl": "https://zenmux.ai/api/anthropic",
+			"reasoning": true,
+			"input": [
+				"text",
+				"image"
+			],
+			"cost": {
+				"input": 0,
+				"output": 0,
+				"cacheRead": 0,
+				"cacheWrite": 0
+			},
+			"contextWindow": 1000000,
+			"maxTokens": 128000,
+			"thinking": {
+				"mode": "anthropic-adaptive",
+				"efforts": [
+					"minimal",
+					"low",
+					"medium",
+					"high",
+					"xhigh"
+				],
+				"effortMap": {
+					"minimal": "low",
+					"low": "medium",
+					"medium": "high",
+					"high": "xhigh",
+					"xhigh": "max"
+				},
+				"supportsDisplay": true
+			}
+		},
 		"anthropic/claude-haiku-4.5": {
 			"id": "anthropic/claude-haiku-4.5",
 			"name": "Claude Haiku 4.5",

package/src/provider-models/descriptors.ts

@@ -12,6 +12,7 @@ import {
 	aimlApiModelManagerOptions,
 	alibabaCodingPlanModelManagerOptions,
 	anthropicModelManagerOptions,
+	basetenModelManagerOptions,
 	cerebrasModelManagerOptions,
 	cloudflareAiGatewayModelManagerOptions,
 	coreWeaveModelManagerOptions,
@@ -73,6 +74,14 @@ export const CATALOG_PROVIDERS = [
 		createModelManagerOptions: (config: ModelManagerConfig) => alibabaCodingPlanModelManagerOptions(config),
 		catalogDiscovery: { label: "Alibaba Coding Plan" },
 	},
+	{
+		id: "baseten",
+		defaultModel: "moonshotai/Kimi-K2.7-Code",
+		envVars: ["BASETEN_API_KEY"],
+		createModelManagerOptions: (config: ModelManagerConfig) => basetenModelManagerOptions(config),
+		dynamicModelsAuthoritative: true,
+		catalogDiscovery: { label: "Baseten" },
+	},
 	{
 		id: "amazon-bedrock",
 		defaultModel: "us.anthropic.claude-opus-4-8",

package/src/provider-models/openai-compat.ts

@@ -2551,6 +2551,103 @@ export function veniceModelManagerOptions(
 	};
 }
 
+// ---------------------------------------------------------------------------
+// 14.5 Baseten
+// ---------------------------------------------------------------------------
+
+export interface BasetenModelManagerConfig {
+	apiKey?: string;
+	baseUrl?: string;
+	fetch?: FetchImpl;
+}
+
+export function basetenModelManagerOptions(
+	config?: BasetenModelManagerConfig,
+): ModelManagerOptions<"openai-completions"> {
+	const apiKey = config?.apiKey;
+	const baseUrl = config?.baseUrl ?? "https://inference.baseten.co/v1";
+	const references = createBundledReferenceMap<"openai-completions">("baseten");
+	return {
+		providerId: "baseten",
+		dynamicModelsAuthoritative: true,
+		...(apiKey && {
+			fetchDynamicModels: () =>
+				fetchOpenAICompatibleModels({
+					api: "openai-completions",
+					provider: "baseten",
+					baseUrl,
+					apiKey,
+					mapModel: (entry, defaults) => {
+						const reference = references.get(defaults.id);
+						const raw = entry as Record<string, unknown> & {
+							supported_features?: unknown;
+							input_modalities?: unknown;
+							pricing?: Record<string, unknown>;
+						};
+						const features = Array.isArray(raw.supported_features) ? raw.supported_features : [];
+						const modalities = Array.isArray(raw.input_modalities) ? raw.input_modalities : [];
+
+						const isBasetenNativeReasoning =
+							defaults.id === "openai/gpt-oss-120b" ||
+							defaults.id === "deepseek-ai/DeepSeek-V4-Pro" ||
+							defaults.id === "zai-org/GLM-5.2";
+						const reasoning =
+							isBasetenNativeReasoning &&
+							(features.includes("reasoning") || features.includes("reasoning_effort"));
+						const supportsTools = features.includes("tools") ? undefined : false;
+						const vision = modalities.includes("image") || (reference?.input.includes("image") ?? false);
+
+						const pricing = raw.pricing ?? {};
+						const cost = {
+							input: toPositiveNumber(pricing.prompt, 0) * 1_000_000,
+							output: toPositiveNumber(pricing.completion, 0) * 1_000_000,
+							cacheRead: toPositiveNumber(pricing.input_cache_read, 0) * 1_000_000,
+							cacheWrite: 0,
+						};
+
+						const contextWindow = toPositiveNumber(
+							raw.context_length,
+							reference?.contextWindow ?? defaults.contextWindow,
+						);
+						const maxTokens = toPositiveNumber(
+							raw.max_completion_tokens,
+							reference?.maxTokens ?? defaults.maxTokens,
+						);
+
+						const baseModel = mapWithBundledReference(entry, defaults, reference);
+
+						const isEffortReasoning = defaults.id === "openai/gpt-oss-120b" || defaults.id === "zai-org/GLM-5.2";
+						const thinking = isEffortReasoning
+							? {
+									mode: "effort" as const,
+									efforts: [Effort.Minimal, Effort.Low, Effort.Medium, Effort.High, Effort.XHigh],
+									effortMap: {
+										minimal: "high",
+										low: "high",
+										medium: "high",
+										high: "high",
+										xhigh: "max",
+									},
+								}
+							: undefined;
+
+						return {
+							...baseModel,
+							reasoning,
+							input: vision ? ["text", "image"] : ["text"],
+							cost,
+							contextWindow,
+							maxTokens,
+							...(thinking ? { thinking } : {}),
+							...(supportsTools === false ? { supportsTools } : {}),
+						};
+					},
+					fetch: config?.fetch,
+				}),
+		}),
+	};
+}
+
 // ---------------------------------------------------------------------------
 // 15. Together
 // ---------------------------------------------------------------------------