@gpuai/sdk 0.5.4 → 0.5.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.openapi-generator/FILES +56 -0
- package/README.md +50 -2
- package/dist/apis/EndpointsApi.d.ts +150 -0
- package/dist/apis/EndpointsApi.js +379 -0
- package/dist/apis/InstancesApi.d.ts +15 -0
- package/dist/apis/InstancesApi.js +45 -0
- package/dist/apis/JobsApi.d.ts +172 -0
- package/dist/apis/JobsApi.js +444 -0
- package/dist/apis/OperationsApi.d.ts +17 -0
- package/dist/apis/OperationsApi.js +48 -0
- package/dist/apis/SecretsApi.d.ts +123 -0
- package/dist/apis/SecretsApi.js +328 -0
- package/dist/apis/index.d.ts +3 -0
- package/dist/apis/index.js +3 -0
- package/dist/esm/apis/EndpointsApi.d.ts +150 -0
- package/dist/esm/apis/EndpointsApi.js +375 -0
- package/dist/esm/apis/InstancesApi.d.ts +15 -0
- package/dist/esm/apis/InstancesApi.js +45 -0
- package/dist/esm/apis/JobsApi.d.ts +172 -0
- package/dist/esm/apis/JobsApi.js +440 -0
- package/dist/esm/apis/OperationsApi.d.ts +17 -0
- package/dist/esm/apis/OperationsApi.js +48 -0
- package/dist/esm/apis/SecretsApi.d.ts +123 -0
- package/dist/esm/apis/SecretsApi.js +324 -0
- package/dist/esm/apis/index.d.ts +3 -0
- package/dist/esm/apis/index.js +3 -0
- package/dist/esm/models/DedicatedIPOffer.d.ts +98 -0
- package/dist/esm/models/DedicatedIPOffer.js +87 -0
- package/dist/esm/models/Endpoint.d.ts +147 -0
- package/dist/esm/models/Endpoint.js +121 -0
- package/dist/esm/models/EndpointCreate.d.ts +80 -0
- package/dist/esm/models/EndpointCreate.js +63 -0
- package/dist/esm/models/EndpointList.d.ts +33 -0
- package/dist/esm/models/EndpointList.js +44 -0
- package/dist/esm/models/EndpointMachine.d.ts +90 -0
- package/dist/esm/models/EndpointMachine.js +84 -0
- package/dist/esm/models/EndpointReplicaCounts.d.ts +38 -0
- package/dist/esm/models/EndpointReplicaCounts.js +47 -0
- package/dist/esm/models/Job.d.ts +352 -0
- package/dist/esm/models/Job.js +254 -0
- package/dist/esm/models/JobAttempt.d.ts +176 -0
- package/dist/esm/models/JobAttempt.js +147 -0
- package/dist/esm/models/JobCreate.d.ts +153 -0
- package/dist/esm/models/JobCreate.js +84 -0
- package/dist/esm/models/JobGpuTypes.d.ts +39 -0
- package/dist/esm/models/JobGpuTypes.js +48 -0
- package/dist/esm/models/JobGpuTypesDataInner.d.ts +58 -0
- package/dist/esm/models/JobGpuTypesDataInner.js +59 -0
- package/dist/esm/models/JobLogChunk.d.ts +50 -0
- package/dist/esm/models/JobLogChunk.js +55 -0
- package/dist/esm/models/JobLogs.d.ts +39 -0
- package/dist/esm/models/JobLogs.js +48 -0
- package/dist/esm/models/JobPage.d.ts +39 -0
- package/dist/esm/models/JobPage.js +48 -0
- package/dist/esm/models/JobSharingHint.d.ts +46 -0
- package/dist/esm/models/JobSharingHint.js +51 -0
- package/dist/esm/models/JobTelemetry.d.ts +51 -0
- package/dist/esm/models/JobTelemetry.js +56 -0
- package/dist/esm/models/JobTelemetryPoint.d.ts +56 -0
- package/dist/esm/models/JobTelemetryPoint.js +59 -0
- package/dist/esm/models/JobTrial.d.ts +79 -0
- package/dist/esm/models/JobTrial.js +73 -0
- package/dist/esm/models/Operation.d.ts +6 -0
- package/dist/esm/models/Operation.js +2 -0
- package/dist/esm/models/Secret.d.ts +62 -0
- package/dist/esm/models/Secret.js +63 -0
- package/dist/esm/models/SecretCreate.d.ts +44 -0
- package/dist/esm/models/SecretCreate.js +49 -0
- package/dist/esm/models/SecretImportItem.d.ts +38 -0
- package/dist/esm/models/SecretImportItem.js +47 -0
- package/dist/esm/models/SecretImportRequest.d.ts +39 -0
- package/dist/esm/models/SecretImportRequest.js +46 -0
- package/dist/esm/models/SecretImportResult.d.ts +44 -0
- package/dist/esm/models/SecretImportResult.js +51 -0
- package/dist/esm/models/SecretList.d.ts +33 -0
- package/dist/esm/models/SecretList.js +44 -0
- package/dist/esm/models/SecretPut.d.ts +38 -0
- package/dist/esm/models/SecretPut.js +45 -0
- package/dist/esm/models/index.d.ts +25 -0
- package/dist/esm/models/index.js +25 -0
- package/dist/esm/runtime.js +1 -1
- package/dist/models/DedicatedIPOffer.d.ts +98 -0
- package/dist/models/DedicatedIPOffer.js +94 -0
- package/dist/models/Endpoint.d.ts +147 -0
- package/dist/models/Endpoint.js +129 -0
- package/dist/models/EndpointCreate.d.ts +80 -0
- package/dist/models/EndpointCreate.js +70 -0
- package/dist/models/EndpointList.d.ts +33 -0
- package/dist/models/EndpointList.js +51 -0
- package/dist/models/EndpointMachine.d.ts +90 -0
- package/dist/models/EndpointMachine.js +92 -0
- package/dist/models/EndpointReplicaCounts.d.ts +38 -0
- package/dist/models/EndpointReplicaCounts.js +54 -0
- package/dist/models/Job.d.ts +352 -0
- package/dist/models/Job.js +262 -0
- package/dist/models/JobAttempt.d.ts +176 -0
- package/dist/models/JobAttempt.js +155 -0
- package/dist/models/JobCreate.d.ts +153 -0
- package/dist/models/JobCreate.js +92 -0
- package/dist/models/JobGpuTypes.d.ts +39 -0
- package/dist/models/JobGpuTypes.js +55 -0
- package/dist/models/JobGpuTypesDataInner.d.ts +58 -0
- package/dist/models/JobGpuTypesDataInner.js +66 -0
- package/dist/models/JobLogChunk.d.ts +50 -0
- package/dist/models/JobLogChunk.js +62 -0
- package/dist/models/JobLogs.d.ts +39 -0
- package/dist/models/JobLogs.js +55 -0
- package/dist/models/JobPage.d.ts +39 -0
- package/dist/models/JobPage.js +55 -0
- package/dist/models/JobSharingHint.d.ts +46 -0
- package/dist/models/JobSharingHint.js +58 -0
- package/dist/models/JobTelemetry.d.ts +51 -0
- package/dist/models/JobTelemetry.js +63 -0
- package/dist/models/JobTelemetryPoint.d.ts +56 -0
- package/dist/models/JobTelemetryPoint.js +66 -0
- package/dist/models/JobTrial.d.ts +79 -0
- package/dist/models/JobTrial.js +81 -0
- package/dist/models/Operation.d.ts +6 -0
- package/dist/models/Operation.js +2 -0
- package/dist/models/Secret.d.ts +62 -0
- package/dist/models/Secret.js +70 -0
- package/dist/models/SecretCreate.d.ts +44 -0
- package/dist/models/SecretCreate.js +56 -0
- package/dist/models/SecretImportItem.d.ts +38 -0
- package/dist/models/SecretImportItem.js +54 -0
- package/dist/models/SecretImportRequest.d.ts +39 -0
- package/dist/models/SecretImportRequest.js +53 -0
- package/dist/models/SecretImportResult.d.ts +44 -0
- package/dist/models/SecretImportResult.js +58 -0
- package/dist/models/SecretList.d.ts +33 -0
- package/dist/models/SecretList.js +51 -0
- package/dist/models/SecretPut.d.ts +38 -0
- package/dist/models/SecretPut.js +52 -0
- package/dist/models/index.d.ts +25 -0
- package/dist/models/index.js +25 -0
- package/dist/runtime.js +1 -1
- package/docs/DedicatedIPOffer.md +56 -0
- package/docs/Endpoint.md +68 -0
- package/docs/EndpointCreate.md +50 -0
- package/docs/EndpointList.md +34 -0
- package/docs/EndpointMachine.md +50 -0
- package/docs/EndpointReplicaCounts.md +36 -0
- package/docs/EndpointsApi.md +544 -0
- package/docs/InstancesApi.md +68 -1
- package/docs/Job.md +125 -0
- package/docs/JobAttempt.md +69 -0
- package/docs/JobCreate.md +66 -0
- package/docs/JobGpuTypes.md +36 -0
- package/docs/JobGpuTypesDataInner.md +42 -0
- package/docs/JobLogChunk.md +40 -0
- package/docs/JobLogs.md +36 -0
- package/docs/JobPage.md +36 -0
- package/docs/JobSharingHint.md +39 -0
- package/docs/JobTelemetry.md +40 -0
- package/docs/JobTelemetryPoint.md +42 -0
- package/docs/JobTrial.md +46 -0
- package/docs/JobsApi.md +609 -0
- package/docs/Operation.md +2 -0
- package/docs/OperationsApi.md +76 -0
- package/docs/Secret.md +45 -0
- package/docs/SecretCreate.md +38 -0
- package/docs/SecretImportItem.md +36 -0
- package/docs/SecretImportRequest.md +36 -0
- package/docs/SecretImportResult.md +38 -0
- package/docs/SecretList.md +34 -0
- package/docs/SecretPut.md +36 -0
- package/docs/SecretsApi.md +450 -0
- package/package.json +1 -1
- package/src/apis/EndpointsApi.ts +481 -0
- package/src/apis/InstancesApi.ts +52 -0
- package/src/apis/JobsApi.ts +551 -0
- package/src/apis/OperationsApi.ts +59 -0
- package/src/apis/SecretsApi.ts +413 -0
- package/src/apis/index.ts +3 -0
- package/src/models/DedicatedIPOffer.ts +165 -0
- package/src/models/Endpoint.ts +247 -0
- package/src/models/EndpointCreate.ts +132 -0
- package/src/models/EndpointList.ts +74 -0
- package/src/models/EndpointMachine.ts +151 -0
- package/src/models/EndpointReplicaCounts.ts +75 -0
- package/src/models/Job.ts +538 -0
- package/src/models/JobAttempt.ts +267 -0
- package/src/models/JobCreate.ts +221 -0
- package/src/models/JobGpuTypes.ts +83 -0
- package/src/models/JobGpuTypesDataInner.ts +104 -0
- package/src/models/JobLogChunk.ts +93 -0
- package/src/models/JobLogs.ts +83 -0
- package/src/models/JobPage.ts +83 -0
- package/src/models/JobSharingHint.ts +86 -0
- package/src/models/JobTelemetry.ts +101 -0
- package/src/models/JobTelemetryPoint.ts +102 -0
- package/src/models/JobTrial.ts +132 -0
- package/src/models/Operation.ts +8 -0
- package/src/models/Secret.ts +111 -0
- package/src/models/SecretCreate.ts +83 -0
- package/src/models/SecretImportItem.ts +75 -0
- package/src/models/SecretImportRequest.ts +82 -0
- package/src/models/SecretImportResult.ts +84 -0
- package/src/models/SecretList.ts +74 -0
- package/src/models/SecretPut.ts +74 -0
- package/src/models/index.ts +25 -0
- package/src/runtime.ts +1 -1
package/.openapi-generator/FILES
CHANGED
|
@@ -42,12 +42,19 @@ docs/CreateSshKeyRequest.md
|
|
|
42
42
|
docs/CreateWebhookEndpointRequest.md
|
|
43
43
|
docs/CryptoDeposit.md
|
|
44
44
|
docs/DataRetention.md
|
|
45
|
+
docs/DedicatedIPOffer.md
|
|
45
46
|
docs/DedicatedIPRequest.md
|
|
46
47
|
docs/Embedding.md
|
|
47
48
|
docs/EmbeddingsRequest.md
|
|
48
49
|
docs/EmbeddingsRequestInput.md
|
|
49
50
|
docs/EmbeddingsResponse.md
|
|
50
51
|
docs/EmbeddingsUsage.md
|
|
52
|
+
docs/Endpoint.md
|
|
53
|
+
docs/EndpointCreate.md
|
|
54
|
+
docs/EndpointList.md
|
|
55
|
+
docs/EndpointMachine.md
|
|
56
|
+
docs/EndpointReplicaCounts.md
|
|
57
|
+
docs/EndpointsApi.md
|
|
51
58
|
docs/Environments.md
|
|
52
59
|
docs/EnvironmentsApi.md
|
|
53
60
|
docs/FileObject.md
|
|
@@ -91,6 +98,19 @@ docs/InstancePage.md
|
|
|
91
98
|
docs/InstancesApi.md
|
|
92
99
|
docs/Invoice.md
|
|
93
100
|
docs/InvoiceList.md
|
|
101
|
+
docs/Job.md
|
|
102
|
+
docs/JobAttempt.md
|
|
103
|
+
docs/JobCreate.md
|
|
104
|
+
docs/JobGpuTypes.md
|
|
105
|
+
docs/JobGpuTypesDataInner.md
|
|
106
|
+
docs/JobLogChunk.md
|
|
107
|
+
docs/JobLogs.md
|
|
108
|
+
docs/JobPage.md
|
|
109
|
+
docs/JobSharingHint.md
|
|
110
|
+
docs/JobTelemetry.md
|
|
111
|
+
docs/JobTelemetryPoint.md
|
|
112
|
+
docs/JobTrial.md
|
|
113
|
+
docs/JobsApi.md
|
|
94
114
|
docs/ListCommunityMachines200Response.md
|
|
95
115
|
docs/ListDeposits200Response.md
|
|
96
116
|
docs/ListRegistryCredentials200Response.md
|
|
@@ -120,6 +140,14 @@ docs/RegistryCredential.md
|
|
|
120
140
|
docs/RegistryCredentialsApi.md
|
|
121
141
|
docs/SSHKey.md
|
|
122
142
|
docs/SSHKeyPage.md
|
|
143
|
+
docs/Secret.md
|
|
144
|
+
docs/SecretCreate.md
|
|
145
|
+
docs/SecretImportItem.md
|
|
146
|
+
docs/SecretImportRequest.md
|
|
147
|
+
docs/SecretImportResult.md
|
|
148
|
+
docs/SecretList.md
|
|
149
|
+
docs/SecretPut.md
|
|
150
|
+
docs/SecretsApi.md
|
|
123
151
|
docs/SpendingLimit.md
|
|
124
152
|
docs/SshKeysApi.md
|
|
125
153
|
docs/StreamOptions.md
|
|
@@ -153,17 +181,20 @@ package.json
|
|
|
153
181
|
src/apis/AutolaunchApi.ts
|
|
154
182
|
src/apis/BillingApi.ts
|
|
155
183
|
src/apis/CommunityApi.ts
|
|
184
|
+
src/apis/EndpointsApi.ts
|
|
156
185
|
src/apis/EnvironmentsApi.ts
|
|
157
186
|
src/apis/FineTuningApi.ts
|
|
158
187
|
src/apis/FunctionsApi.ts
|
|
159
188
|
src/apis/GpuTypesApi.ts
|
|
160
189
|
src/apis/InferenceApi.ts
|
|
161
190
|
src/apis/InstancesApi.ts
|
|
191
|
+
src/apis/JobsApi.ts
|
|
162
192
|
src/apis/MarketApi.ts
|
|
163
193
|
src/apis/MetaApi.ts
|
|
164
194
|
src/apis/OperationsApi.ts
|
|
165
195
|
src/apis/PricingApi.ts
|
|
166
196
|
src/apis/RegistryCredentialsApi.ts
|
|
197
|
+
src/apis/SecretsApi.ts
|
|
167
198
|
src/apis/SshKeysApi.ts
|
|
168
199
|
src/apis/TemplatesApi.ts
|
|
169
200
|
src/apis/UsageApi.ts
|
|
@@ -209,12 +240,18 @@ src/models/CreateSshKeyRequest.ts
|
|
|
209
240
|
src/models/CreateWebhookEndpointRequest.ts
|
|
210
241
|
src/models/CryptoDeposit.ts
|
|
211
242
|
src/models/DataRetention.ts
|
|
243
|
+
src/models/DedicatedIPOffer.ts
|
|
212
244
|
src/models/DedicatedIPRequest.ts
|
|
213
245
|
src/models/Embedding.ts
|
|
214
246
|
src/models/EmbeddingsRequest.ts
|
|
215
247
|
src/models/EmbeddingsRequestInput.ts
|
|
216
248
|
src/models/EmbeddingsResponse.ts
|
|
217
249
|
src/models/EmbeddingsUsage.ts
|
|
250
|
+
src/models/Endpoint.ts
|
|
251
|
+
src/models/EndpointCreate.ts
|
|
252
|
+
src/models/EndpointList.ts
|
|
253
|
+
src/models/EndpointMachine.ts
|
|
254
|
+
src/models/EndpointReplicaCounts.ts
|
|
218
255
|
src/models/Environments.ts
|
|
219
256
|
src/models/FileObject.ts
|
|
220
257
|
src/models/FineTuningJob.ts
|
|
@@ -252,6 +289,18 @@ src/models/InstanceGpuMemory.ts
|
|
|
252
289
|
src/models/InstancePage.ts
|
|
253
290
|
src/models/Invoice.ts
|
|
254
291
|
src/models/InvoiceList.ts
|
|
292
|
+
src/models/Job.ts
|
|
293
|
+
src/models/JobAttempt.ts
|
|
294
|
+
src/models/JobCreate.ts
|
|
295
|
+
src/models/JobGpuTypes.ts
|
|
296
|
+
src/models/JobGpuTypesDataInner.ts
|
|
297
|
+
src/models/JobLogChunk.ts
|
|
298
|
+
src/models/JobLogs.ts
|
|
299
|
+
src/models/JobPage.ts
|
|
300
|
+
src/models/JobSharingHint.ts
|
|
301
|
+
src/models/JobTelemetry.ts
|
|
302
|
+
src/models/JobTelemetryPoint.ts
|
|
303
|
+
src/models/JobTrial.ts
|
|
255
304
|
src/models/ListCommunityMachines200Response.ts
|
|
256
305
|
src/models/ListDeposits200Response.ts
|
|
257
306
|
src/models/ListRegistryCredentials200Response.ts
|
|
@@ -276,6 +325,13 @@ src/models/RegisterCommunityMachineRequest.ts
|
|
|
276
325
|
src/models/RegistryCredential.ts
|
|
277
326
|
src/models/SSHKey.ts
|
|
278
327
|
src/models/SSHKeyPage.ts
|
|
328
|
+
src/models/Secret.ts
|
|
329
|
+
src/models/SecretCreate.ts
|
|
330
|
+
src/models/SecretImportItem.ts
|
|
331
|
+
src/models/SecretImportRequest.ts
|
|
332
|
+
src/models/SecretImportResult.ts
|
|
333
|
+
src/models/SecretList.ts
|
|
334
|
+
src/models/SecretPut.ts
|
|
279
335
|
src/models/SpendingLimit.ts
|
|
280
336
|
src/models/StreamOptions.ts
|
|
281
337
|
src/models/SupplierMachineView.ts
|
package/README.md
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
# @gpuai/sdk@0.5.
|
|
1
|
+
# @gpuai/sdk@0.5.6
|
|
2
2
|
|
|
3
3
|
A TypeScript SDK client for the api.gpu.ai API.
|
|
4
4
|
|
|
@@ -77,6 +77,13 @@ All URIs are relative to *https://api.gpu.ai/v1*
|
|
|
77
77
|
*CommunityApi* | [**listCommunityMachines**](docs/CommunityApi.md#listcommunitymachines) | **GET** /community/machines | List your Community Cloud machines
|
|
78
78
|
*CommunityApi* | [**reclaimCommunityMachine**](docs/CommunityApi.md#reclaimcommunitymachine) | **POST** /community/machines/{id}/reclaim | Reclaim a spot-tier Community Cloud machine
|
|
79
79
|
*CommunityApi* | [**registerCommunityMachine**](docs/CommunityApi.md#registercommunitymachineoperation) | **POST** /community/machines | Register a Community Cloud machine
|
|
80
|
+
*EndpointsApi* | [**createEndpoint**](docs/EndpointsApi.md#createendpoint) | **POST** /endpoints | Create a model endpoint
|
|
81
|
+
*EndpointsApi* | [**createEndpointChatCompletion**](docs/EndpointsApi.md#createendpointchatcompletion) | **POST** /endpoints/{id}/openai/v1/chat/completions | Chat completion on a model endpoint (OpenAI-compatible)
|
|
82
|
+
*EndpointsApi* | [**createEndpointCompletion**](docs/EndpointsApi.md#createendpointcompletion) | **POST** /endpoints/{id}/openai/v1/completions | Text completion on a model endpoint (OpenAI-compatible)
|
|
83
|
+
*EndpointsApi* | [**deleteEndpoint**](docs/EndpointsApi.md#deleteendpoint) | **DELETE** /endpoints/{id} | Delete a model endpoint
|
|
84
|
+
*EndpointsApi* | [**getEndpoint**](docs/EndpointsApi.md#getendpoint) | **GET** /endpoints/{id} | Get a model endpoint
|
|
85
|
+
*EndpointsApi* | [**listEndpointModels**](docs/EndpointsApi.md#listendpointmodels) | **GET** /endpoints/{id}/openai/v1/models | List the model an endpoint serves (OpenAI-compatible)
|
|
86
|
+
*EndpointsApi* | [**listEndpoints**](docs/EndpointsApi.md#listendpoints) | **GET** /endpoints | List model endpoints
|
|
80
87
|
*EnvironmentsApi* | [**getEnvironments**](docs/EnvironmentsApi.md#getenvironments) | **GET** /environments | List launch environments (no auth required)
|
|
81
88
|
*FineTuningApi* | [**cancelFineTuningJob**](docs/FineTuningApi.md#cancelfinetuningjob) | **POST** /fine_tuning/jobs/{id}/cancel | Cancel a fine-tuning job (OpenAI-compatible)
|
|
82
89
|
*FineTuningApi* | [**createFile**](docs/FineTuningApi.md#createfile) | **POST** /files | Upload a fine-tuning dataset file (OpenAI-compatible)
|
|
@@ -111,18 +118,34 @@ All URIs are relative to *https://api.gpu.ai/v1*
|
|
|
111
118
|
*InferenceApi* | [**updateDataRetention**](docs/InferenceApi.md#updatedataretentionoperation) | **PUT** /organization/data-retention | Turn zero data retention on or off for the org
|
|
112
119
|
*InstancesApi* | [**createInstance**](docs/InstancesApi.md#createinstanceoperation) | **POST** /instances | Create an instance (async — returns 202 + Operation-Id header)
|
|
113
120
|
*InstancesApi* | [**deleteInstance**](docs/InstancesApi.md#deleteinstance) | **DELETE** /instances/{id} | Terminate an instance (idempotent)
|
|
121
|
+
*InstancesApi* | [**getDedicatedIpOffer**](docs/InstancesApi.md#getdedicatedipoffer) | **GET** /dedicated-ip | Get the dedicated public IP add-on offer
|
|
114
122
|
*InstancesApi* | [**getInstance**](docs/InstancesApi.md#getinstance) | **GET** /instances/{id} | Get an instance
|
|
115
123
|
*InstancesApi* | [**getInstanceGpuSuggestion**](docs/InstancesApi.md#getinstancegpusuggestion) | **GET** /instances/{id}/gpu-suggestion | Suggest a lower-priced GPU for an instance
|
|
116
124
|
*InstancesApi* | [**listInstances**](docs/InstancesApi.md#listinstances) | **GET** /instances | List instances
|
|
117
125
|
*InstancesApi* | [**updateInstance**](docs/InstancesApi.md#updateinstanceoperation) | **PATCH** /instances/{id} | Update an instance (rename only in v1)
|
|
126
|
+
*JobsApi* | [**cancelJob**](docs/JobsApi.md#canceljob) | **POST** /jobs/{id}/cancel | Cancel a job
|
|
127
|
+
*JobsApi* | [**createJob**](docs/JobsApi.md#createjob) | **POST** /jobs | Submit a job
|
|
128
|
+
*JobsApi* | [**getJob**](docs/JobsApi.md#getjob) | **GET** /jobs/{id} | Get a job
|
|
129
|
+
*JobsApi* | [**getJobLogs**](docs/JobsApi.md#getjoblogs) | **GET** /jobs/{id}/logs | Read a job\'s output
|
|
130
|
+
*JobsApi* | [**getJobTelemetry**](docs/JobsApi.md#getjobtelemetry) | **GET** /jobs/{id}/telemetry | Read a job\'s GPU memory telemetry
|
|
131
|
+
*JobsApi* | [**getJobTrial**](docs/JobsApi.md#getjobtrial) | **GET** /jobs/trial | Whether this organization\'s first jobs are free
|
|
132
|
+
*JobsApi* | [**listJobGpuTypes**](docs/JobsApi.md#listjobgputypes) | **GET** /jobs/gpu-types | List the GPU types a job can run on
|
|
133
|
+
*JobsApi* | [**listJobs**](docs/JobsApi.md#listjobs) | **GET** /jobs | List jobs
|
|
118
134
|
*MarketApi* | [**getMarketHistory**](docs/MarketApi.md#getmarkethistory) | **GET** /market-history | Get a GPU\'s price and availability over time
|
|
119
135
|
*MetaApi* | [**getHealth**](docs/MetaApi.md#gethealth) | **GET** /health | Liveness probe
|
|
120
136
|
*MetaApi* | [**getOpenApiSpec**](docs/MetaApi.md#getopenapispec) | **GET** /openapi.json | OpenAPI 3.1 specification
|
|
137
|
+
*OperationsApi* | [**cancelOperation**](docs/OperationsApi.md#canceloperation) | **POST** /operations/{id}/cancel | Cancel a launch that has not created its instance yet
|
|
121
138
|
*OperationsApi* | [**getOperation**](docs/OperationsApi.md#getoperation) | **GET** /operations/{id} | Get an async operation status
|
|
122
139
|
*PricingApi* | [**listPricing**](docs/PricingApi.md#listpricing) | **GET** /pricing | List pricing per GPU type + region (no auth required)
|
|
123
140
|
*RegistryCredentialsApi* | [**createRegistryCredential**](docs/RegistryCredentialsApi.md#createregistrycredentialoperation) | **POST** /registry-credentials | Store a registry credential
|
|
124
141
|
*RegistryCredentialsApi* | [**deleteRegistryCredential**](docs/RegistryCredentialsApi.md#deleteregistrycredential) | **DELETE** /registry-credentials/{id} | Delete a registry credential
|
|
125
142
|
*RegistryCredentialsApi* | [**listRegistryCredentials**](docs/RegistryCredentialsApi.md#listregistrycredentials) | **GET** /registry-credentials | List registry credentials
|
|
143
|
+
*SecretsApi* | [**createSecret**](docs/SecretsApi.md#createsecret) | **POST** /secrets | Create a secret
|
|
144
|
+
*SecretsApi* | [**deleteSecret**](docs/SecretsApi.md#deletesecret) | **DELETE** /secrets/{name} | Delete a secret
|
|
145
|
+
*SecretsApi* | [**getSecret**](docs/SecretsApi.md#getsecret) | **GET** /secrets/{name} | Get a secret\'s metadata
|
|
146
|
+
*SecretsApi* | [**importSecrets**](docs/SecretsApi.md#importsecrets) | **POST** /secrets/import | Import secrets
|
|
147
|
+
*SecretsApi* | [**listSecrets**](docs/SecretsApi.md#listsecrets) | **GET** /secrets | List secrets
|
|
148
|
+
*SecretsApi* | [**putSecret**](docs/SecretsApi.md#putsecret) | **PUT** /secrets/{name} | Create or replace a secret
|
|
126
149
|
*SshKeysApi* | [**createSshKey**](docs/SshKeysApi.md#createsshkeyoperation) | **POST** /ssh-keys | Create an SSH key
|
|
127
150
|
*SshKeysApi* | [**deleteSshKey**](docs/SshKeysApi.md#deletesshkey) | **DELETE** /ssh-keys/{id} | Delete an SSH key (idempotent — 404 on already-gone per D-07)
|
|
128
151
|
*SshKeysApi* | [**getSshKey**](docs/SshKeysApi.md#getsshkey) | **GET** /ssh-keys/{id} | Get an SSH key
|
|
@@ -181,12 +204,18 @@ All URIs are relative to *https://api.gpu.ai/v1*
|
|
|
181
204
|
- [CreateWebhookEndpointRequest](docs/CreateWebhookEndpointRequest.md)
|
|
182
205
|
- [CryptoDeposit](docs/CryptoDeposit.md)
|
|
183
206
|
- [DataRetention](docs/DataRetention.md)
|
|
207
|
+
- [DedicatedIPOffer](docs/DedicatedIPOffer.md)
|
|
184
208
|
- [DedicatedIPRequest](docs/DedicatedIPRequest.md)
|
|
185
209
|
- [Embedding](docs/Embedding.md)
|
|
186
210
|
- [EmbeddingsRequest](docs/EmbeddingsRequest.md)
|
|
187
211
|
- [EmbeddingsRequestInput](docs/EmbeddingsRequestInput.md)
|
|
188
212
|
- [EmbeddingsResponse](docs/EmbeddingsResponse.md)
|
|
189
213
|
- [EmbeddingsUsage](docs/EmbeddingsUsage.md)
|
|
214
|
+
- [Endpoint](docs/Endpoint.md)
|
|
215
|
+
- [EndpointCreate](docs/EndpointCreate.md)
|
|
216
|
+
- [EndpointList](docs/EndpointList.md)
|
|
217
|
+
- [EndpointMachine](docs/EndpointMachine.md)
|
|
218
|
+
- [EndpointReplicaCounts](docs/EndpointReplicaCounts.md)
|
|
190
219
|
- [Environments](docs/Environments.md)
|
|
191
220
|
- [FileObject](docs/FileObject.md)
|
|
192
221
|
- [FineTuningJob](docs/FineTuningJob.md)
|
|
@@ -224,6 +253,18 @@ All URIs are relative to *https://api.gpu.ai/v1*
|
|
|
224
253
|
- [InstancePage](docs/InstancePage.md)
|
|
225
254
|
- [Invoice](docs/Invoice.md)
|
|
226
255
|
- [InvoiceList](docs/InvoiceList.md)
|
|
256
|
+
- [Job](docs/Job.md)
|
|
257
|
+
- [JobAttempt](docs/JobAttempt.md)
|
|
258
|
+
- [JobCreate](docs/JobCreate.md)
|
|
259
|
+
- [JobGpuTypes](docs/JobGpuTypes.md)
|
|
260
|
+
- [JobGpuTypesDataInner](docs/JobGpuTypesDataInner.md)
|
|
261
|
+
- [JobLogChunk](docs/JobLogChunk.md)
|
|
262
|
+
- [JobLogs](docs/JobLogs.md)
|
|
263
|
+
- [JobPage](docs/JobPage.md)
|
|
264
|
+
- [JobSharingHint](docs/JobSharingHint.md)
|
|
265
|
+
- [JobTelemetry](docs/JobTelemetry.md)
|
|
266
|
+
- [JobTelemetryPoint](docs/JobTelemetryPoint.md)
|
|
267
|
+
- [JobTrial](docs/JobTrial.md)
|
|
227
268
|
- [ListCommunityMachines200Response](docs/ListCommunityMachines200Response.md)
|
|
228
269
|
- [ListDeposits200Response](docs/ListDeposits200Response.md)
|
|
229
270
|
- [ListRegistryCredentials200Response](docs/ListRegistryCredentials200Response.md)
|
|
@@ -248,6 +289,13 @@ All URIs are relative to *https://api.gpu.ai/v1*
|
|
|
248
289
|
- [RegistryCredential](docs/RegistryCredential.md)
|
|
249
290
|
- [SSHKey](docs/SSHKey.md)
|
|
250
291
|
- [SSHKeyPage](docs/SSHKeyPage.md)
|
|
292
|
+
- [Secret](docs/Secret.md)
|
|
293
|
+
- [SecretCreate](docs/SecretCreate.md)
|
|
294
|
+
- [SecretImportItem](docs/SecretImportItem.md)
|
|
295
|
+
- [SecretImportRequest](docs/SecretImportRequest.md)
|
|
296
|
+
- [SecretImportResult](docs/SecretImportResult.md)
|
|
297
|
+
- [SecretList](docs/SecretList.md)
|
|
298
|
+
- [SecretPut](docs/SecretPut.md)
|
|
251
299
|
- [SpendingLimit](docs/SpendingLimit.md)
|
|
252
300
|
- [StreamOptions](docs/StreamOptions.md)
|
|
253
301
|
- [SupplierMachineView](docs/SupplierMachineView.md)
|
|
@@ -290,7 +338,7 @@ and is automatically generated by the
|
|
|
290
338
|
[OpenAPI Generator](https://openapi-generator.tech) project:
|
|
291
339
|
|
|
292
340
|
- API version: `1.0.0`
|
|
293
|
-
- Package version: `0.5.
|
|
341
|
+
- Package version: `0.5.6`
|
|
294
342
|
- Generator version: `7.24.0`
|
|
295
343
|
- Build package: `org.openapitools.codegen.languages.TypeScriptFetchClientCodegen`
|
|
296
344
|
|
|
@@ -0,0 +1,150 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* GPU.ai Public Developer API
|
|
3
|
+
* Programmatic API for GPU.ai. Authenticate with API keys minted from the dashboard. See https://gpu.ai/docs for details.
|
|
4
|
+
*
|
|
5
|
+
* The version of the OpenAPI document: 1.0.0
|
|
6
|
+
* Contact: support@gpu.ai
|
|
7
|
+
*
|
|
8
|
+
* NOTE: This class is auto generated by OpenAPI Generator (https://openapi-generator.tech).
|
|
9
|
+
* https://openapi-generator.tech
|
|
10
|
+
* Do not edit the class manually.
|
|
11
|
+
*/
|
|
12
|
+
import * as runtime from '../runtime';
|
|
13
|
+
import { type ChatCompletionRequest } from '../models/ChatCompletionRequest';
|
|
14
|
+
import { type ChatCompletionResponse } from '../models/ChatCompletionResponse';
|
|
15
|
+
import { type Endpoint } from '../models/Endpoint';
|
|
16
|
+
import { type EndpointCreate } from '../models/EndpointCreate';
|
|
17
|
+
import { type EndpointList } from '../models/EndpointList';
|
|
18
|
+
export interface CreateEndpointRequest {
|
|
19
|
+
endpointCreate: EndpointCreate;
|
|
20
|
+
}
|
|
21
|
+
export interface CreateEndpointChatCompletionRequest {
|
|
22
|
+
id: string;
|
|
23
|
+
chatCompletionRequest: ChatCompletionRequest;
|
|
24
|
+
}
|
|
25
|
+
export interface CreateEndpointCompletionRequest {
|
|
26
|
+
id: string;
|
|
27
|
+
requestBody: {
|
|
28
|
+
[key: string]: any | null;
|
|
29
|
+
};
|
|
30
|
+
}
|
|
31
|
+
export interface DeleteEndpointRequest {
|
|
32
|
+
id: string;
|
|
33
|
+
}
|
|
34
|
+
export interface GetEndpointRequest {
|
|
35
|
+
id: string;
|
|
36
|
+
}
|
|
37
|
+
export interface ListEndpointModelsRequest {
|
|
38
|
+
id: string;
|
|
39
|
+
}
|
|
40
|
+
/**
|
|
41
|
+
*
|
|
42
|
+
*/
|
|
43
|
+
export declare class EndpointsApi extends runtime.BaseAPI {
|
|
44
|
+
/**
|
|
45
|
+
* Creates request options for createEndpoint without sending the request
|
|
46
|
+
*/
|
|
47
|
+
createEndpointRequestOpts(requestParameters: CreateEndpointRequest): Promise<runtime.RequestOpts>;
|
|
48
|
+
/**
|
|
49
|
+
* Creates an OpenAI-compatible endpoint serving a Hugging Face model with vLLM on the chosen GPU type. Nothing starts until the first request arrives, unless `min_replicas` keeps machines warm. Each machine is billed for the time it exists, like an instance, through the same balance. For a gated model, store a Hugging Face token as a secret and name it in `hf_token_secret`; it reaches the machines as HF_TOKEN. Returns 422 `validation_failed` for a bad field, 409 `name_taken` for a duplicate name, and 409 `limit_reached` at the per-organization cap. Requires the `functions:write` scope.
|
|
50
|
+
* Create a model endpoint
|
|
51
|
+
*/
|
|
52
|
+
createEndpointRaw(requestParameters: CreateEndpointRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<Endpoint>>;
|
|
53
|
+
/**
|
|
54
|
+
* Creates an OpenAI-compatible endpoint serving a Hugging Face model with vLLM on the chosen GPU type. Nothing starts until the first request arrives, unless `min_replicas` keeps machines warm. Each machine is billed for the time it exists, like an instance, through the same balance. For a gated model, store a Hugging Face token as a secret and name it in `hf_token_secret`; it reaches the machines as HF_TOKEN. Returns 422 `validation_failed` for a bad field, 409 `name_taken` for a duplicate name, and 409 `limit_reached` at the per-organization cap. Requires the `functions:write` scope.
|
|
55
|
+
* Create a model endpoint
|
|
56
|
+
*/
|
|
57
|
+
createEndpoint(requestParameters: CreateEndpointRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<Endpoint>;
|
|
58
|
+
/**
|
|
59
|
+
* Creates request options for createEndpointChatCompletion without sending the request
|
|
60
|
+
*/
|
|
61
|
+
createEndpointChatCompletionRequestOpts(requestParameters: CreateEndpointChatCompletionRequest): Promise<runtime.RequestOpts>;
|
|
62
|
+
/**
|
|
63
|
+
* The OpenAI chat completions route of one endpoint: point an OpenAI client\'s base_url at the endpoint\'s `url` and use a GPU.ai API key with the `functions:write` scope. The request\'s `model` is replaced with the endpoint\'s model, so any value works. Set `\"stream\": true` for Server-Sent Events, passed through as vLLM produces them. When no machine is ready the request waits while one starts (a cold start takes minutes: machine, image and model download); if none is ready in time the answer is 503 `endpoint_starting` with Retry-After. 402 `insufficient_quota` when the balance is empty. Errors use the OpenAI error envelope.
|
|
64
|
+
* Chat completion on a model endpoint (OpenAI-compatible)
|
|
65
|
+
*/
|
|
66
|
+
createEndpointChatCompletionRaw(requestParameters: CreateEndpointChatCompletionRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<ChatCompletionResponse>>;
|
|
67
|
+
/**
|
|
68
|
+
* The OpenAI chat completions route of one endpoint: point an OpenAI client\'s base_url at the endpoint\'s `url` and use a GPU.ai API key with the `functions:write` scope. The request\'s `model` is replaced with the endpoint\'s model, so any value works. Set `\"stream\": true` for Server-Sent Events, passed through as vLLM produces them. When no machine is ready the request waits while one starts (a cold start takes minutes: machine, image and model download); if none is ready in time the answer is 503 `endpoint_starting` with Retry-After. 402 `insufficient_quota` when the balance is empty. Errors use the OpenAI error envelope.
|
|
69
|
+
* Chat completion on a model endpoint (OpenAI-compatible)
|
|
70
|
+
*/
|
|
71
|
+
createEndpointChatCompletion(requestParameters: CreateEndpointChatCompletionRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<ChatCompletionResponse>;
|
|
72
|
+
/**
|
|
73
|
+
* Creates request options for createEndpointCompletion without sending the request
|
|
74
|
+
*/
|
|
75
|
+
createEndpointCompletionRequestOpts(requestParameters: CreateEndpointCompletionRequest): Promise<runtime.RequestOpts>;
|
|
76
|
+
/**
|
|
77
|
+
* The OpenAI completions route of one endpoint, with the same auth, model rewrite, streaming, cold start and error behavior as chat completions.
|
|
78
|
+
* Text completion on a model endpoint (OpenAI-compatible)
|
|
79
|
+
*/
|
|
80
|
+
createEndpointCompletionRaw(requestParameters: CreateEndpointCompletionRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<{
|
|
81
|
+
[key: string]: any;
|
|
82
|
+
}>>;
|
|
83
|
+
/**
|
|
84
|
+
* The OpenAI completions route of one endpoint, with the same auth, model rewrite, streaming, cold start and error behavior as chat completions.
|
|
85
|
+
* Text completion on a model endpoint (OpenAI-compatible)
|
|
86
|
+
*/
|
|
87
|
+
createEndpointCompletion(requestParameters: CreateEndpointCompletionRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<{
|
|
88
|
+
[key: string]: any;
|
|
89
|
+
}>;
|
|
90
|
+
/**
|
|
91
|
+
* Creates request options for deleteEndpoint without sending the request
|
|
92
|
+
*/
|
|
93
|
+
deleteEndpointRequestOpts(requestParameters: DeleteEndpointRequest): Promise<runtime.RequestOpts>;
|
|
94
|
+
/**
|
|
95
|
+
* Deletes the endpoint. Its machines are released within seconds and stop billing when terminated. Requires the `functions:write` scope.
|
|
96
|
+
* Delete a model endpoint
|
|
97
|
+
*/
|
|
98
|
+
deleteEndpointRaw(requestParameters: DeleteEndpointRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<void>>;
|
|
99
|
+
/**
|
|
100
|
+
* Deletes the endpoint. Its machines are released within seconds and stop billing when terminated. Requires the `functions:write` scope.
|
|
101
|
+
* Delete a model endpoint
|
|
102
|
+
*/
|
|
103
|
+
deleteEndpoint(requestParameters: DeleteEndpointRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<void>;
|
|
104
|
+
/**
|
|
105
|
+
* Creates request options for getEndpoint without sending the request
|
|
106
|
+
*/
|
|
107
|
+
getEndpointRequestOpts(requestParameters: GetEndpointRequest): Promise<runtime.RequestOpts>;
|
|
108
|
+
/**
|
|
109
|
+
* Returns one endpoint with its recent machines (newest first), each with its price, ready and terminated times, and why it was released. Requires the `functions:read` scope.
|
|
110
|
+
* Get a model endpoint
|
|
111
|
+
*/
|
|
112
|
+
getEndpointRaw(requestParameters: GetEndpointRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<Endpoint>>;
|
|
113
|
+
/**
|
|
114
|
+
* Returns one endpoint with its recent machines (newest first), each with its price, ready and terminated times, and why it was released. Requires the `functions:read` scope.
|
|
115
|
+
* Get a model endpoint
|
|
116
|
+
*/
|
|
117
|
+
getEndpoint(requestParameters: GetEndpointRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<Endpoint>;
|
|
118
|
+
/**
|
|
119
|
+
* Creates request options for listEndpointModels without sending the request
|
|
120
|
+
*/
|
|
121
|
+
listEndpointModelsRequestOpts(requestParameters: ListEndpointModelsRequest): Promise<runtime.RequestOpts>;
|
|
122
|
+
/**
|
|
123
|
+
* The OpenAI models route of one endpoint: the one model it serves. Can trigger a cold start like any other request.
|
|
124
|
+
* List the model an endpoint serves (OpenAI-compatible)
|
|
125
|
+
*/
|
|
126
|
+
listEndpointModelsRaw(requestParameters: ListEndpointModelsRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<{
|
|
127
|
+
[key: string]: any;
|
|
128
|
+
}>>;
|
|
129
|
+
/**
|
|
130
|
+
* The OpenAI models route of one endpoint: the one model it serves. Can trigger a cold start like any other request.
|
|
131
|
+
* List the model an endpoint serves (OpenAI-compatible)
|
|
132
|
+
*/
|
|
133
|
+
listEndpointModels(requestParameters: ListEndpointModelsRequest, initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<{
|
|
134
|
+
[key: string]: any;
|
|
135
|
+
}>;
|
|
136
|
+
/**
|
|
137
|
+
* Creates request options for listEndpoints without sending the request
|
|
138
|
+
*/
|
|
139
|
+
listEndpointsRequestOpts(): Promise<runtime.RequestOpts>;
|
|
140
|
+
/**
|
|
141
|
+
* Lists the organization\'s live model endpoints with their status, URL and machine counts. Requires the `functions:read` scope.
|
|
142
|
+
* List model endpoints
|
|
143
|
+
*/
|
|
144
|
+
listEndpointsRaw(initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<runtime.ApiResponse<EndpointList>>;
|
|
145
|
+
/**
|
|
146
|
+
* Lists the organization\'s live model endpoints with their status, URL and machine counts. Requires the `functions:read` scope.
|
|
147
|
+
* List model endpoints
|
|
148
|
+
*/
|
|
149
|
+
listEndpoints(initOverrides?: RequestInit | runtime.InitOverrideFunction): Promise<EndpointList>;
|
|
150
|
+
}
|