Files
openclaw/extensions/baseten/openclaw.plugin.json
Peter Steinberger 695db84cd1 feat(plugins): match shared models across vendor-namespaced catalog ids (#115210)
Aggregators republish first-party models under a namespaced id and varying
case, so the shared-model check could not group novita/moonshotai/kimi-k3 with
moonshot/kimi-k3. Matching now ignores one leading namespace segment and case,
which catches that whole class automatically instead of needing an
upstreamModel marker per row.

Declares the tier on the 18 rows this surfaces across baseten, deepinfra, gmi,
novita, nvidia, and together. All are "capable", matching what the runtime
already applied for an absent flag, so behavior is unchanged.
2026-07-28 10:22:23 -04:00

221 lines
5.3 KiB
JSON

{
"id": "baseten",
"name": "Baseten",
"description": "OpenClaw Baseten provider plugin.",
"activation": {
"onStartup": false
},
"enabledByDefault": true,
"providers": [
"baseten"
],
"providerRequest": {
"providers": {
"baseten": {
"family": "baseten",
"openAICompletions": {
"supportsStreamingUsage": true
}
}
}
},
"modelCatalog": {
"providers": {
"baseten": {
"baseUrl": "https://inference.baseten.co/v1",
"api": "openai-completions",
"defaultModel": "thinkingmachines/inkling",
"models": [
{
"id": "deepseek-ai/DeepSeek-V4-Pro",
"name": "DeepSeek V4 Pro",
"reasoning": true,
"input": [
"text"
],
"contextWindow": 262000,
"maxTokens": 262000,
"cost": {
"input": 1.74,
"output": 3.48,
"cacheRead": 0.145,
"cacheWrite": 0
},
"compat": {
"codeMode": "capable"
}
},
{
"id": "zai-org/GLM-4.7",
"name": "GLM 4.7",
"reasoning": true,
"input": [
"text"
],
"contextWindow": 200000,
"maxTokens": 200000,
"cost": {
"input": 0.6,
"output": 2.2,
"cacheRead": 0.12,
"cacheWrite": 0
}
},
{
"id": "zai-org/GLM-5.2",
"name": "GLM 5.2",
"reasoning": true,
"input": [
"text"
],
"contextWindow": 524000,
"maxTokens": 262000,
"cost": {
"input": 1.4,
"output": 4.4,
"cacheRead": 0.14,
"cacheWrite": 0
},
"compat": {
"codeMode": "capable"
}
},
{
"id": "zai-org/GLM-5.2-Fast",
"name": "GLM 5.2 Fast",
"reasoning": true,
"input": [
"text"
],
"contextWindow": 524000,
"maxTokens": 262000,
"cost": {
"input": 2.1,
"output": 6.6,
"cacheRead": 0.21,
"cacheWrite": 0
}
},
{
"id": "thinkingmachines/inkling",
"name": "Inkling",
"reasoning": true,
"input": [
"text",
"image"
],
"contextWindow": 1048000,
"maxTokens": 32000,
"cost": {
"input": 1,
"output": 4.05,
"cacheRead": 0.17,
"cacheWrite": 0
}
},
{
"id": "moonshotai/Kimi-K2.6",
"name": "Kimi K2.6",
"reasoning": true,
"input": [
"text",
"image"
],
"contextWindow": 262000,
"maxTokens": 262000,
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
}
},
{
"id": "moonshotai/Kimi-K2.7-Code",
"name": "Kimi K2.7 Code",
"reasoning": true,
"input": [
"text",
"image"
],
"contextWindow": 262000,
"maxTokens": 262000,
"cost": {
"input": 0.95,
"output": 4,
"cacheRead": 0.16,
"cacheWrite": 0
}
},
{
"id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B",
"name": "Nemotron Ultra",
"reasoning": true,
"input": [
"text"
],
"contextWindow": 202000,
"maxTokens": 202000,
"cost": {
"input": 0.6,
"output": 2.4,
"cacheRead": 0.12,
"cacheWrite": 0
}
},
{
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"reasoning": true,
"input": [
"text"
],
"contextWindow": 128000,
"maxTokens": 128000,
"cost": {
"input": 0.1,
"output": 0.5,
"cacheRead": 0,
"cacheWrite": 0
}
}
]
}
},
"discovery": {
"baseten": "refreshable"
}
},
"setup": {
"providers": [
{
"id": "baseten",
"envVars": [
"BASETEN_API_KEY"
]
}
]
},
"providerAuthChoices": [
{
"provider": "baseten",
"method": "api-key",
"choiceId": "baseten-api-key",
"appGuidedSecret": true,
"choiceLabel": "Baseten API key",
"groupId": "baseten",
"groupLabel": "Baseten",
"groupHint": "Hosted Model APIs, including Inkling",
"optionKey": "basetenApiKey",
"cliFlag": "--baseten-api-key",
"cliOption": "--baseten-api-key <key>",
"cliDescription": "Baseten API key"
}
],
"configSchema": {
"type": "object",
"additionalProperties": false,
"properties": {}
}
}