omnigateway 0.12.8 → 0.12.9

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.
Files changed (3) hide show
  1. package/bin/omni.js +28 -8
  2. package/gateway.js +28 -8
  3. package/package.json +1 -1
package/bin/omni.js CHANGED
@@ -24692,7 +24692,7 @@ async function readRequestBody(store, requestId) {
24692
24692
  }
24693
24693
  // packages/providers/src/anthropic/models.ts
24694
24694
  var ANTHROPIC_MODELS = {
24695
- defaultModel: "claude-opus-5",
24695
+ defaultModel: "claude-opus-5-5",
24696
24696
  authTypes: ["oauth", "apiKey"],
24697
24697
  models: [
24698
24698
  {
@@ -24701,6 +24701,12 @@ var ANTHROPIC_MODELS = {
24701
24701
  pricing: { input: 10, output: 50, cacheRead: 0.25, cacheWrite5m: 12.5, cacheWrite1h: 20 },
24702
24702
  limits: { contextWindow: 1e6, maxOutputTokens: 128000 }
24703
24703
  },
24704
+ {
24705
+ id: "claude-opus-5-5",
24706
+ label: "Claude Opus 5.5",
24707
+ pricing: { input: 4, output: 20, cacheRead: 0.2, cacheWrite5m: 5, cacheWrite1h: 8 },
24708
+ limits: { contextWindow: 1e6, maxOutputTokens: 128000 }
24709
+ },
24704
24710
  {
24705
24711
  id: "claude-fable-5",
24706
24712
  label: "Claude Fable 5",
@@ -25284,41 +25290,55 @@ var museDescriptor = {
25284
25290
 
25285
25291
  // packages/providers/src/openai/models.ts
25286
25292
  var OPENAI_MODELS = {
25287
- defaultModel: "gpt-5.6",
25293
+ defaultModel: "gpt-6-sol",
25288
25294
  authTypes: ["oauth", "apiKey"],
25289
25295
  models: [
25290
25296
  {
25291
25297
  id: "gpt-6-astra",
25292
25298
  label: "GPT-6 Astra",
25293
- pricing: { input: 10, output: 50, cacheRead: 1, cacheWrite5m: 0, cacheWrite1h: 0 },
25299
+ pricing: { input: 10, output: 50, cacheRead: 1, cacheWrite5m: 12.5, cacheWrite1h: 0 },
25300
+ limits: { contextWindow: 922000, maxOutputTokens: 128000 },
25301
+ oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
25302
+ },
25303
+ {
25304
+ id: "gpt-6-sol",
25305
+ label: "GPT-6 Sol",
25306
+ pricing: { input: 2, output: 10, cacheRead: 0.2, cacheWrite5m: 2.5, cacheWrite1h: 0 },
25307
+ limits: { contextWindow: 922000, maxOutputTokens: 128000 },
25308
+ oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
25309
+ },
25310
+ {
25311
+ id: "gpt-6-luna",
25312
+ label: "GPT-6 Luna",
25313
+ pricing: { input: 0.1, output: 0.5, cacheRead: 0.01, cacheWrite5m: 0.125, cacheWrite1h: 0 },
25294
25314
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
25295
25315
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
25296
25316
  },
25297
25317
  {
25298
25318
  id: "gpt-5.6",
25299
25319
  label: "GPT-5.6 \u2014 routes to Sol",
25300
- pricing: { input: 4, output: 20, cacheRead: 0.4, cacheWrite5m: 0, cacheWrite1h: 0 },
25320
+ pricing: { input: 4, output: 20, cacheRead: 0.4, cacheWrite5m: 5, cacheWrite1h: 0 },
25301
25321
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
25302
25322
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
25303
25323
  },
25304
25324
  {
25305
25325
  id: "gpt-5.6-sol",
25306
25326
  label: "GPT-5.6 Sol",
25307
- pricing: { input: 4, output: 20, cacheRead: 0.4, cacheWrite5m: 0, cacheWrite1h: 0 },
25327
+ pricing: { input: 4, output: 20, cacheRead: 0.4, cacheWrite5m: 5, cacheWrite1h: 0 },
25308
25328
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
25309
25329
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
25310
25330
  },
25311
25331
  {
25312
25332
  id: "gpt-5.6-terra",
25313
25333
  label: "GPT-5.6 Terra",
25314
- pricing: { input: 2, output: 12, cacheRead: 0.2, cacheWrite5m: 0, cacheWrite1h: 0 },
25334
+ pricing: { input: 2, output: 12, cacheRead: 0.2, cacheWrite5m: 2.5, cacheWrite1h: 0 },
25315
25335
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
25316
25336
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
25317
25337
  },
25318
25338
  {
25319
25339
  id: "gpt-5.6-luna",
25320
25340
  label: "GPT-5.6 Luna",
25321
- pricing: { input: 0.2, output: 1.2, cacheRead: 0.02, cacheWrite5m: 0, cacheWrite1h: 0 },
25341
+ pricing: { input: 0.2, output: 1.2, cacheRead: 0.02, cacheWrite5m: 0.25, cacheWrite1h: 0 },
25322
25342
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
25323
25343
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
25324
25344
  }
@@ -37899,7 +37919,7 @@ function createServiceDeps(input2) {
37899
37919
  }
37900
37920
 
37901
37921
  // apps/cli/src/version.ts
37902
- var VERSION = "0.12.8";
37922
+ var VERSION = "0.12.9";
37903
37923
 
37904
37924
  // apps/cli/src/commands/service.ts
37905
37925
  function gatewayArgv(root) {
package/gateway.js CHANGED
@@ -30130,7 +30130,7 @@ async function readRequestBody(store, requestId) {
30130
30130
  }
30131
30131
  // packages/providers/src/anthropic/models.ts
30132
30132
  var ANTHROPIC_MODELS = {
30133
- defaultModel: "claude-opus-5",
30133
+ defaultModel: "claude-opus-5-5",
30134
30134
  authTypes: ["oauth", "apiKey"],
30135
30135
  models: [
30136
30136
  {
@@ -30139,6 +30139,12 @@ var ANTHROPIC_MODELS = {
30139
30139
  pricing: { input: 10, output: 50, cacheRead: 0.25, cacheWrite5m: 12.5, cacheWrite1h: 20 },
30140
30140
  limits: { contextWindow: 1e6, maxOutputTokens: 128000 }
30141
30141
  },
30142
+ {
30143
+ id: "claude-opus-5-5",
30144
+ label: "Claude Opus 5.5",
30145
+ pricing: { input: 4, output: 20, cacheRead: 0.2, cacheWrite5m: 5, cacheWrite1h: 8 },
30146
+ limits: { contextWindow: 1e6, maxOutputTokens: 128000 }
30147
+ },
30142
30148
  {
30143
30149
  id: "claude-fable-5",
30144
30150
  label: "Claude Fable 5",
@@ -30722,41 +30728,55 @@ var museDescriptor = {
30722
30728
 
30723
30729
  // packages/providers/src/openai/models.ts
30724
30730
  var OPENAI_MODELS = {
30725
- defaultModel: "gpt-5.6",
30731
+ defaultModel: "gpt-6-sol",
30726
30732
  authTypes: ["oauth", "apiKey"],
30727
30733
  models: [
30728
30734
  {
30729
30735
  id: "gpt-6-astra",
30730
30736
  label: "GPT-6 Astra",
30731
- pricing: { input: 10, output: 50, cacheRead: 1, cacheWrite5m: 0, cacheWrite1h: 0 },
30737
+ pricing: { input: 10, output: 50, cacheRead: 1, cacheWrite5m: 12.5, cacheWrite1h: 0 },
30738
+ limits: { contextWindow: 922000, maxOutputTokens: 128000 },
30739
+ oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
30740
+ },
30741
+ {
30742
+ id: "gpt-6-sol",
30743
+ label: "GPT-6 Sol",
30744
+ pricing: { input: 2, output: 10, cacheRead: 0.2, cacheWrite5m: 2.5, cacheWrite1h: 0 },
30745
+ limits: { contextWindow: 922000, maxOutputTokens: 128000 },
30746
+ oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
30747
+ },
30748
+ {
30749
+ id: "gpt-6-luna",
30750
+ label: "GPT-6 Luna",
30751
+ pricing: { input: 0.1, output: 0.5, cacheRead: 0.01, cacheWrite5m: 0.125, cacheWrite1h: 0 },
30732
30752
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
30733
30753
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
30734
30754
  },
30735
30755
  {
30736
30756
  id: "gpt-5.6",
30737
30757
  label: "GPT-5.6 \u2014 routes to Sol",
30738
- pricing: { input: 4, output: 20, cacheRead: 0.4, cacheWrite5m: 0, cacheWrite1h: 0 },
30758
+ pricing: { input: 4, output: 20, cacheRead: 0.4, cacheWrite5m: 5, cacheWrite1h: 0 },
30739
30759
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
30740
30760
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
30741
30761
  },
30742
30762
  {
30743
30763
  id: "gpt-5.6-sol",
30744
30764
  label: "GPT-5.6 Sol",
30745
- pricing: { input: 4, output: 20, cacheRead: 0.4, cacheWrite5m: 0, cacheWrite1h: 0 },
30765
+ pricing: { input: 4, output: 20, cacheRead: 0.4, cacheWrite5m: 5, cacheWrite1h: 0 },
30746
30766
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
30747
30767
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
30748
30768
  },
30749
30769
  {
30750
30770
  id: "gpt-5.6-terra",
30751
30771
  label: "GPT-5.6 Terra",
30752
- pricing: { input: 2, output: 12, cacheRead: 0.2, cacheWrite5m: 0, cacheWrite1h: 0 },
30772
+ pricing: { input: 2, output: 12, cacheRead: 0.2, cacheWrite5m: 2.5, cacheWrite1h: 0 },
30753
30773
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
30754
30774
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
30755
30775
  },
30756
30776
  {
30757
30777
  id: "gpt-5.6-luna",
30758
30778
  label: "GPT-5.6 Luna",
30759
- pricing: { input: 0.2, output: 1.2, cacheRead: 0.02, cacheWrite5m: 0, cacheWrite1h: 0 },
30779
+ pricing: { input: 0.2, output: 1.2, cacheRead: 0.02, cacheWrite5m: 0.25, cacheWrite1h: 0 },
30760
30780
  limits: { contextWindow: 922000, maxOutputTokens: 128000 },
30761
30781
  oauthLimits: { contextWindow: 272000, maxOutputTokens: 128000 }
30762
30782
  }
@@ -62759,7 +62779,7 @@ function createRing(limits = DEFAULT_RING_LIMITS) {
62759
62779
  }
62760
62780
 
62761
62781
  // apps/gateway/src/version.ts
62762
- var VERSION = "0.12.8";
62782
+ var VERSION = "0.12.9";
62763
62783
 
62764
62784
  // apps/gateway/src/app.ts
62765
62785
  var ADMIN_SESSION_TTL_MS = 12 * 60 * 60 * 1000;
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "omnigateway",
3
- "version": "0.12.8",
3
+ "version": "0.12.9",
4
4
  "description": "Self-hosted AI gateway with Anthropic- and OpenAI-compatible APIs, an admin console, and a CLI",
5
5
  "license": "MIT",
6
6
  "author": "Harismawan <mail@harismawan.com>",