@elyracode/ai 0.9.24 → 0.9.26

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.
@@ -1417,10 +1417,10 @@ export const MODELS = {
1417
1417
  reasoning: true,
1418
1418
  input: ["text", "image"],
1419
1419
  cost: {
1420
- input: 1,
1421
- output: 6,
1422
- cacheRead: 0.1,
1423
- cacheWrite: 1.25,
1420
+ input: 0.22,
1421
+ output: 1.32,
1422
+ cacheRead: 0.022,
1423
+ cacheWrite: 0.275,
1424
1424
  },
1425
1425
  contextWindow: 272000,
1426
1426
  maxTokens: 128000,
@@ -1434,10 +1434,10 @@ export const MODELS = {
1434
1434
  reasoning: true,
1435
1435
  input: ["text", "image"],
1436
1436
  cost: {
1437
- input: 5,
1438
- output: 30,
1439
- cacheRead: 0.5,
1440
- cacheWrite: 6.25,
1437
+ input: 5.5,
1438
+ output: 33,
1439
+ cacheRead: 0.55,
1440
+ cacheWrite: 6.88,
1441
1441
  },
1442
1442
  contextWindow: 272000,
1443
1443
  maxTokens: 128000,
@@ -1451,10 +1451,10 @@ export const MODELS = {
1451
1451
  reasoning: true,
1452
1452
  input: ["text", "image"],
1453
1453
  cost: {
1454
- input: 2.5,
1455
- output: 15,
1456
- cacheRead: 0.25,
1457
- cacheWrite: 3.125,
1454
+ input: 2.2,
1455
+ output: 13.2,
1456
+ cacheRead: 0.22,
1457
+ cacheWrite: 2.75,
1458
1458
  },
1459
1459
  contextWindow: 272000,
1460
1460
  maxTokens: 128000,
@@ -2092,42 +2092,6 @@ export const MODELS = {
2092
2092
  contextWindow: 200000,
2093
2093
  maxTokens: 64000,
2094
2094
  },
2095
- "claude-opus-4-1": {
2096
- id: "claude-opus-4-1",
2097
- name: "Claude Opus 4.1 (latest)",
2098
- api: "anthropic-messages",
2099
- provider: "anthropic",
2100
- baseUrl: "https://api.anthropic.com",
2101
- reasoning: true,
2102
- thinkingType: "budget",
2103
- input: ["text", "image"],
2104
- cost: {
2105
- input: 15,
2106
- output: 75,
2107
- cacheRead: 1.5,
2108
- cacheWrite: 18.75,
2109
- },
2110
- contextWindow: 200000,
2111
- maxTokens: 32000,
2112
- },
2113
- "claude-opus-4-1-20250805": {
2114
- id: "claude-opus-4-1-20250805",
2115
- name: "Claude Opus 4.1",
2116
- api: "anthropic-messages",
2117
- provider: "anthropic",
2118
- baseUrl: "https://api.anthropic.com",
2119
- reasoning: true,
2120
- thinkingType: "budget",
2121
- input: ["text", "image"],
2122
- cost: {
2123
- input: 15,
2124
- output: 75,
2125
- cacheRead: 1.5,
2126
- cacheWrite: 18.75,
2127
- },
2128
- contextWindow: 200000,
2129
- maxTokens: 32000,
2130
- },
2131
2095
  "claude-opus-4-5": {
2132
2096
  id: "claude-opus-4-5",
2133
2097
  name: "Claude Opus 4.5 (latest)",
@@ -2803,10 +2767,10 @@ export const MODELS = {
2803
2767
  thinkingLevelMap: { "off": null },
2804
2768
  input: ["text", "image"],
2805
2769
  cost: {
2806
- input: 1,
2807
- output: 6,
2808
- cacheRead: 0.1,
2809
- cacheWrite: 1.25,
2770
+ input: 0.2,
2771
+ output: 1.2,
2772
+ cacheRead: 0.02,
2773
+ cacheWrite: 0.25,
2810
2774
  },
2811
2775
  contextWindow: 1050000,
2812
2776
  maxTokens: 128000,
@@ -2839,10 +2803,10 @@ export const MODELS = {
2839
2803
  thinkingLevelMap: { "off": null },
2840
2804
  input: ["text", "image"],
2841
2805
  cost: {
2842
- input: 2.5,
2843
- output: 15,
2844
- cacheRead: 0.25,
2845
- cacheWrite: 3.125,
2806
+ input: 2,
2807
+ output: 12,
2808
+ cacheRead: 0.2,
2809
+ cacheWrite: 2.5,
2846
2810
  },
2847
2811
  contextWindow: 1050000,
2848
2812
  maxTokens: 128000,
@@ -3229,6 +3193,23 @@ export const MODELS = {
3229
3193
  contextWindow: 1000000,
3230
3194
  maxTokens: 128000,
3231
3195
  },
3196
+ "claude-opus-5": {
3197
+ id: "claude-opus-5",
3198
+ name: "Claude Opus 5",
3199
+ api: "anthropic-messages",
3200
+ provider: "cloudflare-ai-gateway",
3201
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
3202
+ reasoning: true,
3203
+ input: ["text", "image"],
3204
+ cost: {
3205
+ input: 5,
3206
+ output: 25,
3207
+ cacheRead: 0.5,
3208
+ cacheWrite: 6.25,
3209
+ },
3210
+ contextWindow: 1000000,
3211
+ maxTokens: 128000,
3212
+ },
3232
3213
  "claude-sonnet-4": {
3233
3214
  id: "claude-sonnet-4",
3234
3215
  name: "Claude Sonnet 4 (latest)",
@@ -3998,39 +3979,39 @@ export const MODELS = {
3998
3979
  contextWindow: 1000000,
3999
3980
  maxTokens: 384000,
4000
3981
  },
4001
- "accounts/fireworks/models/deepseek-v4-pro": {
4002
- id: "accounts/fireworks/models/deepseek-v4-pro",
4003
- name: "DeepSeek V4 Pro",
3982
+ "accounts/fireworks/models/deepseek-v4-flash-0731": {
3983
+ id: "accounts/fireworks/models/deepseek-v4-flash-0731",
3984
+ name: "DeepSeek V4 Flash 0731",
4004
3985
  api: "anthropic-messages",
4005
3986
  provider: "fireworks",
4006
3987
  baseUrl: "https://api.fireworks.ai/inference",
4007
3988
  reasoning: true,
4008
3989
  input: ["text"],
4009
3990
  cost: {
4010
- input: 1.74,
4011
- output: 3.48,
4012
- cacheRead: 0.145,
3991
+ input: 0.14,
3992
+ output: 0.28,
3993
+ cacheRead: 0.028,
4013
3994
  cacheWrite: 0,
4014
3995
  },
4015
3996
  contextWindow: 1000000,
4016
3997
  maxTokens: 384000,
4017
3998
  },
4018
- "accounts/fireworks/models/glm-5p1": {
4019
- id: "accounts/fireworks/models/glm-5p1",
4020
- name: "GLM 5.1",
3999
+ "accounts/fireworks/models/deepseek-v4-pro": {
4000
+ id: "accounts/fireworks/models/deepseek-v4-pro",
4001
+ name: "DeepSeek V4 Pro",
4021
4002
  api: "anthropic-messages",
4022
4003
  provider: "fireworks",
4023
4004
  baseUrl: "https://api.fireworks.ai/inference",
4024
4005
  reasoning: true,
4025
4006
  input: ["text"],
4026
4007
  cost: {
4027
- input: 1.4,
4028
- output: 4.4,
4029
- cacheRead: 0.26,
4008
+ input: 1.74,
4009
+ output: 3.48,
4010
+ cacheRead: 0.145,
4030
4011
  cacheWrite: 0,
4031
4012
  },
4032
- contextWindow: 202800,
4033
- maxTokens: 131072,
4013
+ contextWindow: 1000000,
4014
+ maxTokens: 384000,
4034
4015
  },
4035
4016
  "accounts/fireworks/models/glm-5p2": {
4036
4017
  id: "accounts/fireworks/models/glm-5p2",
@@ -4117,6 +4098,23 @@ export const MODELS = {
4117
4098
  contextWindow: 262000,
4118
4099
  maxTokens: 262000,
4119
4100
  },
4101
+ "accounts/fireworks/models/kimi-k3": {
4102
+ id: "accounts/fireworks/models/kimi-k3",
4103
+ name: "Kimi K3",
4104
+ api: "anthropic-messages",
4105
+ provider: "fireworks",
4106
+ baseUrl: "https://api.fireworks.ai/inference",
4107
+ reasoning: true,
4108
+ input: ["text", "image"],
4109
+ cost: {
4110
+ input: 3,
4111
+ output: 15,
4112
+ cacheRead: 0.3,
4113
+ cacheWrite: 0,
4114
+ },
4115
+ contextWindow: 1048576,
4116
+ maxTokens: 131072,
4117
+ },
4120
4118
  "accounts/fireworks/models/minimax-m2p7": {
4121
4119
  id: "accounts/fireworks/models/minimax-m2p7",
4122
4120
  name: "MiniMax-M2.7",
@@ -4168,23 +4166,6 @@ export const MODELS = {
4168
4166
  contextWindow: 262144,
4169
4167
  maxTokens: 65536,
4170
4168
  },
4171
- "accounts/fireworks/routers/glm-5p1-fast": {
4172
- id: "accounts/fireworks/routers/glm-5p1-fast",
4173
- name: "GLM 5.1 Fast",
4174
- api: "anthropic-messages",
4175
- provider: "fireworks",
4176
- baseUrl: "https://api.fireworks.ai/inference",
4177
- reasoning: true,
4178
- input: ["text"],
4179
- cost: {
4180
- input: 2.8,
4181
- output: 8.8,
4182
- cacheRead: 0.52,
4183
- cacheWrite: 0,
4184
- },
4185
- contextWindow: 202800,
4186
- maxTokens: 131072,
4187
- },
4188
4169
  "accounts/fireworks/routers/glm-5p2-fast": {
4189
4170
  id: "accounts/fireworks/routers/glm-5p2-fast",
4190
4171
  name: "GLM 5.2 Fast",
@@ -4253,6 +4234,23 @@ export const MODELS = {
4253
4234
  contextWindow: 262000,
4254
4235
  maxTokens: 262000,
4255
4236
  },
4237
+ "accounts/fireworks/routers/kimi-k3-fast": {
4238
+ id: "accounts/fireworks/routers/kimi-k3-fast",
4239
+ name: "Kimi K3 Fast",
4240
+ api: "anthropic-messages",
4241
+ provider: "fireworks",
4242
+ baseUrl: "https://api.fireworks.ai/inference",
4243
+ reasoning: true,
4244
+ input: ["text", "image"],
4245
+ cost: {
4246
+ input: 4.5,
4247
+ output: 22.5,
4248
+ cacheRead: 0.45,
4249
+ cacheWrite: 0,
4250
+ },
4251
+ contextWindow: 1048576,
4252
+ maxTokens: 131072,
4253
+ },
4256
4254
  },
4257
4255
  "github-copilot": {
4258
4256
  "claude-fable-5": {
@@ -4369,6 +4367,25 @@ export const MODELS = {
4369
4367
  contextWindow: 200000,
4370
4368
  maxTokens: 64000,
4371
4369
  },
4370
+ "claude-opus-5": {
4371
+ id: "claude-opus-5",
4372
+ name: "Claude Opus 5",
4373
+ api: "openai-completions",
4374
+ provider: "github-copilot",
4375
+ baseUrl: "https://api.individual.githubcopilot.com",
4376
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4377
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4378
+ reasoning: true,
4379
+ input: ["text", "image"],
4380
+ cost: {
4381
+ input: 5,
4382
+ output: 25,
4383
+ cacheRead: 0.5,
4384
+ cacheWrite: 6.25,
4385
+ },
4386
+ contextWindow: 1000000,
4387
+ maxTokens: 64000,
4388
+ },
4372
4389
  "claude-sonnet-4": {
4373
4390
  id: "claude-sonnet-4",
4374
4391
  name: "Claude Sonnet 4 (latest)",
@@ -4444,44 +4461,6 @@ export const MODELS = {
4444
4461
  contextWindow: 1000000,
4445
4462
  maxTokens: 128000,
4446
4463
  },
4447
- "gemini-2.5-pro": {
4448
- id: "gemini-2.5-pro",
4449
- name: "Gemini 2.5 Pro",
4450
- api: "openai-completions",
4451
- provider: "github-copilot",
4452
- baseUrl: "https://api.individual.githubcopilot.com",
4453
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4454
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4455
- reasoning: true,
4456
- input: ["text", "image"],
4457
- cost: {
4458
- input: 1.25,
4459
- output: 10,
4460
- cacheRead: 0.125,
4461
- cacheWrite: 0,
4462
- },
4463
- contextWindow: 128000,
4464
- maxTokens: 64000,
4465
- },
4466
- "gemini-3-flash-preview": {
4467
- id: "gemini-3-flash-preview",
4468
- name: "Gemini 3 Flash Preview",
4469
- api: "openai-completions",
4470
- provider: "github-copilot",
4471
- baseUrl: "https://api.individual.githubcopilot.com",
4472
- headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4473
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4474
- reasoning: true,
4475
- input: ["text", "image"],
4476
- cost: {
4477
- input: 0.5,
4478
- output: 3,
4479
- cacheRead: 0.05,
4480
- cacheWrite: 0,
4481
- },
4482
- contextWindow: 128000,
4483
- maxTokens: 64000,
4484
- },
4485
4464
  "gemini-3.1-pro-preview": {
4486
4465
  id: "gemini-3.1-pro-preview",
4487
4466
  name: "Gemini 3.1 Pro Preview",
@@ -4520,6 +4499,25 @@ export const MODELS = {
4520
4499
  contextWindow: 200000,
4521
4500
  maxTokens: 64000,
4522
4501
  },
4502
+ "gemini-3.6-flash": {
4503
+ id: "gemini-3.6-flash",
4504
+ name: "Gemini 3.6 Flash",
4505
+ api: "openai-completions",
4506
+ provider: "github-copilot",
4507
+ baseUrl: "https://api.individual.githubcopilot.com",
4508
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4509
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4510
+ reasoning: true,
4511
+ input: ["text", "image"],
4512
+ cost: {
4513
+ input: 1.5,
4514
+ output: 7.5,
4515
+ cacheRead: 0.15,
4516
+ cacheWrite: 0,
4517
+ },
4518
+ contextWindow: 1000000,
4519
+ maxTokens: 64000,
4520
+ },
4523
4521
  "gpt-4.1": {
4524
4522
  id: "gpt-4.1",
4525
4523
  name: "GPT-4.1",
@@ -4702,10 +4700,10 @@ export const MODELS = {
4702
4700
  thinkingLevelMap: { "off": null },
4703
4701
  input: ["text", "image"],
4704
4702
  cost: {
4705
- input: 1,
4706
- output: 6,
4707
- cacheRead: 0.1,
4708
- cacheWrite: 1.25,
4703
+ input: 0.2,
4704
+ output: 1.2,
4705
+ cacheRead: 0.02,
4706
+ cacheWrite: 0,
4709
4707
  },
4710
4708
  contextWindow: 1050000,
4711
4709
  maxTokens: 128000,
@@ -4740,17 +4738,17 @@ export const MODELS = {
4740
4738
  thinkingLevelMap: { "off": null },
4741
4739
  input: ["text", "image"],
4742
4740
  cost: {
4743
- input: 2.5,
4744
- output: 15,
4745
- cacheRead: 0.25,
4746
- cacheWrite: 3.125,
4741
+ input: 2,
4742
+ output: 12,
4743
+ cacheRead: 0.2,
4744
+ cacheWrite: 0,
4747
4745
  },
4748
4746
  contextWindow: 1050000,
4749
4747
  maxTokens: 128000,
4750
4748
  },
4751
- "kimi-k2.7-code": {
4752
- id: "kimi-k2.7-code",
4753
- name: "Kimi K2.7 Code",
4749
+ "grok-4.5": {
4750
+ id: "grok-4.5",
4751
+ name: "Grok 4.5",
4754
4752
  api: "openai-completions",
4755
4753
  provider: "github-copilot",
4756
4754
  baseUrl: "https://api.individual.githubcopilot.com",
@@ -4759,16 +4757,54 @@ export const MODELS = {
4759
4757
  reasoning: true,
4760
4758
  input: ["text", "image"],
4761
4759
  cost: {
4762
- input: 0.95,
4763
- output: 4,
4764
- cacheRead: 0.19,
4760
+ input: 2,
4761
+ output: 6,
4762
+ cacheRead: 0.5,
4765
4763
  cacheWrite: 0,
4766
4764
  },
4767
- contextWindow: 256000,
4768
- maxTokens: 32000,
4765
+ contextWindow: 500000,
4766
+ maxTokens: 128000,
4769
4767
  },
4770
- "mai-code-1-flash-picker": {
4771
- id: "mai-code-1-flash-picker",
4768
+ "kimi-k2.7-code": {
4769
+ id: "kimi-k2.7-code",
4770
+ name: "Kimi K2.7 Code",
4771
+ api: "openai-completions",
4772
+ provider: "github-copilot",
4773
+ baseUrl: "https://api.individual.githubcopilot.com",
4774
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4775
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4776
+ reasoning: true,
4777
+ input: ["text", "image"],
4778
+ cost: {
4779
+ input: 0.95,
4780
+ output: 4,
4781
+ cacheRead: 0.19,
4782
+ cacheWrite: 0,
4783
+ },
4784
+ contextWindow: 256000,
4785
+ maxTokens: 32000,
4786
+ },
4787
+ "kimi-k3": {
4788
+ id: "kimi-k3",
4789
+ name: "Kimi K3",
4790
+ api: "openai-completions",
4791
+ provider: "github-copilot",
4792
+ baseUrl: "https://api.individual.githubcopilot.com",
4793
+ headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
4794
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4795
+ reasoning: true,
4796
+ input: ["text", "image"],
4797
+ cost: {
4798
+ input: 0.95,
4799
+ output: 4,
4800
+ cacheRead: 0.19,
4801
+ cacheWrite: 0,
4802
+ },
4803
+ contextWindow: 1048576,
4804
+ maxTokens: 131072,
4805
+ },
4806
+ "mai-code-1-flash-picker": {
4807
+ id: "mai-code-1-flash-picker",
4772
4808
  name: "MAI-Code-1-Flash",
4773
4809
  api: "openai-completions",
4774
4810
  provider: "github-copilot",
@@ -5472,23 +5508,6 @@ export const MODELS = {
5472
5508
  contextWindow: 131072,
5473
5509
  maxTokens: 32768,
5474
5510
  },
5475
- "meta-llama/llama-4-scout-17b-16e-instruct": {
5476
- id: "meta-llama/llama-4-scout-17b-16e-instruct",
5477
- name: "Llama 4 Scout 17B 16E",
5478
- api: "openai-completions",
5479
- provider: "groq",
5480
- baseUrl: "https://api.groq.com/openai/v1",
5481
- reasoning: false,
5482
- input: ["text", "image"],
5483
- cost: {
5484
- input: 0.11,
5485
- output: 0.34,
5486
- cacheRead: 0,
5487
- cacheWrite: 0,
5488
- },
5489
- contextWindow: 131072,
5490
- maxTokens: 8192,
5491
- },
5492
5511
  "openai/gpt-oss-120b": {
5493
5512
  id: "openai/gpt-oss-120b",
5494
5513
  name: "GPT OSS 120B",
@@ -5540,23 +5559,22 @@ export const MODELS = {
5540
5559
  contextWindow: 131072,
5541
5560
  maxTokens: 65536,
5542
5561
  },
5543
- "qwen/qwen3-32b": {
5544
- id: "qwen/qwen3-32b",
5545
- name: "Qwen3-32B",
5562
+ "qwen/qwen3.6-27b": {
5563
+ id: "qwen/qwen3.6-27b",
5564
+ name: "Qwen3.6 27B",
5546
5565
  api: "openai-completions",
5547
5566
  provider: "groq",
5548
5567
  baseUrl: "https://api.groq.com/openai/v1",
5549
5568
  reasoning: true,
5550
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "default" },
5551
- input: ["text"],
5569
+ input: ["text", "image"],
5552
5570
  cost: {
5553
- input: 0.29,
5554
- output: 0.59,
5555
- cacheRead: 0,
5571
+ input: 0.6,
5572
+ output: 3,
5573
+ cacheRead: 0.3,
5556
5574
  cacheWrite: 0,
5557
5575
  },
5558
5576
  contextWindow: 131072,
5559
- maxTokens: 40960,
5577
+ maxTokens: 16384,
5560
5578
  },
5561
5579
  },
5562
5580
  "huggingface": {
@@ -5668,6 +5686,24 @@ export const MODELS = {
5668
5686
  contextWindow: 40960,
5669
5687
  maxTokens: 16384,
5670
5688
  },
5689
+ "Qwen/Qwen3-235B-A22B-Instruct-2507": {
5690
+ id: "Qwen/Qwen3-235B-A22B-Instruct-2507",
5691
+ name: "Qwen3 235B-A22B Instruct 2507",
5692
+ api: "openai-completions",
5693
+ provider: "huggingface",
5694
+ baseUrl: "https://router.huggingface.co/v1",
5695
+ compat: { "supportsDeveloperRole": false },
5696
+ reasoning: false,
5697
+ input: ["text"],
5698
+ cost: {
5699
+ input: 0.855,
5700
+ output: 2.565,
5701
+ cacheRead: 0,
5702
+ cacheWrite: 0,
5703
+ },
5704
+ contextWindow: 262144,
5705
+ maxTokens: 16384,
5706
+ },
5671
5707
  "Qwen/Qwen3-235B-A22B-Thinking-2507": {
5672
5708
  id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
5673
5709
  name: "Qwen3-235B-A22B-Thinking-2507",
@@ -5992,6 +6028,42 @@ export const MODELS = {
5992
6028
  contextWindow: 163840,
5993
6029
  maxTokens: 163840,
5994
6030
  },
6031
+ "deepseek-ai/DeepSeek-V3": {
6032
+ id: "deepseek-ai/DeepSeek-V3",
6033
+ name: "DeepSeek-V3",
6034
+ api: "openai-completions",
6035
+ provider: "huggingface",
6036
+ baseUrl: "https://router.huggingface.co/v1",
6037
+ compat: { "supportsDeveloperRole": false },
6038
+ reasoning: false,
6039
+ input: ["text"],
6040
+ cost: {
6041
+ input: 0.4,
6042
+ output: 1.3,
6043
+ cacheRead: 0,
6044
+ cacheWrite: 0,
6045
+ },
6046
+ contextWindow: 64000,
6047
+ maxTokens: 8192,
6048
+ },
6049
+ "deepseek-ai/DeepSeek-V3.1": {
6050
+ id: "deepseek-ai/DeepSeek-V3.1",
6051
+ name: "DeepSeek-V3.1",
6052
+ api: "openai-completions",
6053
+ provider: "huggingface",
6054
+ baseUrl: "https://router.huggingface.co/v1",
6055
+ compat: { "supportsDeveloperRole": false },
6056
+ reasoning: true,
6057
+ input: ["text"],
6058
+ cost: {
6059
+ input: 0.27,
6060
+ output: 1,
6061
+ cacheRead: 0,
6062
+ cacheWrite: 0,
6063
+ },
6064
+ contextWindow: 131072,
6065
+ maxTokens: 8192,
6066
+ },
5995
6067
  "deepseek-ai/DeepSeek-V3.2": {
5996
6068
  id: "deepseek-ai/DeepSeek-V3.2",
5997
6069
  name: "DeepSeek-V3.2",
@@ -6028,6 +6100,24 @@ export const MODELS = {
6028
6100
  contextWindow: 1048576,
6029
6101
  maxTokens: 384000,
6030
6102
  },
6103
+ "deepseek-ai/DeepSeek-V4-Flash-0731": {
6104
+ id: "deepseek-ai/DeepSeek-V4-Flash-0731",
6105
+ name: "DeepSeek V4 Flash 0731",
6106
+ api: "openai-completions",
6107
+ provider: "huggingface",
6108
+ baseUrl: "https://router.huggingface.co/v1",
6109
+ compat: { "supportsDeveloperRole": false },
6110
+ reasoning: true,
6111
+ input: ["text"],
6112
+ cost: {
6113
+ input: 0.14,
6114
+ output: 0.28,
6115
+ cacheRead: 0,
6116
+ cacheWrite: 0,
6117
+ },
6118
+ contextWindow: 1048576,
6119
+ maxTokens: 384000,
6120
+ },
6031
6121
  "deepseek-ai/DeepSeek-V4-Pro": {
6032
6122
  id: "deepseek-ai/DeepSeek-V4-Pro",
6033
6123
  name: "DeepSeek V4 Pro",
@@ -6208,6 +6298,24 @@ export const MODELS = {
6208
6298
  contextWindow: 262144,
6209
6299
  maxTokens: 262144,
6210
6300
  },
6301
+ "moonshotai/Kimi-K3": {
6302
+ id: "moonshotai/Kimi-K3",
6303
+ name: "Kimi K3",
6304
+ api: "openai-completions",
6305
+ provider: "huggingface",
6306
+ baseUrl: "https://router.huggingface.co/v1",
6307
+ compat: { "supportsDeveloperRole": false },
6308
+ reasoning: true,
6309
+ input: ["text", "image"],
6310
+ cost: {
6311
+ input: 3,
6312
+ output: 15,
6313
+ cacheRead: 0,
6314
+ cacheWrite: 0,
6315
+ },
6316
+ contextWindow: 1000000,
6317
+ maxTokens: 131072,
6318
+ },
6211
6319
  "openai/gpt-oss-120b": {
6212
6320
  id: "openai/gpt-oss-120b",
6213
6321
  name: "GPT OSS 120B",
@@ -6280,6 +6388,60 @@ export const MODELS = {
6280
6388
  contextWindow: 262144,
6281
6389
  maxTokens: 256000,
6282
6390
  },
6391
+ "tencent/Hy3": {
6392
+ id: "tencent/Hy3",
6393
+ name: "Hy3",
6394
+ api: "openai-completions",
6395
+ provider: "huggingface",
6396
+ baseUrl: "https://router.huggingface.co/v1",
6397
+ compat: { "supportsDeveloperRole": false },
6398
+ reasoning: true,
6399
+ input: ["text"],
6400
+ cost: {
6401
+ input: 0.14,
6402
+ output: 0.58,
6403
+ cacheRead: 0,
6404
+ cacheWrite: 0,
6405
+ },
6406
+ contextWindow: 262144,
6407
+ maxTokens: 64000,
6408
+ },
6409
+ "thinkingmachines/Inkling": {
6410
+ id: "thinkingmachines/Inkling",
6411
+ name: "Inkling",
6412
+ api: "openai-completions",
6413
+ provider: "huggingface",
6414
+ baseUrl: "https://router.huggingface.co/v1",
6415
+ compat: { "supportsDeveloperRole": false },
6416
+ reasoning: true,
6417
+ input: ["text", "image"],
6418
+ cost: {
6419
+ input: 1,
6420
+ output: 4.05,
6421
+ cacheRead: 0,
6422
+ cacheWrite: 0,
6423
+ },
6424
+ contextWindow: 1048576,
6425
+ maxTokens: 1048576,
6426
+ },
6427
+ "thinkingmachines/Inkling-Small": {
6428
+ id: "thinkingmachines/Inkling-Small",
6429
+ name: "Inkling Small",
6430
+ api: "openai-completions",
6431
+ provider: "huggingface",
6432
+ baseUrl: "https://router.huggingface.co/v1",
6433
+ compat: { "supportsDeveloperRole": false },
6434
+ reasoning: true,
6435
+ input: ["text", "image"],
6436
+ cost: {
6437
+ input: 0.5,
6438
+ output: 1.2,
6439
+ cacheRead: 0,
6440
+ cacheWrite: 0,
6441
+ },
6442
+ contextWindow: 524288,
6443
+ maxTokens: 1048576,
6444
+ },
6283
6445
  "zai-org/GLM-4.5": {
6284
6446
  id: "zai-org/GLM-4.5",
6285
6447
  name: "GLM-4.5",
@@ -7134,6 +7296,23 @@ export const MODELS = {
7134
7296
  contextWindow: 128000,
7135
7297
  maxTokens: 128000,
7136
7298
  },
7299
+ "voxtral-small-latest": {
7300
+ id: "voxtral-small-latest",
7301
+ name: "Voxtral Small (latest)",
7302
+ api: "mistral-conversations",
7303
+ provider: "mistral",
7304
+ baseUrl: "https://api.mistral.ai",
7305
+ reasoning: false,
7306
+ input: ["text"],
7307
+ cost: {
7308
+ input: 0.1,
7309
+ output: 0.3,
7310
+ cacheRead: 0,
7311
+ cacheWrite: 0,
7312
+ },
7313
+ contextWindow: 32000,
7314
+ maxTokens: 32000,
7315
+ },
7137
7316
  },
7138
7317
  "moonshotai": {
7139
7318
  "kimi-k2-0711-preview": {
@@ -7990,10 +8169,10 @@ export const MODELS = {
7990
8169
  thinkingLevelMap: { "off": null },
7991
8170
  input: ["text", "image"],
7992
8171
  cost: {
7993
- input: 1,
7994
- output: 6,
7995
- cacheRead: 0.1,
7996
- cacheWrite: 1.25,
8172
+ input: 0.2,
8173
+ output: 1.2,
8174
+ cacheRead: 0.02,
8175
+ cacheWrite: 0.25,
7997
8176
  },
7998
8177
  contextWindow: 1050000,
7999
8178
  maxTokens: 128000,
@@ -8026,10 +8205,10 @@ export const MODELS = {
8026
8205
  thinkingLevelMap: { "off": null },
8027
8206
  input: ["text", "image"],
8028
8207
  cost: {
8029
- input: 2.5,
8030
- output: 15,
8031
- cacheRead: 0.25,
8032
- cacheWrite: 3.125,
8208
+ input: 2,
8209
+ output: 12,
8210
+ cacheRead: 0.2,
8211
+ cacheWrite: 2.5,
8033
8212
  },
8034
8213
  contextWindow: 1050000,
8035
8214
  maxTokens: 128000,
@@ -8387,23 +8566,6 @@ export const MODELS = {
8387
8566
  contextWindow: 200000,
8388
8567
  maxTokens: 64000,
8389
8568
  },
8390
- "claude-opus-4-1": {
8391
- id: "claude-opus-4-1",
8392
- name: "Claude Opus 4.1",
8393
- api: "anthropic-messages",
8394
- provider: "opencode",
8395
- baseUrl: "https://opencode.ai/zen",
8396
- reasoning: true,
8397
- input: ["text", "image"],
8398
- cost: {
8399
- input: 15,
8400
- output: 75,
8401
- cacheRead: 1.5,
8402
- cacheWrite: 18.75,
8403
- },
8404
- contextWindow: 200000,
8405
- maxTokens: 32000,
8406
- },
8407
8569
  "claude-opus-4-5": {
8408
8570
  id: "claude-opus-4-5",
8409
8571
  name: "Claude Opus 4.5",
@@ -9056,10 +9218,10 @@ export const MODELS = {
9056
9218
  thinkingLevelMap: { "off": null },
9057
9219
  input: ["text", "image"],
9058
9220
  cost: {
9059
- input: 1,
9060
- output: 6,
9061
- cacheRead: 0.1,
9062
- cacheWrite: 1.25,
9221
+ input: 0.2,
9222
+ output: 1.2,
9223
+ cacheRead: 0.02,
9224
+ cacheWrite: 0.25,
9063
9225
  },
9064
9226
  contextWindow: 1050000,
9065
9227
  maxTokens: 128000,
@@ -9185,18 +9347,35 @@ export const MODELS = {
9185
9347
  contextWindow: 262144,
9186
9348
  maxTokens: 262144,
9187
9349
  },
9188
- "laguna-s-2.1-free": {
9189
- id: "laguna-s-2.1-free",
9190
- name: "Laguna S 2.1 Free",
9350
+ "kimi-k3": {
9351
+ id: "kimi-k3",
9352
+ name: "Kimi K3",
9191
9353
  api: "openai-completions",
9192
9354
  provider: "opencode",
9193
9355
  baseUrl: "https://opencode.ai/zen/v1",
9194
9356
  reasoning: true,
9195
- input: ["text"],
9357
+ input: ["text", "image"],
9196
9358
  cost: {
9197
- input: 0,
9198
- output: 0,
9199
- cacheRead: 0,
9359
+ input: 3,
9360
+ output: 15,
9361
+ cacheRead: 0.3,
9362
+ cacheWrite: 0,
9363
+ },
9364
+ contextWindow: 1048576,
9365
+ maxTokens: 131072,
9366
+ },
9367
+ "laguna-s-2.1-free": {
9368
+ id: "laguna-s-2.1-free",
9369
+ name: "Laguna S 2.1 Free",
9370
+ api: "openai-completions",
9371
+ provider: "opencode",
9372
+ baseUrl: "https://opencode.ai/zen/v1",
9373
+ reasoning: true,
9374
+ input: ["text"],
9375
+ cost: {
9376
+ input: 0,
9377
+ output: 0,
9378
+ cacheRead: 0,
9200
9379
  cacheWrite: 0,
9201
9380
  },
9202
9381
  contextWindow: 256000,
@@ -9219,6 +9398,23 @@ export const MODELS = {
9219
9398
  contextWindow: 262144,
9220
9399
  maxTokens: 32768,
9221
9400
  },
9401
+ "longcat-2.0-free": {
9402
+ id: "longcat-2.0-free",
9403
+ name: "LongCat-2.0 Free",
9404
+ api: "openai-completions",
9405
+ provider: "opencode",
9406
+ baseUrl: "https://opencode.ai/zen/v1",
9407
+ reasoning: true,
9408
+ input: ["text"],
9409
+ cost: {
9410
+ input: 0,
9411
+ output: 0,
9412
+ cacheRead: 0,
9413
+ cacheWrite: 0,
9414
+ },
9415
+ contextWindow: 1000000,
9416
+ maxTokens: 131072,
9417
+ },
9222
9418
  "mimo-v2.5-free": {
9223
9419
  id: "mimo-v2.5-free",
9224
9420
  name: "MiMo V2.5 Free",
@@ -9359,7 +9555,7 @@ export const MODELS = {
9359
9555
  "opencode-go": {
9360
9556
  "deepseek-v4-flash": {
9361
9557
  id: "deepseek-v4-flash",
9362
- name: "DeepSeek V4 Flash",
9558
+ name: "DeepSeek V4 Flash (2x usage)",
9363
9559
  api: "openai-completions",
9364
9560
  provider: "opencode-go",
9365
9561
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9368,9 +9564,9 @@ export const MODELS = {
9368
9564
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
9369
9565
  input: ["text"],
9370
9566
  cost: {
9371
- input: 0.14,
9372
- output: 0.28,
9373
- cacheRead: 0.0028,
9567
+ input: 0.07,
9568
+ output: 0.14,
9569
+ cacheRead: 0.0014,
9374
9570
  cacheWrite: 0,
9375
9571
  },
9376
9572
  contextWindow: 1000000,
@@ -9429,6 +9625,24 @@ export const MODELS = {
9429
9625
  contextWindow: 1000000,
9430
9626
  maxTokens: 131072,
9431
9627
  },
9628
+ "gpt-5.6-luna": {
9629
+ id: "gpt-5.6-luna",
9630
+ name: "GPT-5.6 Luna (2x usage)",
9631
+ api: "openai-responses",
9632
+ provider: "opencode-go",
9633
+ baseUrl: "https://opencode.ai/zen/go/v1",
9634
+ reasoning: true,
9635
+ thinkingLevelMap: { "off": null },
9636
+ input: ["text", "image"],
9637
+ cost: {
9638
+ input: 0.1,
9639
+ output: 0.6,
9640
+ cacheRead: 0.01,
9641
+ cacheWrite: 0.125,
9642
+ },
9643
+ contextWindow: 1050000,
9644
+ maxTokens: 128000,
9645
+ },
9432
9646
  "grok-4.5": {
9433
9647
  id: "grok-4.5",
9434
9648
  name: "Grok 4.5",
@@ -9499,7 +9713,7 @@ export const MODELS = {
9499
9713
  },
9500
9714
  "kimi-k3": {
9501
9715
  id: "kimi-k3",
9502
- name: "Kimi K3 (2x usage)",
9716
+ name: "Kimi K3",
9503
9717
  api: "openai-completions",
9504
9718
  provider: "opencode-go",
9505
9719
  baseUrl: "https://opencode.ai/zen/go/v1",
@@ -9634,6 +9848,23 @@ export const MODELS = {
9634
9848
  contextWindow: 1000000,
9635
9849
  maxTokens: 65536,
9636
9850
  },
9851
+ "qwen3.8-max": {
9852
+ id: "qwen3.8-max",
9853
+ name: "Qwen3.8 Max",
9854
+ api: "anthropic-messages",
9855
+ provider: "opencode-go",
9856
+ baseUrl: "https://opencode.ai/zen/go",
9857
+ reasoning: true,
9858
+ input: ["text", "image"],
9859
+ cost: {
9860
+ input: 2,
9861
+ output: 6,
9862
+ cacheRead: 0.25,
9863
+ cacheWrite: 2.5,
9864
+ },
9865
+ contextWindow: 1000000,
9866
+ maxTokens: 131072,
9867
+ },
9637
9868
  },
9638
9869
  "openrouter": {
9639
9870
  "ai21/jamba-large-1.7": {
@@ -9824,6 +10055,24 @@ export const MODELS = {
9824
10055
  contextWindow: 1000000,
9825
10056
  maxTokens: 128000,
9826
10057
  },
10058
+ "anthropic/claude-fable-5:batch": {
10059
+ id: "anthropic/claude-fable-5:batch",
10060
+ name: "Anthropic: Claude Fable 5 (batch)",
10061
+ api: "openai-completions",
10062
+ provider: "openrouter",
10063
+ baseUrl: "https://openrouter.ai/api/v1",
10064
+ reasoning: true,
10065
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "xhigh", "xhigh": "max" },
10066
+ input: ["text", "image"],
10067
+ cost: {
10068
+ input: 5,
10069
+ output: 25,
10070
+ cacheRead: 0.5,
10071
+ cacheWrite: 6.25,
10072
+ },
10073
+ contextWindow: 1000000,
10074
+ maxTokens: 128000,
10075
+ },
9827
10076
  "anthropic/claude-haiku-4.5": {
9828
10077
  id: "anthropic/claude-haiku-4.5",
9829
10078
  name: "Anthropic: Claude Haiku 4.5",
@@ -9841,6 +10090,23 @@ export const MODELS = {
9841
10090
  contextWindow: 200000,
9842
10091
  maxTokens: 64000,
9843
10092
  },
10093
+ "anthropic/claude-haiku-4.5:batch": {
10094
+ id: "anthropic/claude-haiku-4.5:batch",
10095
+ name: "Anthropic: Claude Haiku 4.5 (batch)",
10096
+ api: "openai-completions",
10097
+ provider: "openrouter",
10098
+ baseUrl: "https://openrouter.ai/api/v1",
10099
+ reasoning: true,
10100
+ input: ["text", "image"],
10101
+ cost: {
10102
+ input: 0.5,
10103
+ output: 2.5,
10104
+ cacheRead: 0.049999999999999996,
10105
+ cacheWrite: 0.625,
10106
+ },
10107
+ contextWindow: 200000,
10108
+ maxTokens: 64000,
10109
+ },
9844
10110
  "anthropic/claude-opus-4": {
9845
10111
  id: "anthropic/claude-opus-4",
9846
10112
  name: "Anthropic: Claude Opus 4",
@@ -9875,6 +10141,23 @@ export const MODELS = {
9875
10141
  contextWindow: 200000,
9876
10142
  maxTokens: 32000,
9877
10143
  },
10144
+ "anthropic/claude-opus-4.1:batch": {
10145
+ id: "anthropic/claude-opus-4.1:batch",
10146
+ name: "Anthropic: Claude Opus 4.1 (batch)",
10147
+ api: "openai-completions",
10148
+ provider: "openrouter",
10149
+ baseUrl: "https://openrouter.ai/api/v1",
10150
+ reasoning: true,
10151
+ input: ["text", "image"],
10152
+ cost: {
10153
+ input: 7.5,
10154
+ output: 37.5,
10155
+ cacheRead: 0.75,
10156
+ cacheWrite: 9.375,
10157
+ },
10158
+ contextWindow: 200000,
10159
+ maxTokens: 32000,
10160
+ },
9878
10161
  "anthropic/claude-opus-4.5": {
9879
10162
  id: "anthropic/claude-opus-4.5",
9880
10163
  name: "Anthropic: Claude Opus 4.5",
@@ -9892,6 +10175,23 @@ export const MODELS = {
9892
10175
  contextWindow: 200000,
9893
10176
  maxTokens: 64000,
9894
10177
  },
10178
+ "anthropic/claude-opus-4.5:batch": {
10179
+ id: "anthropic/claude-opus-4.5:batch",
10180
+ name: "Anthropic: Claude Opus 4.5 (batch)",
10181
+ api: "openai-completions",
10182
+ provider: "openrouter",
10183
+ baseUrl: "https://openrouter.ai/api/v1",
10184
+ reasoning: true,
10185
+ input: ["text", "image"],
10186
+ cost: {
10187
+ input: 2.5,
10188
+ output: 12.5,
10189
+ cacheRead: 0.25,
10190
+ cacheWrite: 3.125,
10191
+ },
10192
+ contextWindow: 200000,
10193
+ maxTokens: 64000,
10194
+ },
9895
10195
  "anthropic/claude-opus-4.6": {
9896
10196
  id: "anthropic/claude-opus-4.6",
9897
10197
  name: "Anthropic: Claude Opus 4.6",
@@ -9910,6 +10210,24 @@ export const MODELS = {
9910
10210
  contextWindow: 1000000,
9911
10211
  maxTokens: 128000,
9912
10212
  },
10213
+ "anthropic/claude-opus-4.6:batch": {
10214
+ id: "anthropic/claude-opus-4.6:batch",
10215
+ name: "Anthropic: Claude Opus 4.6 (batch)",
10216
+ api: "openai-completions",
10217
+ provider: "openrouter",
10218
+ baseUrl: "https://openrouter.ai/api/v1",
10219
+ reasoning: true,
10220
+ thinkingLevelMap: { "xhigh": "max" },
10221
+ input: ["text", "image"],
10222
+ cost: {
10223
+ input: 2.5,
10224
+ output: 12.5,
10225
+ cacheRead: 0.25,
10226
+ cacheWrite: 3.125,
10227
+ },
10228
+ contextWindow: 1000000,
10229
+ maxTokens: 128000,
10230
+ },
9913
10231
  "anthropic/claude-opus-4.7": {
9914
10232
  id: "anthropic/claude-opus-4.7",
9915
10233
  name: "Anthropic: Claude Opus 4.7",
@@ -9946,6 +10264,24 @@ export const MODELS = {
9946
10264
  contextWindow: 1000000,
9947
10265
  maxTokens: 128000,
9948
10266
  },
10267
+ "anthropic/claude-opus-4.7:batch": {
10268
+ id: "anthropic/claude-opus-4.7:batch",
10269
+ name: "Anthropic: Claude Opus 4.7 (batch)",
10270
+ api: "openai-completions",
10271
+ provider: "openrouter",
10272
+ baseUrl: "https://openrouter.ai/api/v1",
10273
+ reasoning: true,
10274
+ thinkingLevelMap: { "xhigh": "xhigh" },
10275
+ input: ["text", "image"],
10276
+ cost: {
10277
+ input: 2.5,
10278
+ output: 12.5,
10279
+ cacheRead: 0.25,
10280
+ cacheWrite: 3.125,
10281
+ },
10282
+ contextWindow: 1000000,
10283
+ maxTokens: 128000,
10284
+ },
9949
10285
  "anthropic/claude-opus-4.8": {
9950
10286
  id: "anthropic/claude-opus-4.8",
9951
10287
  name: "Anthropic: Claude Opus 4.8",
@@ -9982,6 +10318,24 @@ export const MODELS = {
9982
10318
  contextWindow: 1000000,
9983
10319
  maxTokens: 128000,
9984
10320
  },
10321
+ "anthropic/claude-opus-4.8:batch": {
10322
+ id: "anthropic/claude-opus-4.8:batch",
10323
+ name: "Anthropic: Claude Opus 4.8 (batch)",
10324
+ api: "openai-completions",
10325
+ provider: "openrouter",
10326
+ baseUrl: "https://openrouter.ai/api/v1",
10327
+ reasoning: true,
10328
+ thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
10329
+ input: ["text", "image"],
10330
+ cost: {
10331
+ input: 2.5,
10332
+ output: 12.5,
10333
+ cacheRead: 0.25,
10334
+ cacheWrite: 3.125,
10335
+ },
10336
+ contextWindow: 1000000,
10337
+ maxTokens: 128000,
10338
+ },
9985
10339
  "anthropic/claude-opus-5": {
9986
10340
  id: "anthropic/claude-opus-5",
9987
10341
  name: "Claude Opus 5",
@@ -10016,6 +10370,23 @@ export const MODELS = {
10016
10370
  contextWindow: 1000000,
10017
10371
  maxTokens: 128000,
10018
10372
  },
10373
+ "anthropic/claude-opus-5:batch": {
10374
+ id: "anthropic/claude-opus-5:batch",
10375
+ name: "Claude Opus 5 (batch)",
10376
+ api: "openai-completions",
10377
+ provider: "openrouter",
10378
+ baseUrl: "https://openrouter.ai/api/v1",
10379
+ reasoning: true,
10380
+ input: ["text", "image"],
10381
+ cost: {
10382
+ input: 2.5,
10383
+ output: 12.5,
10384
+ cacheRead: 0.25,
10385
+ cacheWrite: 3.125,
10386
+ },
10387
+ contextWindow: 1000000,
10388
+ maxTokens: 128000,
10389
+ },
10019
10390
  "anthropic/claude-sonnet-4": {
10020
10391
  id: "anthropic/claude-sonnet-4",
10021
10392
  name: "Anthropic: Claude Sonnet 4",
@@ -10050,6 +10421,23 @@ export const MODELS = {
10050
10421
  contextWindow: 1000000,
10051
10422
  maxTokens: 64000,
10052
10423
  },
10424
+ "anthropic/claude-sonnet-4.5:batch": {
10425
+ id: "anthropic/claude-sonnet-4.5:batch",
10426
+ name: "Anthropic: Claude Sonnet 4.5 (batch)",
10427
+ api: "openai-completions",
10428
+ provider: "openrouter",
10429
+ baseUrl: "https://openrouter.ai/api/v1",
10430
+ reasoning: true,
10431
+ input: ["text", "image"],
10432
+ cost: {
10433
+ input: 1.5,
10434
+ output: 7.5,
10435
+ cacheRead: 0.15,
10436
+ cacheWrite: 1.875,
10437
+ },
10438
+ contextWindow: 1000000,
10439
+ maxTokens: 64000,
10440
+ },
10053
10441
  "anthropic/claude-sonnet-4.6": {
10054
10442
  id: "anthropic/claude-sonnet-4.6",
10055
10443
  name: "Anthropic: Claude Sonnet 4.6",
@@ -10067,6 +10455,23 @@ export const MODELS = {
10067
10455
  contextWindow: 1000000,
10068
10456
  maxTokens: 128000,
10069
10457
  },
10458
+ "anthropic/claude-sonnet-4.6:batch": {
10459
+ id: "anthropic/claude-sonnet-4.6:batch",
10460
+ name: "Anthropic: Claude Sonnet 4.6 (batch)",
10461
+ api: "openai-completions",
10462
+ provider: "openrouter",
10463
+ baseUrl: "https://openrouter.ai/api/v1",
10464
+ reasoning: true,
10465
+ input: ["text", "image"],
10466
+ cost: {
10467
+ input: 1.5,
10468
+ output: 7.5,
10469
+ cacheRead: 0.15,
10470
+ cacheWrite: 1.875,
10471
+ },
10472
+ contextWindow: 1000000,
10473
+ maxTokens: 128000,
10474
+ },
10070
10475
  "anthropic/claude-sonnet-5": {
10071
10476
  id: "anthropic/claude-sonnet-5",
10072
10477
  name: "Anthropic: Claude Sonnet 5",
@@ -10084,6 +10489,23 @@ export const MODELS = {
10084
10489
  contextWindow: 1000000,
10085
10490
  maxTokens: 128000,
10086
10491
  },
10492
+ "anthropic/claude-sonnet-5:batch": {
10493
+ id: "anthropic/claude-sonnet-5:batch",
10494
+ name: "Anthropic: Claude Sonnet 5 (batch)",
10495
+ api: "openai-completions",
10496
+ provider: "openrouter",
10497
+ baseUrl: "https://openrouter.ai/api/v1",
10498
+ reasoning: true,
10499
+ input: ["text", "image"],
10500
+ cost: {
10501
+ input: 1,
10502
+ output: 5,
10503
+ cacheRead: 0.09999999999999999,
10504
+ cacheWrite: 1.25,
10505
+ },
10506
+ contextWindow: 1000000,
10507
+ maxTokens: 128000,
10508
+ },
10087
10509
  "arcee-ai/trinity-large-thinking": {
10088
10510
  id: "arcee-ai/trinity-large-thinking",
10089
10511
  name: "Arcee AI: Trinity Large Thinking",
@@ -10093,13 +10515,13 @@ export const MODELS = {
10093
10515
  reasoning: true,
10094
10516
  input: ["text"],
10095
10517
  cost: {
10096
- input: 0.25,
10097
- output: 0.7999999999999999,
10518
+ input: 0.22,
10519
+ output: 0.85,
10098
10520
  cacheRead: 0.06,
10099
10521
  cacheWrite: 0,
10100
10522
  },
10101
10523
  contextWindow: 262144,
10102
- maxTokens: 80000,
10524
+ maxTokens: 262144,
10103
10525
  },
10104
10526
  "arcee-ai/virtuoso-large": {
10105
10527
  id: "arcee-ai/virtuoso-large",
@@ -10263,8 +10685,8 @@ export const MODELS = {
10263
10685
  reasoning: false,
10264
10686
  input: ["text"],
10265
10687
  cost: {
10266
- input: 0.20020000000000002,
10267
- output: 0.8000999999999999,
10688
+ input: 0.2574,
10689
+ output: 1.0287,
10268
10690
  cacheRead: 0,
10269
10691
  cacheWrite: 0,
10270
10692
  },
@@ -10392,7 +10814,7 @@ export const MODELS = {
10392
10814
  },
10393
10815
  "deepseek/deepseek-v4-flash": {
10394
10816
  id: "deepseek/deepseek-v4-flash",
10395
- name: "DeepSeek: DeepSeek V4 Flash",
10817
+ name: "DeepSeek: DeepSeek V4 Flash 0423",
10396
10818
  api: "openai-completions",
10397
10819
  provider: "openrouter",
10398
10820
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10401,13 +10823,32 @@ export const MODELS = {
10401
10823
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10402
10824
  input: ["text"],
10403
10825
  cost: {
10404
- input: 0.098,
10405
- output: 0.196,
10406
- cacheRead: 0.0196,
10826
+ input: 0.0882,
10827
+ output: 0.1764,
10828
+ cacheRead: 0.01764,
10407
10829
  cacheWrite: 0,
10408
10830
  },
10409
10831
  contextWindow: 1048576,
10410
- maxTokens: 4096,
10832
+ maxTokens: 131072,
10833
+ },
10834
+ "deepseek/deepseek-v4-flash-0731": {
10835
+ id: "deepseek/deepseek-v4-flash-0731",
10836
+ name: "DeepSeek: DeepSeek V4 Flash 0731",
10837
+ api: "openai-completions",
10838
+ provider: "openrouter",
10839
+ baseUrl: "https://openrouter.ai/api/v1",
10840
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
10841
+ reasoning: true,
10842
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
10843
+ input: ["text"],
10844
+ cost: {
10845
+ input: 0.09,
10846
+ output: 0.18,
10847
+ cacheRead: 0.018,
10848
+ cacheWrite: 0,
10849
+ },
10850
+ contextWindow: 1048576,
10851
+ maxTokens: 65536,
10411
10852
  },
10412
10853
  "deepseek/deepseek-v4-pro": {
10413
10854
  id: "deepseek/deepseek-v4-pro",
@@ -10440,7 +10881,7 @@ export const MODELS = {
10440
10881
  input: 0.3,
10441
10882
  output: 2.5,
10442
10883
  cacheRead: 0.03,
10443
- cacheWrite: 0.08333333333333334,
10884
+ cacheWrite: 0.0833333333333333,
10444
10885
  },
10445
10886
  contextWindow: 1048576,
10446
10887
  maxTokens: 65535,
@@ -10457,26 +10898,60 @@ export const MODELS = {
10457
10898
  input: 0.09999999999999999,
10458
10899
  output: 0.39999999999999997,
10459
10900
  cacheRead: 0.01,
10460
- cacheWrite: 0.08333333333333334,
10901
+ cacheWrite: 0.0833333333333333,
10461
10902
  },
10462
10903
  contextWindow: 1048576,
10463
10904
  maxTokens: 65535,
10464
10905
  },
10465
- "google/gemini-2.5-pro": {
10466
- id: "google/gemini-2.5-pro",
10467
- name: "Google: Gemini 2.5 Pro",
10906
+ "google/gemini-2.5-flash-lite:batch": {
10907
+ id: "google/gemini-2.5-flash-lite:batch",
10908
+ name: "Google: Gemini 2.5 Flash Lite (batch)",
10468
10909
  api: "openai-completions",
10469
10910
  provider: "openrouter",
10470
10911
  baseUrl: "https://openrouter.ai/api/v1",
10471
10912
  reasoning: true,
10472
10913
  input: ["text", "image"],
10473
10914
  cost: {
10474
- input: 1.25,
10475
- output: 10,
10476
- cacheRead: 0.125,
10477
- cacheWrite: 0.375,
10478
- },
10479
- contextWindow: 1048576,
10915
+ input: 0.049999999999999996,
10916
+ output: 0.19999999999999998,
10917
+ cacheRead: 0.01,
10918
+ cacheWrite: 0,
10919
+ },
10920
+ contextWindow: 1048576,
10921
+ maxTokens: 65535,
10922
+ },
10923
+ "google/gemini-2.5-flash:batch": {
10924
+ id: "google/gemini-2.5-flash:batch",
10925
+ name: "Google: Gemini 2.5 Flash (batch)",
10926
+ api: "openai-completions",
10927
+ provider: "openrouter",
10928
+ baseUrl: "https://openrouter.ai/api/v1",
10929
+ reasoning: true,
10930
+ input: ["text", "image"],
10931
+ cost: {
10932
+ input: 0.15,
10933
+ output: 1.25,
10934
+ cacheRead: 0.03,
10935
+ cacheWrite: 0,
10936
+ },
10937
+ contextWindow: 1048576,
10938
+ maxTokens: 65535,
10939
+ },
10940
+ "google/gemini-2.5-pro": {
10941
+ id: "google/gemini-2.5-pro",
10942
+ name: "Google: Gemini 2.5 Pro",
10943
+ api: "openai-completions",
10944
+ provider: "openrouter",
10945
+ baseUrl: "https://openrouter.ai/api/v1",
10946
+ reasoning: true,
10947
+ input: ["text", "image"],
10948
+ cost: {
10949
+ input: 1.25,
10950
+ output: 10,
10951
+ cacheRead: 0.125,
10952
+ cacheWrite: 0.375,
10953
+ },
10954
+ contextWindow: 1048576,
10480
10955
  maxTokens: 65536,
10481
10956
  },
10482
10957
  "google/gemini-2.5-pro-preview": {
@@ -10513,6 +10988,23 @@ export const MODELS = {
10513
10988
  contextWindow: 1048576,
10514
10989
  maxTokens: 65535,
10515
10990
  },
10991
+ "google/gemini-2.5-pro:batch": {
10992
+ id: "google/gemini-2.5-pro:batch",
10993
+ name: "Google: Gemini 2.5 Pro (batch)",
10994
+ api: "openai-completions",
10995
+ provider: "openrouter",
10996
+ baseUrl: "https://openrouter.ai/api/v1",
10997
+ reasoning: true,
10998
+ input: ["text", "image"],
10999
+ cost: {
11000
+ input: 0.625,
11001
+ output: 5,
11002
+ cacheRead: 0.125,
11003
+ cacheWrite: 0,
11004
+ },
11005
+ contextWindow: 1048576,
11006
+ maxTokens: 65536,
11007
+ },
10516
11008
  "google/gemini-3-flash-preview": {
10517
11009
  id: "google/gemini-3-flash-preview",
10518
11010
  name: "Google: Gemini 3 Flash Preview",
@@ -10525,10 +11017,27 @@ export const MODELS = {
10525
11017
  input: 0.5,
10526
11018
  output: 3,
10527
11019
  cacheRead: 0.049999999999999996,
10528
- cacheWrite: 0.08333333333333334,
11020
+ cacheWrite: 0.0833333333333333,
10529
11021
  },
10530
11022
  contextWindow: 1048576,
10531
- maxTokens: 65535,
11023
+ maxTokens: 65536,
11024
+ },
11025
+ "google/gemini-3-flash-preview:batch": {
11026
+ id: "google/gemini-3-flash-preview:batch",
11027
+ name: "Google: Gemini 3 Flash Preview (batch)",
11028
+ api: "openai-completions",
11029
+ provider: "openrouter",
11030
+ baseUrl: "https://openrouter.ai/api/v1",
11031
+ reasoning: true,
11032
+ input: ["text", "image"],
11033
+ cost: {
11034
+ input: 0.25,
11035
+ output: 1.5,
11036
+ cacheRead: 0,
11037
+ cacheWrite: 0,
11038
+ },
11039
+ contextWindow: 1048576,
11040
+ maxTokens: 65536,
10532
11041
  },
10533
11042
  "google/gemini-3-pro-image": {
10534
11043
  id: "google/gemini-3-pro-image",
@@ -10559,7 +11068,7 @@ export const MODELS = {
10559
11068
  input: 0.25,
10560
11069
  output: 1.5,
10561
11070
  cacheRead: 0.024999999999999998,
10562
- cacheWrite: 0.08333333333333334,
11071
+ cacheWrite: 0.0833333333333333,
10563
11072
  },
10564
11073
  contextWindow: 1048576,
10565
11074
  maxTokens: 65536,
@@ -10576,7 +11085,24 @@ export const MODELS = {
10576
11085
  input: 0.25,
10577
11086
  output: 1.5,
10578
11087
  cacheRead: 0.024999999999999998,
10579
- cacheWrite: 0.08333333333333334,
11088
+ cacheWrite: 0.0833333333333333,
11089
+ },
11090
+ contextWindow: 1048576,
11091
+ maxTokens: 65536,
11092
+ },
11093
+ "google/gemini-3.1-flash-lite:batch": {
11094
+ id: "google/gemini-3.1-flash-lite:batch",
11095
+ name: "Google: Gemini 3.1 Flash Lite (batch)",
11096
+ api: "openai-completions",
11097
+ provider: "openrouter",
11098
+ baseUrl: "https://openrouter.ai/api/v1",
11099
+ reasoning: true,
11100
+ input: ["text", "image"],
11101
+ cost: {
11102
+ input: 0.125,
11103
+ output: 0.75,
11104
+ cacheRead: 0.012499999999999999,
11105
+ cacheWrite: 0,
10580
11106
  },
10581
11107
  contextWindow: 1048576,
10582
11108
  maxTokens: 65536,
@@ -10615,6 +11141,23 @@ export const MODELS = {
10615
11141
  contextWindow: 1048576,
10616
11142
  maxTokens: 65536,
10617
11143
  },
11144
+ "google/gemini-3.1-pro-preview:batch": {
11145
+ id: "google/gemini-3.1-pro-preview:batch",
11146
+ name: "Google: Gemini 3.1 Pro Preview (batch)",
11147
+ api: "openai-completions",
11148
+ provider: "openrouter",
11149
+ baseUrl: "https://openrouter.ai/api/v1",
11150
+ reasoning: true,
11151
+ input: ["text", "image"],
11152
+ cost: {
11153
+ input: 1,
11154
+ output: 6,
11155
+ cacheRead: 0,
11156
+ cacheWrite: 0,
11157
+ },
11158
+ contextWindow: 1048576,
11159
+ maxTokens: 65536,
11160
+ },
10618
11161
  "google/gemini-3.5-flash": {
10619
11162
  id: "google/gemini-3.5-flash",
10620
11163
  name: "Google: Gemini 3.5 Flash",
@@ -10627,7 +11170,7 @@ export const MODELS = {
10627
11170
  input: 1.5,
10628
11171
  output: 9,
10629
11172
  cacheRead: 0.15,
10630
- cacheWrite: 0.08333333333333334,
11173
+ cacheWrite: 0.0833333333333333,
10631
11174
  },
10632
11175
  contextWindow: 1048576,
10633
11176
  maxTokens: 65536,
@@ -10644,7 +11187,41 @@ export const MODELS = {
10644
11187
  input: 0.3,
10645
11188
  output: 2.5,
10646
11189
  cacheRead: 0.03,
10647
- cacheWrite: 0.08333333333333334,
11190
+ cacheWrite: 0.0833333333333333,
11191
+ },
11192
+ contextWindow: 1048576,
11193
+ maxTokens: 65536,
11194
+ },
11195
+ "google/gemini-3.5-flash-lite:batch": {
11196
+ id: "google/gemini-3.5-flash-lite:batch",
11197
+ name: "Google: Gemini 3.5 Flash Lite (batch)",
11198
+ api: "openai-completions",
11199
+ provider: "openrouter",
11200
+ baseUrl: "https://openrouter.ai/api/v1",
11201
+ reasoning: true,
11202
+ input: ["text", "image"],
11203
+ cost: {
11204
+ input: 0.15,
11205
+ output: 1.25,
11206
+ cacheRead: 0.015,
11207
+ cacheWrite: 0,
11208
+ },
11209
+ contextWindow: 1048576,
11210
+ maxTokens: 65536,
11211
+ },
11212
+ "google/gemini-3.5-flash:batch": {
11213
+ id: "google/gemini-3.5-flash:batch",
11214
+ name: "Google: Gemini 3.5 Flash (batch)",
11215
+ api: "openai-completions",
11216
+ provider: "openrouter",
11217
+ baseUrl: "https://openrouter.ai/api/v1",
11218
+ reasoning: true,
11219
+ input: ["text", "image"],
11220
+ cost: {
11221
+ input: 0.75,
11222
+ output: 4.5,
11223
+ cacheRead: 0.075,
11224
+ cacheWrite: 0,
10648
11225
  },
10649
11226
  contextWindow: 1048576,
10650
11227
  maxTokens: 65536,
@@ -10661,7 +11238,24 @@ export const MODELS = {
10661
11238
  input: 1.5,
10662
11239
  output: 7.5,
10663
11240
  cacheRead: 0.15,
10664
- cacheWrite: 0.08333333333333334,
11241
+ cacheWrite: 0.0833333333333333,
11242
+ },
11243
+ contextWindow: 1048576,
11244
+ maxTokens: 65536,
11245
+ },
11246
+ "google/gemini-3.6-flash:batch": {
11247
+ id: "google/gemini-3.6-flash:batch",
11248
+ name: "Google: Gemini 3.6 Flash (batch)",
11249
+ api: "openai-completions",
11250
+ provider: "openrouter",
11251
+ baseUrl: "https://openrouter.ai/api/v1",
11252
+ reasoning: true,
11253
+ input: ["text", "image"],
11254
+ cost: {
11255
+ input: 0.75,
11256
+ output: 3.75,
11257
+ cacheRead: 0.075,
11258
+ cacheWrite: 0.0833333333333333,
10665
11259
  },
10666
11260
  contextWindow: 1048576,
10667
11261
  maxTokens: 65536,
@@ -10709,13 +11303,13 @@ export const MODELS = {
10709
11303
  reasoning: true,
10710
11304
  input: ["text", "image"],
10711
11305
  cost: {
10712
- input: 0.12,
10713
- output: 0.35,
10714
- cacheRead: 0.049999999999999996,
11306
+ input: 0.07,
11307
+ output: 0.33999999999999997,
11308
+ cacheRead: 0,
10715
11309
  cacheWrite: 0,
10716
11310
  },
10717
11311
  contextWindow: 262144,
10718
- maxTokens: 262144,
11312
+ maxTokens: 16384,
10719
11313
  },
10720
11314
  "google/gemma-4-26b-a4b-it:free": {
10721
11315
  id: "google/gemma-4-26b-a4b-it:free",
@@ -10743,9 +11337,9 @@ export const MODELS = {
10743
11337
  reasoning: true,
10744
11338
  input: ["text", "image"],
10745
11339
  cost: {
10746
- input: 0.14,
10747
- output: 0.39999999999999997,
10748
- cacheRead: 0,
11340
+ input: 0.09999999999999999,
11341
+ output: 0.33999999999999997,
11342
+ cacheRead: 0.09999999999999999,
10749
11343
  cacheWrite: 0,
10750
11344
  },
10751
11345
  contextWindow: 262144,
@@ -10836,9 +11430,26 @@ export const MODELS = {
10836
11430
  contextWindow: 262144,
10837
11431
  maxTokens: 32768,
10838
11432
  },
10839
- "inclusionai/ling-3.0-flash:free": {
10840
- id: "inclusionai/ling-3.0-flash:free",
10841
- name: "Ling-3.0-flash (free)",
11433
+ "inclusionai/ling-3.0-flash": {
11434
+ id: "inclusionai/ling-3.0-flash",
11435
+ name: "Ling-3.0-flash",
11436
+ api: "openai-completions",
11437
+ provider: "openrouter",
11438
+ baseUrl: "https://openrouter.ai/api/v1",
11439
+ reasoning: true,
11440
+ input: ["text"],
11441
+ cost: {
11442
+ input: 0.020999999999999998,
11443
+ output: 0.063,
11444
+ cacheRead: 0.004200000000000001,
11445
+ cacheWrite: 0,
11446
+ },
11447
+ contextWindow: 262144,
11448
+ maxTokens: 32768,
11449
+ },
11450
+ "inclusionai/ling-3.0-tiny:free": {
11451
+ id: "inclusionai/ling-3.0-tiny:free",
11452
+ name: "inclusionAI: Ling 3.0 Tiny (free)",
10842
11453
  api: "openai-completions",
10843
11454
  provider: "openrouter",
10844
11455
  baseUrl: "https://openrouter.ai/api/v1",
@@ -10981,13 +11592,13 @@ export const MODELS = {
10981
11592
  reasoning: false,
10982
11593
  input: ["text"],
10983
11594
  cost: {
10984
- input: 0.13,
10985
- output: 0.39999999999999997,
11595
+ input: 0.09999999999999999,
11596
+ output: 0.32,
10986
11597
  cacheRead: 0,
10987
11598
  cacheWrite: 0,
10988
11599
  },
10989
11600
  contextWindow: 131072,
10990
- maxTokens: 128000,
11601
+ maxTokens: 16384,
10991
11602
  },
10992
11603
  "meta-llama/llama-4-maverick": {
10993
11604
  id: "meta-llama/llama-4-maverick",
@@ -11040,6 +11651,23 @@ export const MODELS = {
11040
11651
  contextWindow: 1048576,
11041
11652
  maxTokens: 4096,
11042
11653
  },
11654
+ "meta/muse-spark-1.2": {
11655
+ id: "meta/muse-spark-1.2",
11656
+ name: "Meta: Muse Spark 1.2",
11657
+ api: "openai-completions",
11658
+ provider: "openrouter",
11659
+ baseUrl: "https://openrouter.ai/api/v1",
11660
+ reasoning: true,
11661
+ input: ["text", "image"],
11662
+ cost: {
11663
+ input: 1.25,
11664
+ output: 4.25,
11665
+ cacheRead: 0.15,
11666
+ cacheWrite: 0,
11667
+ },
11668
+ contextWindow: 1048576,
11669
+ maxTokens: 4096,
11670
+ },
11043
11671
  "minimax/minimax-m1": {
11044
11672
  id: "minimax/minimax-m1",
11045
11673
  name: "MiniMax: MiniMax M1",
@@ -11100,7 +11728,7 @@ export const MODELS = {
11100
11728
  reasoning: true,
11101
11729
  input: ["text"],
11102
11730
  cost: {
11103
- input: 0.15,
11731
+ input: 0.22,
11104
11732
  output: 0.8999999999999999,
11105
11733
  cacheRead: 0.049999999999999996,
11106
11734
  cacheWrite: 0,
@@ -11117,9 +11745,9 @@ export const MODELS = {
11117
11745
  reasoning: true,
11118
11746
  input: ["text"],
11119
11747
  cost: {
11120
- input: 0.25,
11121
- output: 1,
11122
- cacheRead: 0.049999999999999996,
11748
+ input: 0.27,
11749
+ output: 1.08,
11750
+ cacheRead: 0.054,
11123
11751
  cacheWrite: 0,
11124
11752
  },
11125
11753
  contextWindow: 204800,
@@ -11142,38 +11770,38 @@ export const MODELS = {
11142
11770
  contextWindow: 1048576,
11143
11771
  maxTokens: 512000,
11144
11772
  },
11145
- "mistralai/codestral-2508": {
11146
- id: "mistralai/codestral-2508",
11147
- name: "Mistral: Codestral 2508",
11773
+ "minimax/minimax-m3:batch": {
11774
+ id: "minimax/minimax-m3:batch",
11775
+ name: "MiniMax: MiniMax M3 (batch)",
11148
11776
  api: "openai-completions",
11149
11777
  provider: "openrouter",
11150
11778
  baseUrl: "https://openrouter.ai/api/v1",
11151
- reasoning: false,
11152
- input: ["text"],
11779
+ reasoning: true,
11780
+ input: ["text", "image"],
11153
11781
  cost: {
11154
- input: 0.3,
11155
- output: 0.8999999999999999,
11782
+ input: 0.15,
11783
+ output: 0.6,
11156
11784
  cacheRead: 0.03,
11157
11785
  cacheWrite: 0,
11158
11786
  },
11159
- contextWindow: 256000,
11787
+ contextWindow: 524288,
11160
11788
  maxTokens: 4096,
11161
11789
  },
11162
- "mistralai/devstral-2512": {
11163
- id: "mistralai/devstral-2512",
11164
- name: "Mistral: Devstral 2 2512",
11790
+ "mistralai/codestral-2508": {
11791
+ id: "mistralai/codestral-2508",
11792
+ name: "Mistral: Codestral 2508",
11165
11793
  api: "openai-completions",
11166
11794
  provider: "openrouter",
11167
11795
  baseUrl: "https://openrouter.ai/api/v1",
11168
11796
  reasoning: false,
11169
11797
  input: ["text"],
11170
11798
  cost: {
11171
- input: 0.39999999999999997,
11172
- output: 2,
11173
- cacheRead: 0.04,
11799
+ input: 0.3,
11800
+ output: 0.8999999999999999,
11801
+ cacheRead: 0.03,
11174
11802
  cacheWrite: 0,
11175
11803
  },
11176
- contextWindow: 262144,
11804
+ contextWindow: 256000,
11177
11805
  maxTokens: 4096,
11178
11806
  },
11179
11807
  "mistralai/ministral-14b-2512": {
@@ -11389,13 +12017,13 @@ export const MODELS = {
11389
12017
  reasoning: false,
11390
12018
  input: ["text", "image"],
11391
12019
  cost: {
11392
- input: 0.09999999999999999,
11393
- output: 0.3,
11394
- cacheRead: 0.01,
12020
+ input: 0.09375,
12021
+ output: 0.25,
12022
+ cacheRead: 0,
11395
12023
  cacheWrite: 0,
11396
12024
  },
11397
12025
  contextWindow: 256000,
11398
- maxTokens: 4096,
12026
+ maxTokens: 16384,
11399
12027
  },
11400
12028
  "mistralai/mixtral-8x22b-instruct": {
11401
12029
  id: "mistralai/mixtral-8x22b-instruct",
@@ -11508,9 +12136,9 @@ export const MODELS = {
11508
12136
  reasoning: true,
11509
12137
  input: ["text", "image"],
11510
12138
  cost: {
11511
- input: 0.684,
11512
- output: 3.42,
11513
- cacheRead: 0.144,
12139
+ input: 0.589,
12140
+ output: 2.48,
12141
+ cacheRead: 0.0992,
11514
12142
  cacheWrite: 0,
11515
12143
  },
11516
12144
  contextWindow: 262144,
@@ -11525,14 +12153,31 @@ export const MODELS = {
11525
12153
  reasoning: true,
11526
12154
  input: ["text", "image"],
11527
12155
  cost: {
11528
- input: 0.82,
11529
- output: 3.75,
12156
+ input: 0.7,
12157
+ output: 3.5,
11530
12158
  cacheRead: 0.15,
11531
12159
  cacheWrite: 0,
11532
12160
  },
11533
12161
  contextWindow: 262144,
11534
12162
  maxTokens: 262144,
11535
12163
  },
12164
+ "moonshotai/kimi-k2.7-code:batch": {
12165
+ id: "moonshotai/kimi-k2.7-code:batch",
12166
+ name: "MoonshotAI: Kimi K2.7 Code (batch)",
12167
+ api: "openai-completions",
12168
+ provider: "openrouter",
12169
+ baseUrl: "https://openrouter.ai/api/v1",
12170
+ reasoning: true,
12171
+ input: ["text", "image"],
12172
+ cost: {
12173
+ input: 0.475,
12174
+ output: 2,
12175
+ cacheRead: 0.095,
12176
+ cacheWrite: 0,
12177
+ },
12178
+ contextWindow: 262144,
12179
+ maxTokens: 4096,
12180
+ },
11536
12181
  "moonshotai/kimi-k3": {
11537
12182
  id: "moonshotai/kimi-k3",
11538
12183
  name: "MoonshotAI: Kimi K3",
@@ -11595,11 +12240,11 @@ export const MODELS = {
11595
12240
  cost: {
11596
12241
  input: 0.049999999999999996,
11597
12242
  output: 0.19999999999999998,
11598
- cacheRead: 0,
12243
+ cacheRead: 0.03,
11599
12244
  cacheWrite: 0,
11600
12245
  },
11601
12246
  contextWindow: 262144,
11602
- maxTokens: 228000,
12247
+ maxTokens: 262144,
11603
12248
  },
11604
12249
  "nvidia/nemotron-3-nano-30b-a3b:free": {
11605
12250
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -11644,8 +12289,8 @@ export const MODELS = {
11644
12289
  reasoning: true,
11645
12290
  input: ["text"],
11646
12291
  cost: {
11647
- input: 0.08,
11648
- output: 0.44999999999999996,
12292
+ input: 0.3,
12293
+ output: 0.8999999999999999,
11649
12294
  cacheRead: 0,
11650
12295
  cacheWrite: 0,
11651
12296
  },
@@ -11678,13 +12323,30 @@ export const MODELS = {
11678
12323
  reasoning: true,
11679
12324
  input: ["text"],
11680
12325
  cost: {
11681
- input: 0.5,
11682
- output: 2.2,
12326
+ input: 0.6,
12327
+ output: 3.5999999999999996,
12328
+ cacheRead: 0.19999999999999998,
12329
+ cacheWrite: 0,
12330
+ },
12331
+ contextWindow: 512288,
12332
+ maxTokens: 4096,
12333
+ },
12334
+ "nvidia/nemotron-3-ultra-550b-a55b:batch": {
12335
+ id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
12336
+ name: "NVIDIA: Nemotron 3 Ultra (batch)",
12337
+ api: "openai-completions",
12338
+ provider: "openrouter",
12339
+ baseUrl: "https://openrouter.ai/api/v1",
12340
+ reasoning: true,
12341
+ input: ["text"],
12342
+ cost: {
12343
+ input: 0.3,
12344
+ output: 1.7999999999999998,
11683
12345
  cacheRead: 0.09999999999999999,
11684
12346
  cacheWrite: 0,
11685
12347
  },
11686
12348
  contextWindow: 512288,
11687
- maxTokens: 16384,
12349
+ maxTokens: 4096,
11688
12350
  },
11689
12351
  "nvidia/nemotron-3-ultra-550b-a55b:free": {
11690
12352
  id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11788,8 +12450,25 @@ export const MODELS = {
11788
12450
  contextWindow: 16385,
11789
12451
  maxTokens: 4096,
11790
12452
  },
11791
- "openai/gpt-4": {
11792
- id: "openai/gpt-4",
12453
+ "openai/gpt-3.5-turbo:batch": {
12454
+ id: "openai/gpt-3.5-turbo:batch",
12455
+ name: "OpenAI: GPT-3.5 Turbo (batch)",
12456
+ api: "openai-completions",
12457
+ provider: "openrouter",
12458
+ baseUrl: "https://openrouter.ai/api/v1",
12459
+ reasoning: false,
12460
+ input: ["text"],
12461
+ cost: {
12462
+ input: 0.25,
12463
+ output: 0.75,
12464
+ cacheRead: 0,
12465
+ cacheWrite: 0,
12466
+ },
12467
+ contextWindow: 16385,
12468
+ maxTokens: 4096,
12469
+ },
12470
+ "openai/gpt-4": {
12471
+ id: "openai/gpt-4",
11793
12472
  name: "OpenAI: GPT-4",
11794
12473
  api: "openai-completions",
11795
12474
  provider: "openrouter",
@@ -11805,6 +12484,23 @@ export const MODELS = {
11805
12484
  contextWindow: 8191,
11806
12485
  maxTokens: 4096,
11807
12486
  },
12487
+ "openai/gpt-4-turbo:batch": {
12488
+ id: "openai/gpt-4-turbo:batch",
12489
+ name: "OpenAI: GPT-4 Turbo (batch)",
12490
+ api: "openai-completions",
12491
+ provider: "openrouter",
12492
+ baseUrl: "https://openrouter.ai/api/v1",
12493
+ reasoning: false,
12494
+ input: ["text", "image"],
12495
+ cost: {
12496
+ input: 5,
12497
+ output: 15,
12498
+ cacheRead: 0,
12499
+ cacheWrite: 0,
12500
+ },
12501
+ contextWindow: 128000,
12502
+ maxTokens: 4096,
12503
+ },
11808
12504
  "openai/gpt-4.1": {
11809
12505
  id: "openai/gpt-4.1",
11810
12506
  name: "OpenAI: GPT-4.1",
@@ -11839,6 +12535,23 @@ export const MODELS = {
11839
12535
  contextWindow: 1047576,
11840
12536
  maxTokens: 32768,
11841
12537
  },
12538
+ "openai/gpt-4.1-mini:batch": {
12539
+ id: "openai/gpt-4.1-mini:batch",
12540
+ name: "OpenAI: GPT-4.1 Mini (batch)",
12541
+ api: "openai-completions",
12542
+ provider: "openrouter",
12543
+ baseUrl: "https://openrouter.ai/api/v1",
12544
+ reasoning: false,
12545
+ input: ["text", "image"],
12546
+ cost: {
12547
+ input: 0.19999999999999998,
12548
+ output: 0.7999999999999999,
12549
+ cacheRead: 0.049999999999999996,
12550
+ cacheWrite: 0,
12551
+ },
12552
+ contextWindow: 1047576,
12553
+ maxTokens: 32768,
12554
+ },
11842
12555
  "openai/gpt-4.1-nano": {
11843
12556
  id: "openai/gpt-4.1-nano",
11844
12557
  name: "OpenAI: GPT-4.1 Nano",
@@ -11856,6 +12569,40 @@ export const MODELS = {
11856
12569
  contextWindow: 1047576,
11857
12570
  maxTokens: 32768,
11858
12571
  },
12572
+ "openai/gpt-4.1-nano:batch": {
12573
+ id: "openai/gpt-4.1-nano:batch",
12574
+ name: "OpenAI: GPT-4.1 Nano (batch)",
12575
+ api: "openai-completions",
12576
+ provider: "openrouter",
12577
+ baseUrl: "https://openrouter.ai/api/v1",
12578
+ reasoning: false,
12579
+ input: ["text", "image"],
12580
+ cost: {
12581
+ input: 0.049999999999999996,
12582
+ output: 0.19999999999999998,
12583
+ cacheRead: 0.012499999999999999,
12584
+ cacheWrite: 0,
12585
+ },
12586
+ contextWindow: 1047576,
12587
+ maxTokens: 32768,
12588
+ },
12589
+ "openai/gpt-4.1:batch": {
12590
+ id: "openai/gpt-4.1:batch",
12591
+ name: "OpenAI: GPT-4.1 (batch)",
12592
+ api: "openai-completions",
12593
+ provider: "openrouter",
12594
+ baseUrl: "https://openrouter.ai/api/v1",
12595
+ reasoning: false,
12596
+ input: ["text", "image"],
12597
+ cost: {
12598
+ input: 1,
12599
+ output: 4,
12600
+ cacheRead: 0.25,
12601
+ cacheWrite: 0,
12602
+ },
12603
+ contextWindow: 1047576,
12604
+ maxTokens: 32768,
12605
+ },
11859
12606
  "openai/gpt-4o": {
11860
12607
  id: "openai/gpt-4o",
11861
12608
  name: "OpenAI: GPT-4o",
@@ -11890,6 +12637,40 @@ export const MODELS = {
11890
12637
  contextWindow: 128000,
11891
12638
  maxTokens: 16384,
11892
12639
  },
12640
+ "openai/gpt-4o-mini:batch": {
12641
+ id: "openai/gpt-4o-mini:batch",
12642
+ name: "OpenAI: GPT-4o-mini (batch)",
12643
+ api: "openai-completions",
12644
+ provider: "openrouter",
12645
+ baseUrl: "https://openrouter.ai/api/v1",
12646
+ reasoning: false,
12647
+ input: ["text", "image"],
12648
+ cost: {
12649
+ input: 0.075,
12650
+ output: 0.3,
12651
+ cacheRead: 0.0375,
12652
+ cacheWrite: 0,
12653
+ },
12654
+ contextWindow: 128000,
12655
+ maxTokens: 16384,
12656
+ },
12657
+ "openai/gpt-4o:batch": {
12658
+ id: "openai/gpt-4o:batch",
12659
+ name: "OpenAI: GPT-4o (batch)",
12660
+ api: "openai-completions",
12661
+ provider: "openrouter",
12662
+ baseUrl: "https://openrouter.ai/api/v1",
12663
+ reasoning: false,
12664
+ input: ["text", "image"],
12665
+ cost: {
12666
+ input: 1.25,
12667
+ output: 5,
12668
+ cacheRead: 0.625,
12669
+ cacheWrite: 0,
12670
+ },
12671
+ contextWindow: 128000,
12672
+ maxTokens: 16384,
12673
+ },
11893
12674
  "openai/gpt-5": {
11894
12675
  id: "openai/gpt-5",
11895
12676
  name: "OpenAI: GPT-5",
@@ -11907,18 +12688,18 @@ export const MODELS = {
11907
12688
  contextWindow: 400000,
11908
12689
  maxTokens: 128000,
11909
12690
  },
11910
- "openai/gpt-5-codex": {
11911
- id: "openai/gpt-5-codex",
11912
- name: "OpenAI: GPT-5 Codex",
12691
+ "openai/gpt-5-codex:batch": {
12692
+ id: "openai/gpt-5-codex:batch",
12693
+ name: "OpenAI: GPT-5 Codex (batch)",
11913
12694
  api: "openai-completions",
11914
12695
  provider: "openrouter",
11915
12696
  baseUrl: "https://openrouter.ai/api/v1",
11916
12697
  reasoning: true,
11917
12698
  input: ["text", "image"],
11918
12699
  cost: {
11919
- input: 1.25,
11920
- output: 10,
11921
- cacheRead: 0.125,
12700
+ input: 0.625,
12701
+ output: 5,
12702
+ cacheRead: 0.0625,
11922
12703
  cacheWrite: 0,
11923
12704
  },
11924
12705
  contextWindow: 400000,
@@ -11941,6 +12722,23 @@ export const MODELS = {
11941
12722
  contextWindow: 400000,
11942
12723
  maxTokens: 128000,
11943
12724
  },
12725
+ "openai/gpt-5-mini:batch": {
12726
+ id: "openai/gpt-5-mini:batch",
12727
+ name: "OpenAI: GPT-5 Mini (batch)",
12728
+ api: "openai-completions",
12729
+ provider: "openrouter",
12730
+ baseUrl: "https://openrouter.ai/api/v1",
12731
+ reasoning: true,
12732
+ input: ["text", "image"],
12733
+ cost: {
12734
+ input: 0.125,
12735
+ output: 1,
12736
+ cacheRead: 0.012499999999999999,
12737
+ cacheWrite: 0,
12738
+ },
12739
+ contextWindow: 400000,
12740
+ maxTokens: 128000,
12741
+ },
11944
12742
  "openai/gpt-5-nano": {
11945
12743
  id: "openai/gpt-5-nano",
11946
12744
  name: "OpenAI: GPT-5 Nano",
@@ -11958,6 +12756,23 @@ export const MODELS = {
11958
12756
  contextWindow: 400000,
11959
12757
  maxTokens: 128000,
11960
12758
  },
12759
+ "openai/gpt-5-nano:batch": {
12760
+ id: "openai/gpt-5-nano:batch",
12761
+ name: "OpenAI: GPT-5 Nano (batch)",
12762
+ api: "openai-completions",
12763
+ provider: "openrouter",
12764
+ baseUrl: "https://openrouter.ai/api/v1",
12765
+ reasoning: true,
12766
+ input: ["text", "image"],
12767
+ cost: {
12768
+ input: 0.024999999999999998,
12769
+ output: 0.19999999999999998,
12770
+ cacheRead: 0.0025,
12771
+ cacheWrite: 0,
12772
+ },
12773
+ contextWindow: 400000,
12774
+ maxTokens: 128000,
12775
+ },
11961
12776
  "openai/gpt-5-pro": {
11962
12777
  id: "openai/gpt-5-pro",
11963
12778
  name: "OpenAI: GPT-5 Pro",
@@ -11975,30 +12790,30 @@ export const MODELS = {
11975
12790
  contextWindow: 400000,
11976
12791
  maxTokens: 128000,
11977
12792
  },
11978
- "openai/gpt-5.1": {
11979
- id: "openai/gpt-5.1",
11980
- name: "OpenAI: GPT-5.1",
12793
+ "openai/gpt-5-pro:batch": {
12794
+ id: "openai/gpt-5-pro:batch",
12795
+ name: "OpenAI: GPT-5 Pro (batch)",
11981
12796
  api: "openai-completions",
11982
12797
  provider: "openrouter",
11983
12798
  baseUrl: "https://openrouter.ai/api/v1",
11984
12799
  reasoning: true,
11985
12800
  input: ["text", "image"],
11986
12801
  cost: {
11987
- input: 1.25,
11988
- output: 10,
11989
- cacheRead: 0.125,
12802
+ input: 7.5,
12803
+ output: 60,
12804
+ cacheRead: 0,
11990
12805
  cacheWrite: 0,
11991
12806
  },
11992
12807
  contextWindow: 400000,
11993
12808
  maxTokens: 128000,
11994
12809
  },
11995
- "openai/gpt-5.1-chat": {
11996
- id: "openai/gpt-5.1-chat",
11997
- name: "OpenAI: GPT-5.1 Chat",
12810
+ "openai/gpt-5.1": {
12811
+ id: "openai/gpt-5.1",
12812
+ name: "OpenAI: GPT-5.1",
11998
12813
  api: "openai-completions",
11999
12814
  provider: "openrouter",
12000
12815
  baseUrl: "https://openrouter.ai/api/v1",
12001
- reasoning: false,
12816
+ reasoning: true,
12002
12817
  input: ["text", "image"],
12003
12818
  cost: {
12004
12819
  input: 1.25,
@@ -12006,8 +12821,8 @@ export const MODELS = {
12006
12821
  cacheRead: 0.125,
12007
12822
  cacheWrite: 0,
12008
12823
  },
12009
- contextWindow: 128000,
12010
- maxTokens: 16384,
12824
+ contextWindow: 400000,
12825
+ maxTokens: 128000,
12011
12826
  },
12012
12827
  "openai/gpt-5.1-codex": {
12013
12828
  id: "openai/gpt-5.1-codex",
@@ -12020,7 +12835,7 @@ export const MODELS = {
12020
12835
  cost: {
12021
12836
  input: 1.25,
12022
12837
  output: 10,
12023
- cacheRead: 0.125,
12838
+ cacheRead: 0.13,
12024
12839
  cacheWrite: 0,
12025
12840
  },
12026
12841
  contextWindow: 400000,
@@ -12054,11 +12869,28 @@ export const MODELS = {
12054
12869
  cost: {
12055
12870
  input: 0.25,
12056
12871
  output: 2,
12057
- cacheRead: 0.024999999999999998,
12872
+ cacheRead: 0.03,
12058
12873
  cacheWrite: 0,
12059
12874
  },
12060
12875
  contextWindow: 400000,
12061
- maxTokens: 100000,
12876
+ maxTokens: 128000,
12877
+ },
12878
+ "openai/gpt-5.1:batch": {
12879
+ id: "openai/gpt-5.1:batch",
12880
+ name: "OpenAI: GPT-5.1 (batch)",
12881
+ api: "openai-completions",
12882
+ provider: "openrouter",
12883
+ baseUrl: "https://openrouter.ai/api/v1",
12884
+ reasoning: true,
12885
+ input: ["text", "image"],
12886
+ cost: {
12887
+ input: 0.625,
12888
+ output: 5,
12889
+ cacheRead: 0.0625,
12890
+ cacheWrite: 0,
12891
+ },
12892
+ contextWindow: 400000,
12893
+ maxTokens: 128000,
12062
12894
  },
12063
12895
  "openai/gpt-5.2": {
12064
12896
  id: "openai/gpt-5.2",
@@ -12132,6 +12964,42 @@ export const MODELS = {
12132
12964
  contextWindow: 400000,
12133
12965
  maxTokens: 128000,
12134
12966
  },
12967
+ "openai/gpt-5.2-pro:batch": {
12968
+ id: "openai/gpt-5.2-pro:batch",
12969
+ name: "OpenAI: GPT-5.2 Pro (batch)",
12970
+ api: "openai-completions",
12971
+ provider: "openrouter",
12972
+ baseUrl: "https://openrouter.ai/api/v1",
12973
+ reasoning: true,
12974
+ thinkingLevelMap: { "xhigh": "xhigh" },
12975
+ input: ["text", "image"],
12976
+ cost: {
12977
+ input: 10.5,
12978
+ output: 84,
12979
+ cacheRead: 0,
12980
+ cacheWrite: 0,
12981
+ },
12982
+ contextWindow: 400000,
12983
+ maxTokens: 128000,
12984
+ },
12985
+ "openai/gpt-5.2:batch": {
12986
+ id: "openai/gpt-5.2:batch",
12987
+ name: "OpenAI: GPT-5.2 (batch)",
12988
+ api: "openai-completions",
12989
+ provider: "openrouter",
12990
+ baseUrl: "https://openrouter.ai/api/v1",
12991
+ reasoning: true,
12992
+ thinkingLevelMap: { "xhigh": "xhigh" },
12993
+ input: ["text", "image"],
12994
+ cost: {
12995
+ input: 0.875,
12996
+ output: 7,
12997
+ cacheRead: 0.0875,
12998
+ cacheWrite: 0,
12999
+ },
13000
+ contextWindow: 400000,
13001
+ maxTokens: 128000,
13002
+ },
12135
13003
  "openai/gpt-5.3-chat": {
12136
13004
  id: "openai/gpt-5.3-chat",
12137
13005
  name: "OpenAI: GPT-5.3 Chat",
@@ -12204,6 +13072,24 @@ export const MODELS = {
12204
13072
  contextWindow: 400000,
12205
13073
  maxTokens: 128000,
12206
13074
  },
13075
+ "openai/gpt-5.4-mini:batch": {
13076
+ id: "openai/gpt-5.4-mini:batch",
13077
+ name: "OpenAI: GPT-5.4 Mini (batch)",
13078
+ api: "openai-completions",
13079
+ provider: "openrouter",
13080
+ baseUrl: "https://openrouter.ai/api/v1",
13081
+ reasoning: true,
13082
+ thinkingLevelMap: { "xhigh": "xhigh" },
13083
+ input: ["text", "image"],
13084
+ cost: {
13085
+ input: 0.375,
13086
+ output: 2.25,
13087
+ cacheRead: 0.0375,
13088
+ cacheWrite: 0,
13089
+ },
13090
+ contextWindow: 400000,
13091
+ maxTokens: 128000,
13092
+ },
12207
13093
  "openai/gpt-5.4-nano": {
12208
13094
  id: "openai/gpt-5.4-nano",
12209
13095
  name: "OpenAI: GPT-5.4 Nano",
@@ -12222,6 +13108,24 @@ export const MODELS = {
12222
13108
  contextWindow: 400000,
12223
13109
  maxTokens: 128000,
12224
13110
  },
13111
+ "openai/gpt-5.4-nano:batch": {
13112
+ id: "openai/gpt-5.4-nano:batch",
13113
+ name: "OpenAI: GPT-5.4 Nano (batch)",
13114
+ api: "openai-completions",
13115
+ provider: "openrouter",
13116
+ baseUrl: "https://openrouter.ai/api/v1",
13117
+ reasoning: true,
13118
+ thinkingLevelMap: { "xhigh": "xhigh" },
13119
+ input: ["text", "image"],
13120
+ cost: {
13121
+ input: 0.09999999999999999,
13122
+ output: 0.625,
13123
+ cacheRead: 0.01,
13124
+ cacheWrite: 0,
13125
+ },
13126
+ contextWindow: 400000,
13127
+ maxTokens: 128000,
13128
+ },
12225
13129
  "openai/gpt-5.4-pro": {
12226
13130
  id: "openai/gpt-5.4-pro",
12227
13131
  name: "OpenAI: GPT-5.4 Pro",
@@ -12240,62 +13144,253 @@ export const MODELS = {
12240
13144
  contextWindow: 1050000,
12241
13145
  maxTokens: 128000,
12242
13146
  },
12243
- "openai/gpt-5.5": {
12244
- id: "openai/gpt-5.5",
12245
- name: "OpenAI: GPT-5.5",
13147
+ "openai/gpt-5.4-pro:batch": {
13148
+ id: "openai/gpt-5.4-pro:batch",
13149
+ name: "OpenAI: GPT-5.4 Pro (batch)",
13150
+ api: "openai-completions",
13151
+ provider: "openrouter",
13152
+ baseUrl: "https://openrouter.ai/api/v1",
13153
+ reasoning: true,
13154
+ thinkingLevelMap: { "xhigh": "xhigh" },
13155
+ input: ["text", "image"],
13156
+ cost: {
13157
+ input: 15,
13158
+ output: 90,
13159
+ cacheRead: 0,
13160
+ cacheWrite: 0,
13161
+ },
13162
+ contextWindow: 1050000,
13163
+ maxTokens: 128000,
13164
+ },
13165
+ "openai/gpt-5.4:batch": {
13166
+ id: "openai/gpt-5.4:batch",
13167
+ name: "OpenAI: GPT-5.4 (batch)",
13168
+ api: "openai-completions",
13169
+ provider: "openrouter",
13170
+ baseUrl: "https://openrouter.ai/api/v1",
13171
+ reasoning: true,
13172
+ thinkingLevelMap: { "xhigh": "xhigh" },
13173
+ input: ["text", "image"],
13174
+ cost: {
13175
+ input: 1.25,
13176
+ output: 7.5,
13177
+ cacheRead: 0.125,
13178
+ cacheWrite: 0,
13179
+ },
13180
+ contextWindow: 1050000,
13181
+ maxTokens: 128000,
13182
+ },
13183
+ "openai/gpt-5.5": {
13184
+ id: "openai/gpt-5.5",
13185
+ name: "OpenAI: GPT-5.5",
13186
+ api: "openai-completions",
13187
+ provider: "openrouter",
13188
+ baseUrl: "https://openrouter.ai/api/v1",
13189
+ reasoning: true,
13190
+ thinkingLevelMap: { "xhigh": "xhigh" },
13191
+ input: ["text", "image"],
13192
+ cost: {
13193
+ input: 5,
13194
+ output: 30,
13195
+ cacheRead: 0.5,
13196
+ cacheWrite: 0,
13197
+ },
13198
+ contextWindow: 1050000,
13199
+ maxTokens: 128000,
13200
+ },
13201
+ "openai/gpt-5.5-pro": {
13202
+ id: "openai/gpt-5.5-pro",
13203
+ name: "OpenAI: GPT-5.5 Pro",
13204
+ api: "openai-completions",
13205
+ provider: "openrouter",
13206
+ baseUrl: "https://openrouter.ai/api/v1",
13207
+ reasoning: true,
13208
+ thinkingLevelMap: { "xhigh": "xhigh" },
13209
+ input: ["text", "image"],
13210
+ cost: {
13211
+ input: 30,
13212
+ output: 180,
13213
+ cacheRead: 0,
13214
+ cacheWrite: 0,
13215
+ },
13216
+ contextWindow: 1050000,
13217
+ maxTokens: 128000,
13218
+ },
13219
+ "openai/gpt-5.5-pro:batch": {
13220
+ id: "openai/gpt-5.5-pro:batch",
13221
+ name: "OpenAI: GPT-5.5 Pro (batch)",
13222
+ api: "openai-completions",
13223
+ provider: "openrouter",
13224
+ baseUrl: "https://openrouter.ai/api/v1",
13225
+ reasoning: true,
13226
+ thinkingLevelMap: { "xhigh": "xhigh" },
13227
+ input: ["text", "image"],
13228
+ cost: {
13229
+ input: 15,
13230
+ output: 90,
13231
+ cacheRead: 0,
13232
+ cacheWrite: 0,
13233
+ },
13234
+ contextWindow: 1050000,
13235
+ maxTokens: 128000,
13236
+ },
13237
+ "openai/gpt-5.5:batch": {
13238
+ id: "openai/gpt-5.5:batch",
13239
+ name: "OpenAI: GPT-5.5 (batch)",
13240
+ api: "openai-completions",
13241
+ provider: "openrouter",
13242
+ baseUrl: "https://openrouter.ai/api/v1",
13243
+ reasoning: true,
13244
+ thinkingLevelMap: { "xhigh": "xhigh" },
13245
+ input: ["text", "image"],
13246
+ cost: {
13247
+ input: 2.5,
13248
+ output: 15,
13249
+ cacheRead: 0.25,
13250
+ cacheWrite: 0,
13251
+ },
13252
+ contextWindow: 1050000,
13253
+ maxTokens: 128000,
13254
+ },
13255
+ "openai/gpt-5.6-luna": {
13256
+ id: "openai/gpt-5.6-luna",
13257
+ name: "OpenAI: GPT-5.6 Luna",
13258
+ api: "openai-completions",
13259
+ provider: "openrouter",
13260
+ baseUrl: "https://openrouter.ai/api/v1",
13261
+ reasoning: true,
13262
+ input: ["text", "image"],
13263
+ cost: {
13264
+ input: 0.09999999999999999,
13265
+ output: 0.6,
13266
+ cacheRead: 0.01,
13267
+ cacheWrite: 0.125,
13268
+ },
13269
+ contextWindow: 1050000,
13270
+ maxTokens: 128000,
13271
+ },
13272
+ "openai/gpt-5.6-luna-pro": {
13273
+ id: "openai/gpt-5.6-luna-pro",
13274
+ name: "OpenAI: GPT-5.6 Luna Pro",
13275
+ api: "openai-completions",
13276
+ provider: "openrouter",
13277
+ baseUrl: "https://openrouter.ai/api/v1",
13278
+ reasoning: true,
13279
+ input: ["text", "image"],
13280
+ cost: {
13281
+ input: 0.09999999999999999,
13282
+ output: 0.6,
13283
+ cacheRead: 0.01,
13284
+ cacheWrite: 0.125,
13285
+ },
13286
+ contextWindow: 1050000,
13287
+ maxTokens: 128000,
13288
+ },
13289
+ "openai/gpt-5.6-luna-pro:batch": {
13290
+ id: "openai/gpt-5.6-luna-pro:batch",
13291
+ name: "OpenAI: GPT-5.6 Luna Pro (batch)",
13292
+ api: "openai-completions",
13293
+ provider: "openrouter",
13294
+ baseUrl: "https://openrouter.ai/api/v1",
13295
+ reasoning: true,
13296
+ input: ["text", "image"],
13297
+ cost: {
13298
+ input: 0.09999999999999999,
13299
+ output: 0.6,
13300
+ cacheRead: 0.01,
13301
+ cacheWrite: 0,
13302
+ },
13303
+ contextWindow: 1050000,
13304
+ maxTokens: 128000,
13305
+ },
13306
+ "openai/gpt-5.6-luna:batch": {
13307
+ id: "openai/gpt-5.6-luna:batch",
13308
+ name: "OpenAI: GPT-5.6 Luna (batch)",
13309
+ api: "openai-completions",
13310
+ provider: "openrouter",
13311
+ baseUrl: "https://openrouter.ai/api/v1",
13312
+ reasoning: true,
13313
+ input: ["text", "image"],
13314
+ cost: {
13315
+ input: 0.09999999999999999,
13316
+ output: 0.6,
13317
+ cacheRead: 0.01,
13318
+ cacheWrite: 0,
13319
+ },
13320
+ contextWindow: 1050000,
13321
+ maxTokens: 128000,
13322
+ },
13323
+ "openai/gpt-5.6-sol": {
13324
+ id: "openai/gpt-5.6-sol",
13325
+ name: "OpenAI: GPT-5.6 Sol",
13326
+ api: "openai-completions",
13327
+ provider: "openrouter",
13328
+ baseUrl: "https://openrouter.ai/api/v1",
13329
+ reasoning: true,
13330
+ input: ["text", "image"],
13331
+ cost: {
13332
+ input: 5,
13333
+ output: 30,
13334
+ cacheRead: 0.5,
13335
+ cacheWrite: 6.25,
13336
+ },
13337
+ contextWindow: 1050000,
13338
+ maxTokens: 128000,
13339
+ },
13340
+ "openai/gpt-5.6-sol-pro": {
13341
+ id: "openai/gpt-5.6-sol-pro",
13342
+ name: "OpenAI: GPT-5.6 Sol Pro",
12246
13343
  api: "openai-completions",
12247
13344
  provider: "openrouter",
12248
13345
  baseUrl: "https://openrouter.ai/api/v1",
12249
13346
  reasoning: true,
12250
- thinkingLevelMap: { "xhigh": "xhigh" },
12251
13347
  input: ["text", "image"],
12252
13348
  cost: {
12253
13349
  input: 5,
12254
13350
  output: 30,
12255
13351
  cacheRead: 0.5,
12256
- cacheWrite: 0,
13352
+ cacheWrite: 6.25,
12257
13353
  },
12258
13354
  contextWindow: 1050000,
12259
13355
  maxTokens: 128000,
12260
13356
  },
12261
- "openai/gpt-5.5-pro": {
12262
- id: "openai/gpt-5.5-pro",
12263
- name: "OpenAI: GPT-5.5 Pro",
13357
+ "openai/gpt-5.6-sol-pro:batch": {
13358
+ id: "openai/gpt-5.6-sol-pro:batch",
13359
+ name: "OpenAI: GPT-5.6 Sol Pro (batch)",
12264
13360
  api: "openai-completions",
12265
13361
  provider: "openrouter",
12266
13362
  baseUrl: "https://openrouter.ai/api/v1",
12267
13363
  reasoning: true,
12268
- thinkingLevelMap: { "xhigh": "xhigh" },
12269
13364
  input: ["text", "image"],
12270
13365
  cost: {
12271
- input: 30,
12272
- output: 180,
12273
- cacheRead: 0,
13366
+ input: 2.5,
13367
+ output: 15,
13368
+ cacheRead: 0.25,
12274
13369
  cacheWrite: 0,
12275
13370
  },
12276
13371
  contextWindow: 1050000,
12277
13372
  maxTokens: 128000,
12278
13373
  },
12279
- "openai/gpt-5.6-luna": {
12280
- id: "openai/gpt-5.6-luna",
12281
- name: "OpenAI: GPT-5.6 Luna",
13374
+ "openai/gpt-5.6-sol:batch": {
13375
+ id: "openai/gpt-5.6-sol:batch",
13376
+ name: "OpenAI: GPT-5.6 Sol (batch)",
12282
13377
  api: "openai-completions",
12283
13378
  provider: "openrouter",
12284
13379
  baseUrl: "https://openrouter.ai/api/v1",
12285
13380
  reasoning: true,
12286
13381
  input: ["text", "image"],
12287
13382
  cost: {
12288
- input: 1,
12289
- output: 6,
12290
- cacheRead: 0.09999999999999999,
12291
- cacheWrite: 1.25,
13383
+ input: 2.5,
13384
+ output: 15,
13385
+ cacheRead: 0.25,
13386
+ cacheWrite: 0,
12292
13387
  },
12293
13388
  contextWindow: 1050000,
12294
13389
  maxTokens: 128000,
12295
13390
  },
12296
- "openai/gpt-5.6-luna-pro": {
12297
- id: "openai/gpt-5.6-luna-pro",
12298
- name: "OpenAI: GPT-5.6 Luna Pro",
13391
+ "openai/gpt-5.6-terra": {
13392
+ id: "openai/gpt-5.6-terra",
13393
+ name: "OpenAI: GPT-5.6 Terra",
12299
13394
  api: "openai-completions",
12300
13395
  provider: "openrouter",
12301
13396
  baseUrl: "https://openrouter.ai/api/v1",
@@ -12310,72 +13405,72 @@ export const MODELS = {
12310
13405
  contextWindow: 1050000,
12311
13406
  maxTokens: 128000,
12312
13407
  },
12313
- "openai/gpt-5.6-sol": {
12314
- id: "openai/gpt-5.6-sol",
12315
- name: "OpenAI: GPT-5.6 Sol",
13408
+ "openai/gpt-5.6-terra-pro": {
13409
+ id: "openai/gpt-5.6-terra-pro",
13410
+ name: "OpenAI: GPT-5.6 Terra Pro",
12316
13411
  api: "openai-completions",
12317
13412
  provider: "openrouter",
12318
13413
  baseUrl: "https://openrouter.ai/api/v1",
12319
13414
  reasoning: true,
12320
13415
  input: ["text", "image"],
12321
13416
  cost: {
12322
- input: 5,
12323
- output: 30,
12324
- cacheRead: 0.5,
12325
- cacheWrite: 6.25,
13417
+ input: 1,
13418
+ output: 6,
13419
+ cacheRead: 0.09999999999999999,
13420
+ cacheWrite: 1.25,
12326
13421
  },
12327
13422
  contextWindow: 1050000,
12328
13423
  maxTokens: 128000,
12329
13424
  },
12330
- "openai/gpt-5.6-sol-pro": {
12331
- id: "openai/gpt-5.6-sol-pro",
12332
- name: "OpenAI: GPT-5.6 Sol Pro",
13425
+ "openai/gpt-5.6-terra-pro:batch": {
13426
+ id: "openai/gpt-5.6-terra-pro:batch",
13427
+ name: "OpenAI: GPT-5.6 Terra Pro (batch)",
12333
13428
  api: "openai-completions",
12334
13429
  provider: "openrouter",
12335
13430
  baseUrl: "https://openrouter.ai/api/v1",
12336
13431
  reasoning: true,
12337
13432
  input: ["text", "image"],
12338
13433
  cost: {
12339
- input: 5,
12340
- output: 30,
12341
- cacheRead: 0.5,
12342
- cacheWrite: 6.25,
13434
+ input: 1,
13435
+ output: 6,
13436
+ cacheRead: 0.09999999999999999,
13437
+ cacheWrite: 0,
12343
13438
  },
12344
13439
  contextWindow: 1050000,
12345
13440
  maxTokens: 128000,
12346
13441
  },
12347
- "openai/gpt-5.6-terra": {
12348
- id: "openai/gpt-5.6-terra",
12349
- name: "OpenAI: GPT-5.6 Terra",
13442
+ "openai/gpt-5.6-terra:batch": {
13443
+ id: "openai/gpt-5.6-terra:batch",
13444
+ name: "OpenAI: GPT-5.6 Terra (batch)",
12350
13445
  api: "openai-completions",
12351
13446
  provider: "openrouter",
12352
13447
  baseUrl: "https://openrouter.ai/api/v1",
12353
13448
  reasoning: true,
12354
13449
  input: ["text", "image"],
12355
13450
  cost: {
12356
- input: 2.5,
12357
- output: 15,
12358
- cacheRead: 0.25,
12359
- cacheWrite: 3.125,
13451
+ input: 1,
13452
+ output: 6,
13453
+ cacheRead: 0.09999999999999999,
13454
+ cacheWrite: 0,
12360
13455
  },
12361
13456
  contextWindow: 1050000,
12362
13457
  maxTokens: 128000,
12363
13458
  },
12364
- "openai/gpt-5.6-terra-pro": {
12365
- id: "openai/gpt-5.6-terra-pro",
12366
- name: "OpenAI: GPT-5.6 Terra Pro",
13459
+ "openai/gpt-5:batch": {
13460
+ id: "openai/gpt-5:batch",
13461
+ name: "OpenAI: GPT-5 (batch)",
12367
13462
  api: "openai-completions",
12368
13463
  provider: "openrouter",
12369
13464
  baseUrl: "https://openrouter.ai/api/v1",
12370
13465
  reasoning: true,
12371
13466
  input: ["text", "image"],
12372
13467
  cost: {
12373
- input: 2.5,
12374
- output: 15,
12375
- cacheRead: 0.25,
12376
- cacheWrite: 3.125,
13468
+ input: 0.625,
13469
+ output: 5,
13470
+ cacheRead: 0.0625,
13471
+ cacheWrite: 0,
12377
13472
  },
12378
- contextWindow: 1050000,
13473
+ contextWindow: 400000,
12379
13474
  maxTokens: 128000,
12380
13475
  },
12381
13476
  "openai/gpt-audio": {
@@ -12455,13 +13550,13 @@ export const MODELS = {
12455
13550
  reasoning: true,
12456
13551
  input: ["text"],
12457
13552
  cost: {
12458
- input: 0.029,
12459
- output: 0.14,
12460
- cacheRead: 0,
13553
+ input: 0.03,
13554
+ output: 0.13,
13555
+ cacheRead: 0.03,
12461
13556
  cacheWrite: 0,
12462
13557
  },
12463
13558
  contextWindow: 131072,
12464
- maxTokens: 4096,
13559
+ maxTokens: 131072,
12465
13560
  },
12466
13561
  "openai/gpt-oss-20b:free": {
12467
13562
  id: "openai/gpt-oss-20b:free",
@@ -12514,35 +13609,35 @@ export const MODELS = {
12514
13609
  contextWindow: 200000,
12515
13610
  maxTokens: 100000,
12516
13611
  },
12517
- "openai/o3": {
12518
- id: "openai/o3",
12519
- name: "OpenAI: o3",
13612
+ "openai/o1:batch": {
13613
+ id: "openai/o1:batch",
13614
+ name: "OpenAI: o1 (batch)",
12520
13615
  api: "openai-completions",
12521
13616
  provider: "openrouter",
12522
13617
  baseUrl: "https://openrouter.ai/api/v1",
12523
13618
  reasoning: true,
12524
13619
  input: ["text", "image"],
12525
13620
  cost: {
12526
- input: 2,
12527
- output: 8,
12528
- cacheRead: 0.5,
13621
+ input: 7.5,
13622
+ output: 30,
13623
+ cacheRead: 3.75,
12529
13624
  cacheWrite: 0,
12530
13625
  },
12531
13626
  contextWindow: 200000,
12532
13627
  maxTokens: 100000,
12533
13628
  },
12534
- "openai/o3-deep-research": {
12535
- id: "openai/o3-deep-research",
12536
- name: "OpenAI: o3 Deep Research",
13629
+ "openai/o3": {
13630
+ id: "openai/o3",
13631
+ name: "OpenAI: o3",
12537
13632
  api: "openai-completions",
12538
13633
  provider: "openrouter",
12539
13634
  baseUrl: "https://openrouter.ai/api/v1",
12540
13635
  reasoning: true,
12541
13636
  input: ["text", "image"],
12542
13637
  cost: {
12543
- input: 10,
12544
- output: 40,
12545
- cacheRead: 2.5,
13638
+ input: 2,
13639
+ output: 8,
13640
+ cacheRead: 0.5,
12546
13641
  cacheWrite: 0,
12547
13642
  },
12548
13643
  contextWindow: 200000,
@@ -12582,6 +13677,40 @@ export const MODELS = {
12582
13677
  contextWindow: 200000,
12583
13678
  maxTokens: 100000,
12584
13679
  },
13680
+ "openai/o3-mini-high:batch": {
13681
+ id: "openai/o3-mini-high:batch",
13682
+ name: "OpenAI: o3 Mini High (batch)",
13683
+ api: "openai-completions",
13684
+ provider: "openrouter",
13685
+ baseUrl: "https://openrouter.ai/api/v1",
13686
+ reasoning: true,
13687
+ input: ["text"],
13688
+ cost: {
13689
+ input: 0.55,
13690
+ output: 2.2,
13691
+ cacheRead: 0.275,
13692
+ cacheWrite: 0,
13693
+ },
13694
+ contextWindow: 200000,
13695
+ maxTokens: 100000,
13696
+ },
13697
+ "openai/o3-mini:batch": {
13698
+ id: "openai/o3-mini:batch",
13699
+ name: "OpenAI: o3 Mini (batch)",
13700
+ api: "openai-completions",
13701
+ provider: "openrouter",
13702
+ baseUrl: "https://openrouter.ai/api/v1",
13703
+ reasoning: true,
13704
+ input: ["text"],
13705
+ cost: {
13706
+ input: 0.55,
13707
+ output: 2.2,
13708
+ cacheRead: 0.275,
13709
+ cacheWrite: 0,
13710
+ },
13711
+ contextWindow: 200000,
13712
+ maxTokens: 100000,
13713
+ },
12585
13714
  "openai/o3-pro": {
12586
13715
  id: "openai/o3-pro",
12587
13716
  name: "OpenAI: o3 Pro",
@@ -12599,35 +13728,52 @@ export const MODELS = {
12599
13728
  contextWindow: 200000,
12600
13729
  maxTokens: 100000,
12601
13730
  },
12602
- "openai/o4-mini": {
12603
- id: "openai/o4-mini",
12604
- name: "OpenAI: o4 Mini",
13731
+ "openai/o3-pro:batch": {
13732
+ id: "openai/o3-pro:batch",
13733
+ name: "OpenAI: o3 Pro (batch)",
12605
13734
  api: "openai-completions",
12606
13735
  provider: "openrouter",
12607
13736
  baseUrl: "https://openrouter.ai/api/v1",
12608
13737
  reasoning: true,
12609
13738
  input: ["text", "image"],
12610
13739
  cost: {
12611
- input: 1.1,
12612
- output: 4.4,
12613
- cacheRead: 0.275,
13740
+ input: 10,
13741
+ output: 40,
13742
+ cacheRead: 0,
12614
13743
  cacheWrite: 0,
12615
13744
  },
12616
13745
  contextWindow: 200000,
12617
13746
  maxTokens: 100000,
12618
13747
  },
12619
- "openai/o4-mini-deep-research": {
12620
- id: "openai/o4-mini-deep-research",
12621
- name: "OpenAI: o4 Mini Deep Research",
13748
+ "openai/o3:batch": {
13749
+ id: "openai/o3:batch",
13750
+ name: "OpenAI: o3 (batch)",
12622
13751
  api: "openai-completions",
12623
13752
  provider: "openrouter",
12624
13753
  baseUrl: "https://openrouter.ai/api/v1",
12625
13754
  reasoning: true,
12626
13755
  input: ["text", "image"],
12627
13756
  cost: {
12628
- input: 2,
12629
- output: 8,
12630
- cacheRead: 0.5,
13757
+ input: 1,
13758
+ output: 4,
13759
+ cacheRead: 0.25,
13760
+ cacheWrite: 0,
13761
+ },
13762
+ contextWindow: 200000,
13763
+ maxTokens: 100000,
13764
+ },
13765
+ "openai/o4-mini": {
13766
+ id: "openai/o4-mini",
13767
+ name: "OpenAI: o4 Mini",
13768
+ api: "openai-completions",
13769
+ provider: "openrouter",
13770
+ baseUrl: "https://openrouter.ai/api/v1",
13771
+ reasoning: true,
13772
+ input: ["text", "image"],
13773
+ cost: {
13774
+ input: 1.1,
13775
+ output: 4.4,
13776
+ cacheRead: 0.275,
12631
13777
  cacheWrite: 0,
12632
13778
  },
12633
13779
  contextWindow: 200000,
@@ -12650,6 +13796,40 @@ export const MODELS = {
12650
13796
  contextWindow: 200000,
12651
13797
  maxTokens: 100000,
12652
13798
  },
13799
+ "openai/o4-mini-high:batch": {
13800
+ id: "openai/o4-mini-high:batch",
13801
+ name: "OpenAI: o4 Mini High (batch)",
13802
+ api: "openai-completions",
13803
+ provider: "openrouter",
13804
+ baseUrl: "https://openrouter.ai/api/v1",
13805
+ reasoning: true,
13806
+ input: ["text", "image"],
13807
+ cost: {
13808
+ input: 0.55,
13809
+ output: 2.2,
13810
+ cacheRead: 0.1375,
13811
+ cacheWrite: 0,
13812
+ },
13813
+ contextWindow: 200000,
13814
+ maxTokens: 100000,
13815
+ },
13816
+ "openai/o4-mini:batch": {
13817
+ id: "openai/o4-mini:batch",
13818
+ name: "OpenAI: o4 Mini (batch)",
13819
+ api: "openai-completions",
13820
+ provider: "openrouter",
13821
+ baseUrl: "https://openrouter.ai/api/v1",
13822
+ reasoning: true,
13823
+ input: ["text", "image"],
13824
+ cost: {
13825
+ input: 0.55,
13826
+ output: 2.2,
13827
+ cacheRead: 0.1375,
13828
+ cacheWrite: 0,
13829
+ },
13830
+ contextWindow: 200000,
13831
+ maxTokens: 100000,
13832
+ },
12653
13833
  "openrouter/auto": {
12654
13834
  id: "openrouter/auto",
12655
13835
  name: "Auto Router",
@@ -12701,40 +13881,6 @@ export const MODELS = {
12701
13881
  contextWindow: 200000,
12702
13882
  maxTokens: 4096,
12703
13883
  },
12704
- "poolside/laguna-m.1": {
12705
- id: "poolside/laguna-m.1",
12706
- name: "Poolside: Laguna M.1",
12707
- api: "openai-completions",
12708
- provider: "openrouter",
12709
- baseUrl: "https://openrouter.ai/api/v1",
12710
- reasoning: true,
12711
- input: ["text"],
12712
- cost: {
12713
- input: 0.19999999999999998,
12714
- output: 0.39999999999999997,
12715
- cacheRead: 0.09999999999999999,
12716
- cacheWrite: 0,
12717
- },
12718
- contextWindow: 262144,
12719
- maxTokens: 32768,
12720
- },
12721
- "poolside/laguna-m.1:free": {
12722
- id: "poolside/laguna-m.1:free",
12723
- name: "Poolside: Laguna M.1 (free)",
12724
- api: "openai-completions",
12725
- provider: "openrouter",
12726
- baseUrl: "https://openrouter.ai/api/v1",
12727
- reasoning: true,
12728
- input: ["text"],
12729
- cost: {
12730
- input: 0,
12731
- output: 0,
12732
- cacheRead: 0,
12733
- cacheWrite: 0,
12734
- },
12735
- contextWindow: 262144,
12736
- maxTokens: 32768,
12737
- },
12738
13884
  "poolside/laguna-s-2.1": {
12739
13885
  id: "poolside/laguna-s-2.1",
12740
13886
  name: "Poolside: Laguna S 2.1",
@@ -12744,9 +13890,9 @@ export const MODELS = {
12744
13890
  reasoning: true,
12745
13891
  input: ["text"],
12746
13892
  cost: {
12747
- input: 0.09999999999999999,
12748
- output: 0.19999999999999998,
12749
- cacheRead: 0.01,
13893
+ input: 0.09,
13894
+ output: 0.18,
13895
+ cacheRead: 0.009,
12750
13896
  cacheWrite: 0,
12751
13897
  },
12752
13898
  contextWindow: 1048576,
@@ -12829,8 +13975,8 @@ export const MODELS = {
12829
13975
  reasoning: false,
12830
13976
  input: ["text"],
12831
13977
  cost: {
12832
- input: 0.04,
12833
- output: 0.09999999999999999,
13978
+ input: 0.09999999999999999,
13979
+ output: 0.19999999999999998,
12834
13980
  cacheRead: 0,
12835
13981
  cacheWrite: 0,
12836
13982
  },
@@ -12880,10 +14026,10 @@ export const MODELS = {
12880
14026
  reasoning: true,
12881
14027
  input: ["text"],
12882
14028
  cost: {
12883
- input: 0.26,
12884
- output: 0.78,
14029
+ input: 0.39999999999999997,
14030
+ output: 1.2,
12885
14031
  cacheRead: 0,
12886
- cacheWrite: 0.325,
14032
+ cacheWrite: 0.5,
12887
14033
  },
12888
14034
  contextWindow: 1000000,
12889
14035
  maxTokens: 32768,
@@ -12948,13 +14094,13 @@ export const MODELS = {
12948
14094
  reasoning: true,
12949
14095
  input: ["text"],
12950
14096
  cost: {
12951
- input: 0.3,
12952
- output: 3,
14097
+ input: 0.22999999999999998,
14098
+ output: 2.3,
12953
14099
  cacheRead: 0,
12954
14100
  cacheWrite: 0,
12955
14101
  },
12956
14102
  contextWindow: 262144,
12957
- maxTokens: 32768,
14103
+ maxTokens: 4096,
12958
14104
  },
12959
14105
  "qwen/qwen3-30b-a3b": {
12960
14106
  id: "qwen/qwen3-30b-a3b",
@@ -12965,13 +14111,13 @@ export const MODELS = {
12965
14111
  reasoning: true,
12966
14112
  input: ["text"],
12967
14113
  cost: {
12968
- input: 0.13,
12969
- output: 0.52,
14114
+ input: 0.12,
14115
+ output: 0.5,
12970
14116
  cacheRead: 0,
12971
14117
  cacheWrite: 0,
12972
14118
  },
12973
14119
  contextWindow: 131072,
12974
- maxTokens: 8192,
14120
+ maxTokens: 16384,
12975
14121
  },
12976
14122
  "qwen/qwen3-30b-a3b-instruct-2507": {
12977
14123
  id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -12982,13 +14128,13 @@ export const MODELS = {
12982
14128
  reasoning: false,
12983
14129
  input: ["text"],
12984
14130
  cost: {
12985
- input: 0.09999999999999999,
12986
- output: 0.3,
14131
+ input: 0.04815,
14132
+ output: 0.19305,
12987
14133
  cacheRead: 0,
12988
14134
  cacheWrite: 0,
12989
14135
  },
12990
14136
  contextWindow: 262144,
12991
- maxTokens: 4096,
14137
+ maxTokens: 32000,
12992
14138
  },
12993
14139
  "qwen/qwen3-30b-a3b-thinking-2507": {
12994
14140
  id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -12999,8 +14145,8 @@ export const MODELS = {
12999
14145
  reasoning: true,
13000
14146
  input: ["text"],
13001
14147
  cost: {
13002
- input: 0.13,
13003
- output: 1.56,
14148
+ input: 0.19999999999999998,
14149
+ output: 2.4,
13004
14150
  cacheRead: 0,
13005
14151
  cacheWrite: 0,
13006
14152
  },
@@ -13101,7 +14247,7 @@ export const MODELS = {
13101
14247
  reasoning: false,
13102
14248
  input: ["text"],
13103
14249
  cost: {
13104
- input: 0.11,
14250
+ input: 0.12,
13105
14251
  output: 0.7999999999999999,
13106
14252
  cacheRead: 0.07,
13107
14253
  cacheWrite: 0,
@@ -13141,7 +14287,7 @@ export const MODELS = {
13141
14287
  cacheWrite: 0.975,
13142
14288
  },
13143
14289
  contextWindow: 262144,
13144
- maxTokens: 32768,
14290
+ maxTokens: 65536,
13145
14291
  },
13146
14292
  "qwen/qwen3-max-thinking": {
13147
14293
  id: "qwen/qwen3-max-thinking",
@@ -13158,7 +14304,7 @@ export const MODELS = {
13158
14304
  cacheWrite: 0,
13159
14305
  },
13160
14306
  contextWindow: 262144,
13161
- maxTokens: 32768,
14307
+ maxTokens: 65536,
13162
14308
  },
13163
14309
  "qwen/qwen3-next-80b-a3b-instruct": {
13164
14310
  id: "qwen/qwen3-next-80b-a3b-instruct",
@@ -13169,13 +14315,13 @@ export const MODELS = {
13169
14315
  reasoning: false,
13170
14316
  input: ["text"],
13171
14317
  cost: {
13172
- input: 0.09999999999999999,
14318
+ input: 0.09,
13173
14319
  output: 1.1,
13174
- cacheRead: 0.07,
14320
+ cacheRead: 0,
13175
14321
  cacheWrite: 0,
13176
14322
  },
13177
14323
  contextWindow: 262144,
13178
- maxTokens: 262144,
14324
+ maxTokens: 16384,
13179
14325
  },
13180
14326
  "qwen/qwen3-next-80b-a3b-thinking": {
13181
14327
  id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -13186,13 +14332,13 @@ export const MODELS = {
13186
14332
  reasoning: true,
13187
14333
  input: ["text"],
13188
14334
  cost: {
13189
- input: 0.0975,
13190
- output: 0.78,
14335
+ input: 0.15,
14336
+ output: 1.2,
13191
14337
  cacheRead: 0,
13192
14338
  cacheWrite: 0,
13193
14339
  },
13194
14340
  contextWindow: 262144,
13195
- maxTokens: 32768,
14341
+ maxTokens: 4096,
13196
14342
  },
13197
14343
  "qwen/qwen3-vl-235b-a22b-instruct": {
13198
14344
  id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13220,8 +14366,8 @@ export const MODELS = {
13220
14366
  reasoning: true,
13221
14367
  input: ["text", "image"],
13222
14368
  cost: {
13223
- input: 0.26,
13224
- output: 2.6,
14369
+ input: 0.39999999999999997,
14370
+ output: 4,
13225
14371
  cacheRead: 0,
13226
14372
  cacheWrite: 0,
13227
14373
  },
@@ -13254,8 +14400,8 @@ export const MODELS = {
13254
14400
  reasoning: true,
13255
14401
  input: ["text", "image"],
13256
14402
  cost: {
13257
- input: 0.13,
13258
- output: 1.56,
14403
+ input: 0.19999999999999998,
14404
+ output: 2.4,
13259
14405
  cacheRead: 0,
13260
14406
  cacheWrite: 0,
13261
14407
  },
@@ -13305,8 +14451,8 @@ export const MODELS = {
13305
14451
  reasoning: true,
13306
14452
  input: ["text", "image"],
13307
14453
  cost: {
13308
- input: 0.117,
13309
- output: 1.365,
14454
+ input: 0.18,
14455
+ output: 2.0999999999999996,
13310
14456
  cacheRead: 0,
13311
14457
  cacheWrite: 0,
13312
14458
  },
@@ -13322,13 +14468,13 @@ export const MODELS = {
13322
14468
  reasoning: true,
13323
14469
  input: ["text", "image"],
13324
14470
  cost: {
13325
- input: 0.26,
13326
- output: 2.08,
14471
+ input: 0.29,
14472
+ output: 2.4,
13327
14473
  cacheRead: 0,
13328
14474
  cacheWrite: 0,
13329
14475
  },
13330
14476
  contextWindow: 262144,
13331
- maxTokens: 65536,
14477
+ maxTokens: 81920,
13332
14478
  },
13333
14479
  "qwen/qwen3.5-27b": {
13334
14480
  id: "qwen/qwen3.5-27b",
@@ -13458,13 +14604,13 @@ export const MODELS = {
13458
14604
  reasoning: true,
13459
14605
  input: ["text", "image"],
13460
14606
  cost: {
13461
- input: 0.288,
13462
- output: 2.4,
13463
- cacheRead: 0,
14607
+ input: 0.6,
14608
+ output: 3.5999999999999996,
14609
+ cacheRead: 0.12,
13464
14610
  cacheWrite: 0,
13465
14611
  },
13466
14612
  contextWindow: 262144,
13467
- maxTokens: 4096,
14613
+ maxTokens: 262144,
13468
14614
  },
13469
14615
  "qwen/qwen3.6-35b-a3b": {
13470
14616
  id: "qwen/qwen3.6-35b-a3b",
@@ -13477,7 +14623,7 @@ export const MODELS = {
13477
14623
  cost: {
13478
14624
  input: 0.14,
13479
14625
  output: 1,
13480
- cacheRead: 0,
14626
+ cacheRead: 0.049999999999999996,
13481
14627
  cacheWrite: 0,
13482
14628
  },
13483
14629
  contextWindow: 262144,
@@ -13509,10 +14655,10 @@ export const MODELS = {
13509
14655
  reasoning: true,
13510
14656
  input: ["text"],
13511
14657
  cost: {
13512
- input: 1.04,
13513
- output: 6.24,
14658
+ input: 1.0270000000000001,
14659
+ output: 6.162,
13514
14660
  cacheRead: 0,
13515
- cacheWrite: 1.3,
14661
+ cacheWrite: 1.28375,
13516
14662
  },
13517
14663
  contextWindow: 262144,
13518
14664
  maxTokens: 65536,
@@ -13534,6 +14680,23 @@ export const MODELS = {
13534
14680
  contextWindow: 1000000,
13535
14681
  maxTokens: 65536,
13536
14682
  },
14683
+ "qwen/qwen3.7-flash": {
14684
+ id: "qwen/qwen3.7-flash",
14685
+ name: "Qwen: Qwen3.7 Flash",
14686
+ api: "openai-completions",
14687
+ provider: "openrouter",
14688
+ baseUrl: "https://openrouter.ai/api/v1",
14689
+ reasoning: true,
14690
+ input: ["text", "image"],
14691
+ cost: {
14692
+ input: 0.03,
14693
+ output: 0.13,
14694
+ cacheRead: 0.006,
14695
+ cacheWrite: 0.038000000000000006,
14696
+ },
14697
+ contextWindow: 1000000,
14698
+ maxTokens: 65536,
14699
+ },
13537
14700
  "qwen/qwen3.7-max": {
13538
14701
  id: "qwen/qwen3.7-max",
13539
14702
  name: "Qwen: Qwen3.7 Max",
@@ -13549,7 +14712,7 @@ export const MODELS = {
13549
14712
  cacheWrite: 1.84375,
13550
14713
  },
13551
14714
  contextWindow: 1000000,
13552
- maxTokens: 65536,
14715
+ maxTokens: 131072,
13553
14716
  },
13554
14717
  "qwen/qwen3.7-plus": {
13555
14718
  id: "qwen/qwen3.7-plus",
@@ -13566,7 +14729,24 @@ export const MODELS = {
13566
14729
  cacheWrite: 0.39999999999999997,
13567
14730
  },
13568
14731
  contextWindow: 1000000,
13569
- maxTokens: 65536,
14732
+ maxTokens: 131072,
14733
+ },
14734
+ "qwen/qwen3.8-max": {
14735
+ id: "qwen/qwen3.8-max",
14736
+ name: "Qwen: Qwen3.8 Max",
14737
+ api: "openai-completions",
14738
+ provider: "openrouter",
14739
+ baseUrl: "https://openrouter.ai/api/v1",
14740
+ reasoning: true,
14741
+ input: ["text", "image"],
14742
+ cost: {
14743
+ input: 2,
14744
+ output: 6,
14745
+ cacheRead: 0.25,
14746
+ cacheWrite: 2.5,
14747
+ },
14748
+ contextWindow: 1000000,
14749
+ maxTokens: 131072,
13570
14750
  },
13571
14751
  "rekaai/reka-edge": {
13572
14752
  id: "rekaai/reka-edge",
@@ -13701,8 +14881,8 @@ export const MODELS = {
13701
14881
  cacheRead: 0,
13702
14882
  cacheWrite: 0,
13703
14883
  },
13704
- contextWindow: 32768,
13705
- maxTokens: 32768,
14884
+ contextWindow: 1024000,
14885
+ maxTokens: 1024000,
13706
14886
  },
13707
14887
  "thinkingmachines/inkling": {
13708
14888
  id: "thinkingmachines/inkling",
@@ -13721,6 +14901,40 @@ export const MODELS = {
13721
14901
  contextWindow: 1048576,
13722
14902
  maxTokens: 4096,
13723
14903
  },
14904
+ "thinkingmachines/inkling-small": {
14905
+ id: "thinkingmachines/inkling-small",
14906
+ name: "Thinking Machines: Inkling Small",
14907
+ api: "openai-completions",
14908
+ provider: "openrouter",
14909
+ baseUrl: "https://openrouter.ai/api/v1",
14910
+ reasoning: true,
14911
+ input: ["text", "image"],
14912
+ cost: {
14913
+ input: 0.44999999999999996,
14914
+ output: 1.2,
14915
+ cacheRead: 0.09999999999999999,
14916
+ cacheWrite: 0,
14917
+ },
14918
+ contextWindow: 524288,
14919
+ maxTokens: 262144,
14920
+ },
14921
+ "thinkingmachines/inkling:batch": {
14922
+ id: "thinkingmachines/inkling:batch",
14923
+ name: "Thinking Machines: Inkling (batch)",
14924
+ api: "openai-completions",
14925
+ provider: "openrouter",
14926
+ baseUrl: "https://openrouter.ai/api/v1",
14927
+ reasoning: true,
14928
+ input: ["text", "image"],
14929
+ cost: {
14930
+ input: 0.5,
14931
+ output: 2.025,
14932
+ cacheRead: 0.08499999999999999,
14933
+ cacheWrite: 0,
14934
+ },
14935
+ contextWindow: 524288,
14936
+ maxTokens: 4096,
14937
+ },
13724
14938
  "upstage/solar-pro-3": {
13725
14939
  id: "upstage/solar-pro-3",
13726
14940
  name: "Upstage: Solar Pro 3",
@@ -13735,12 +14949,12 @@ export const MODELS = {
13735
14949
  cacheRead: 0.015,
13736
14950
  cacheWrite: 0,
13737
14951
  },
13738
- contextWindow: 128000,
13739
- maxTokens: 4096,
14952
+ contextWindow: 131072,
14953
+ maxTokens: 131072,
13740
14954
  },
13741
14955
  "x-ai/grok-4.20": {
13742
14956
  id: "x-ai/grok-4.20",
13743
- name: "xAI: Grok 4.20",
14957
+ name: "SpaceXAI: Grok 4.20",
13744
14958
  api: "openai-completions",
13745
14959
  provider: "openrouter",
13746
14960
  baseUrl: "https://openrouter.ai/api/v1",
@@ -13757,7 +14971,7 @@ export const MODELS = {
13757
14971
  },
13758
14972
  "x-ai/grok-4.3": {
13759
14973
  id: "x-ai/grok-4.3",
13760
- name: "xAI: Grok 4.3",
14974
+ name: "SpaceXAI: Grok 4.3",
13761
14975
  api: "openai-completions",
13762
14976
  provider: "openrouter",
13763
14977
  baseUrl: "https://openrouter.ai/api/v1",
@@ -13774,7 +14988,7 @@ export const MODELS = {
13774
14988
  },
13775
14989
  "x-ai/grok-4.5": {
13776
14990
  id: "x-ai/grok-4.5",
13777
- name: "xAI: Grok 4.5",
14991
+ name: "SpaceXAI: Grok 4.5",
13778
14992
  api: "openai-completions",
13779
14993
  provider: "openrouter",
13780
14994
  baseUrl: "https://openrouter.ai/api/v1",
@@ -13791,7 +15005,7 @@ export const MODELS = {
13791
15005
  },
13792
15006
  "x-ai/grok-build-0.1": {
13793
15007
  id: "x-ai/grok-build-0.1",
13794
- name: "xAI: Grok Build 0.1",
15008
+ name: "SpaceXAI: Grok Build 0.1",
13795
15009
  api: "openai-completions",
13796
15010
  provider: "openrouter",
13797
15011
  baseUrl: "https://openrouter.ai/api/v1",
@@ -14002,13 +15216,13 @@ export const MODELS = {
14002
15216
  reasoning: true,
14003
15217
  input: ["text"],
14004
15218
  cost: {
14005
- input: 0.966,
14006
- output: 3.036,
14007
- cacheRead: 0.1794,
15219
+ input: 0.952,
15220
+ output: 2.992,
15221
+ cacheRead: 0.17679999999999998,
14008
15222
  cacheWrite: 0,
14009
15223
  },
14010
15224
  contextWindow: 204800,
14011
- maxTokens: 128000,
15225
+ maxTokens: 131072,
14012
15226
  },
14013
15227
  "z-ai/glm-5.2": {
14014
15228
  id: "z-ai/glm-5.2",
@@ -14019,13 +15233,30 @@ export const MODELS = {
14019
15233
  reasoning: true,
14020
15234
  input: ["text"],
14021
15235
  cost: {
14022
- input: 0.7868,
14023
- output: 2.4728,
14024
- cacheRead: 0.14612,
15236
+ input: 0.6859999999999999,
15237
+ output: 2.156,
15238
+ cacheRead: 0.12739999999999999,
14025
15239
  cacheWrite: 0,
14026
15240
  },
14027
15241
  contextWindow: 1048576,
14028
- maxTokens: 131072,
15242
+ maxTokens: 128000,
15243
+ },
15244
+ "z-ai/glm-5.2:batch": {
15245
+ id: "z-ai/glm-5.2:batch",
15246
+ name: "Z.ai: GLM 5.2 (batch)",
15247
+ api: "openai-completions",
15248
+ provider: "openrouter",
15249
+ baseUrl: "https://openrouter.ai/api/v1",
15250
+ reasoning: true,
15251
+ input: ["text"],
15252
+ cost: {
15253
+ input: 0.7,
15254
+ output: 2.2,
15255
+ cacheRead: 0.13,
15256
+ cacheWrite: 0,
15257
+ },
15258
+ contextWindow: 512000,
15259
+ maxTokens: 4096,
14029
15260
  },
14030
15261
  "z-ai/glm-5v-turbo": {
14031
15262
  id: "z-ai/glm-5v-turbo",
@@ -14113,6 +15344,25 @@ export const MODELS = {
14113
15344
  contextWindow: 1000000,
14114
15345
  maxTokens: 128000,
14115
15346
  },
15347
+ "~deepseek/deepseek-v4-flash-latest": {
15348
+ id: "~deepseek/deepseek-v4-flash-latest",
15349
+ name: "DeepSeek V4 Flash Latest",
15350
+ api: "openai-completions",
15351
+ provider: "openrouter",
15352
+ baseUrl: "https://openrouter.ai/api/v1",
15353
+ compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
15354
+ reasoning: true,
15355
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
15356
+ input: ["text"],
15357
+ cost: {
15358
+ input: 0.09,
15359
+ output: 0.18,
15360
+ cacheRead: 0.018,
15361
+ cacheWrite: 0,
15362
+ },
15363
+ contextWindow: 1048576,
15364
+ maxTokens: 65536,
15365
+ },
14116
15366
  "~google/gemini-flash-latest": {
14117
15367
  id: "~google/gemini-flash-latest",
14118
15368
  name: "Google Gemini Flash Latest",
@@ -14125,7 +15375,7 @@ export const MODELS = {
14125
15375
  input: 1.5,
14126
15376
  output: 7.5,
14127
15377
  cacheRead: 0.15,
14128
- cacheWrite: 0.08333333333333334,
15378
+ cacheWrite: 0.0833333333333333,
14129
15379
  },
14130
15380
  contextWindow: 1048576,
14131
15381
  maxTokens: 65536,
@@ -14156,13 +15406,13 @@ export const MODELS = {
14156
15406
  reasoning: true,
14157
15407
  input: ["text", "image"],
14158
15408
  cost: {
14159
- input: 3,
14160
- output: 15,
14161
- cacheRead: 0.3,
15409
+ input: 2.5,
15410
+ output: 14,
15411
+ cacheRead: 0.29,
14162
15412
  cacheWrite: 0,
14163
15413
  },
14164
15414
  contextWindow: 1048576,
14165
- maxTokens: 4096,
15415
+ maxTokens: 1048576,
14166
15416
  },
14167
15417
  "~openai/gpt-latest": {
14168
15418
  id: "~openai/gpt-latest",
@@ -14323,12 +15573,31 @@ export const MODELS = {
14323
15573
  cost: {
14324
15574
  input: 1.25,
14325
15575
  output: 3.75,
14326
- cacheRead: 0,
15576
+ cacheRead: 0.125,
14327
15577
  cacheWrite: 0,
14328
15578
  },
14329
15579
  contextWindow: 1000000,
14330
15580
  maxTokens: 500000,
14331
15581
  },
15582
+ "deepseek-ai/DeepSeek-V4-Flash-0731": {
15583
+ id: "deepseek-ai/DeepSeek-V4-Flash-0731",
15584
+ name: "DeepSeek V4 Flash 0731",
15585
+ api: "openai-completions",
15586
+ provider: "together",
15587
+ baseUrl: "https://api.together.ai/v1",
15588
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
15589
+ reasoning: true,
15590
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
15591
+ input: ["text"],
15592
+ cost: {
15593
+ input: 0.14,
15594
+ output: 0.28,
15595
+ cacheRead: 0.03,
15596
+ cacheWrite: 0,
15597
+ },
15598
+ contextWindow: 1000000,
15599
+ maxTokens: 384000,
15600
+ },
14332
15601
  "deepseek-ai/DeepSeek-V4-Pro": {
14333
15602
  id: "deepseek-ai/DeepSeek-V4-Pro",
14334
15603
  name: "DeepSeek V4 Pro",
@@ -14423,6 +15692,25 @@ export const MODELS = {
14423
15692
  contextWindow: 262144,
14424
15693
  maxTokens: 131072,
14425
15694
  },
15695
+ "moonshotai/Kimi-K3": {
15696
+ id: "moonshotai/Kimi-K3",
15697
+ name: "Kimi K3",
15698
+ api: "openai-completions",
15699
+ provider: "together",
15700
+ baseUrl: "https://api.together.ai/v1",
15701
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
15702
+ reasoning: true,
15703
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
15704
+ input: ["text", "image"],
15705
+ cost: {
15706
+ input: 3,
15707
+ output: 15,
15708
+ cacheRead: 0.3,
15709
+ cacheWrite: 0,
15710
+ },
15711
+ contextWindow: 1048576,
15712
+ maxTokens: 131072,
15713
+ },
14426
15714
  "nvidia/nemotron-3-ultra-550b-a55b": {
14427
15715
  id: "nvidia/nemotron-3-ultra-550b-a55b",
14428
15716
  name: "Nemotron 3 Ultra 550B A55B",
@@ -14894,6 +16182,23 @@ export const MODELS = {
14894
16182
  contextWindow: 1000000,
14895
16183
  maxTokens: 64000,
14896
16184
  },
16185
+ "alibaba/qwen3.7-flash": {
16186
+ id: "alibaba/qwen3.7-flash",
16187
+ name: "Qwen 3.7 Flash",
16188
+ api: "anthropic-messages",
16189
+ provider: "vercel-ai-gateway",
16190
+ baseUrl: "https://ai-gateway.vercel.sh",
16191
+ reasoning: true,
16192
+ input: ["text", "image"],
16193
+ cost: {
16194
+ input: 0.03,
16195
+ output: 0.13,
16196
+ cacheRead: 0.006,
16197
+ cacheWrite: 0.038000000000000006,
16198
+ },
16199
+ contextWindow: 991000,
16200
+ maxTokens: 64000,
16201
+ },
14897
16202
  "alibaba/qwen3.7-max": {
14898
16203
  id: "alibaba/qwen3.7-max",
14899
16204
  name: "Qwen 3.7 Max",
@@ -14928,6 +16233,23 @@ export const MODELS = {
14928
16233
  contextWindow: 1000000,
14929
16234
  maxTokens: 64000,
14930
16235
  },
16236
+ "alibaba/qwen3.8-max": {
16237
+ id: "alibaba/qwen3.8-max",
16238
+ name: "Qwen 3.8 Max",
16239
+ api: "anthropic-messages",
16240
+ provider: "vercel-ai-gateway",
16241
+ baseUrl: "https://ai-gateway.vercel.sh",
16242
+ reasoning: true,
16243
+ input: ["text", "image"],
16244
+ cost: {
16245
+ input: 2,
16246
+ output: 6,
16247
+ cacheRead: 0.25,
16248
+ cacheWrite: 2.5,
16249
+ },
16250
+ contextWindow: 1000000,
16251
+ maxTokens: 128000,
16252
+ },
14931
16253
  "amazon/nova-2-lite": {
14932
16254
  id: "amazon/nova-2-lite",
14933
16255
  name: "Nova 2 Lite",
@@ -15065,23 +16387,6 @@ export const MODELS = {
15065
16387
  contextWindow: 200000,
15066
16388
  maxTokens: 8192,
15067
16389
  },
15068
- "anthropic/claude-opus-4.1": {
15069
- id: "anthropic/claude-opus-4.1",
15070
- name: "Claude Opus 4.1",
15071
- api: "anthropic-messages",
15072
- provider: "vercel-ai-gateway",
15073
- baseUrl: "https://ai-gateway.vercel.sh",
15074
- reasoning: true,
15075
- input: ["text", "image"],
15076
- cost: {
15077
- input: 15,
15078
- output: 75,
15079
- cacheRead: 1.5,
15080
- cacheWrite: 18.75,
15081
- },
15082
- contextWindow: 200000,
15083
- maxTokens: 32000,
15084
- },
15085
16390
  "anthropic/claude-opus-4.5": {
15086
16391
  id: "anthropic/claude-opus-4.5",
15087
16392
  name: "Claude Opus 4.5",
@@ -15135,24 +16440,6 @@ export const MODELS = {
15135
16440
  contextWindow: 1000000,
15136
16441
  maxTokens: 128000,
15137
16442
  },
15138
- "anthropic/claude-opus-4.7-fast": {
15139
- id: "anthropic/claude-opus-4.7-fast",
15140
- name: "Claude Opus 4.7 (Fast)",
15141
- api: "anthropic-messages",
15142
- provider: "vercel-ai-gateway",
15143
- baseUrl: "https://ai-gateway.vercel.sh",
15144
- reasoning: true,
15145
- thinkingLevelMap: { "xhigh": "xhigh" },
15146
- input: ["text", "image"],
15147
- cost: {
15148
- input: 30,
15149
- output: 150,
15150
- cacheRead: 3,
15151
- cacheWrite: 37.5,
15152
- },
15153
- contextWindow: 1000000,
15154
- maxTokens: 128000,
15155
- },
15156
16443
  "anthropic/claude-opus-4.8": {
15157
16444
  id: "anthropic/claude-opus-4.8",
15158
16445
  name: "Claude Opus 4.8",
@@ -15196,29 +16483,12 @@ export const MODELS = {
15196
16483
  provider: "vercel-ai-gateway",
15197
16484
  baseUrl: "https://ai-gateway.vercel.sh",
15198
16485
  reasoning: true,
15199
- input: ["text", "image"],
15200
- cost: {
15201
- input: 5,
15202
- output: 25,
15203
- cacheRead: 0.5,
15204
- cacheWrite: 6.25,
15205
- },
15206
- contextWindow: 1000000,
15207
- maxTokens: 128000,
15208
- },
15209
- "anthropic/claude-opus-5-fast": {
15210
- id: "anthropic/claude-opus-5-fast",
15211
- name: "Claude Opus 5 (Fast)",
15212
- api: "anthropic-messages",
15213
- provider: "vercel-ai-gateway",
15214
- baseUrl: "https://ai-gateway.vercel.sh",
15215
- reasoning: true,
15216
- input: ["text", "image"],
15217
- cost: {
15218
- input: 10,
15219
- output: 50,
15220
- cacheRead: 1,
15221
- cacheWrite: 12.5,
16486
+ input: ["text", "image"],
16487
+ cost: {
16488
+ input: 5,
16489
+ output: 25,
16490
+ cacheRead: 0.5,
16491
+ cacheWrite: 6.25,
15222
16492
  },
15223
16493
  contextWindow: 1000000,
15224
16494
  maxTokens: 128000,
@@ -15467,7 +16737,7 @@ export const MODELS = {
15467
16737
  api: "anthropic-messages",
15468
16738
  provider: "vercel-ai-gateway",
15469
16739
  baseUrl: "https://ai-gateway.vercel.sh",
15470
- reasoning: true,
16740
+ reasoning: false,
15471
16741
  input: ["text"],
15472
16742
  cost: {
15473
16743
  input: 0.62,
@@ -15487,8 +16757,25 @@ export const MODELS = {
15487
16757
  reasoning: true,
15488
16758
  input: ["text"],
15489
16759
  cost: {
15490
- input: 0.14,
15491
- output: 0.28,
16760
+ input: 0.19999999999999998,
16761
+ output: 0.39999999999999997,
16762
+ cacheRead: 0.04,
16763
+ cacheWrite: 0,
16764
+ },
16765
+ contextWindow: 1000000,
16766
+ maxTokens: 384000,
16767
+ },
16768
+ "deepseek/deepseek-v4-flash-0731": {
16769
+ id: "deepseek/deepseek-v4-flash-0731",
16770
+ name: "DeepSeek V4 Flash 0731",
16771
+ api: "anthropic-messages",
16772
+ provider: "vercel-ai-gateway",
16773
+ baseUrl: "https://ai-gateway.vercel.sh",
16774
+ reasoning: true,
16775
+ input: ["text"],
16776
+ cost: {
16777
+ input: 0.13,
16778
+ output: 0.26,
15492
16779
  cacheRead: 0.028,
15493
16780
  cacheWrite: 0,
15494
16781
  },
@@ -15504,13 +16791,13 @@ export const MODELS = {
15504
16791
  reasoning: true,
15505
16792
  input: ["text"],
15506
16793
  cost: {
15507
- input: 0.435,
15508
- output: 0.87,
15509
- cacheRead: 0.0036,
16794
+ input: 1.74,
16795
+ output: 3.48,
16796
+ cacheRead: 0.14,
15510
16797
  cacheWrite: 0,
15511
16798
  },
15512
- contextWindow: 1000000,
15513
- maxTokens: 384000,
16799
+ contextWindow: 1048600,
16800
+ maxTokens: 1048600,
15514
16801
  },
15515
16802
  "google/gemini-2.5-flash": {
15516
16803
  id: "google/gemini-2.5-flash",
@@ -15580,23 +16867,6 @@ export const MODELS = {
15580
16867
  contextWindow: 1000000,
15581
16868
  maxTokens: 65000,
15582
16869
  },
15583
- "google/gemini-3-pro-preview": {
15584
- id: "google/gemini-3-pro-preview",
15585
- name: "Gemini 3 Pro Preview",
15586
- api: "anthropic-messages",
15587
- provider: "vercel-ai-gateway",
15588
- baseUrl: "https://ai-gateway.vercel.sh",
15589
- reasoning: true,
15590
- input: ["text", "image"],
15591
- cost: {
15592
- input: 2,
15593
- output: 12,
15594
- cacheRead: 0.19999999999999998,
15595
- cacheWrite: 0,
15596
- },
15597
- contextWindow: 1000000,
15598
- maxTokens: 64000,
15599
- },
15600
16870
  "google/gemini-3.1-flash-lite": {
15601
16871
  id: "google/gemini-3.1-flash-lite",
15602
16872
  name: "Gemini 3.1 Flash Lite",
@@ -15614,23 +16884,6 @@ export const MODELS = {
15614
16884
  contextWindow: 1000000,
15615
16885
  maxTokens: 65000,
15616
16886
  },
15617
- "google/gemini-3.1-flash-lite-preview": {
15618
- id: "google/gemini-3.1-flash-lite-preview",
15619
- name: "Gemini 3.1 Flash Lite Preview",
15620
- api: "anthropic-messages",
15621
- provider: "vercel-ai-gateway",
15622
- baseUrl: "https://ai-gateway.vercel.sh",
15623
- reasoning: true,
15624
- input: ["text", "image"],
15625
- cost: {
15626
- input: 0.25,
15627
- output: 1.5,
15628
- cacheRead: 0.03,
15629
- cacheWrite: 0,
15630
- },
15631
- contextWindow: 1000000,
15632
- maxTokens: 65000,
15633
- },
15634
16887
  "google/gemini-3.1-pro-preview": {
15635
16888
  id: "google/gemini-3.1-pro-preview",
15636
16889
  name: "Gemini 3.1 Pro Preview",
@@ -15730,7 +16983,7 @@ export const MODELS = {
15730
16983
  cacheRead: 0,
15731
16984
  cacheWrite: 0,
15732
16985
  },
15733
- contextWindow: 262144,
16986
+ contextWindow: 256000,
15734
16987
  maxTokens: 131072,
15735
16988
  },
15736
16989
  "inception/mercury-2": {
@@ -15767,14 +17020,31 @@ export const MODELS = {
15767
17020
  contextWindow: 32000,
15768
17021
  maxTokens: 16384,
15769
17022
  },
15770
- "inclusionai/ling-3.0-flash-free": {
15771
- id: "inclusionai/ling-3.0-flash-free",
17023
+ "inclusionai/ling-3.0-flash": {
17024
+ id: "inclusionai/ling-3.0-flash",
15772
17025
  name: "Ling 3.0 Flash",
15773
17026
  api: "anthropic-messages",
15774
17027
  provider: "vercel-ai-gateway",
15775
17028
  baseUrl: "https://ai-gateway.vercel.sh",
15776
17029
  reasoning: true,
15777
17030
  input: ["text"],
17031
+ cost: {
17032
+ input: 0.06,
17033
+ output: 0.18,
17034
+ cacheRead: 0.012,
17035
+ cacheWrite: 0,
17036
+ },
17037
+ contextWindow: 256000,
17038
+ maxTokens: 32000,
17039
+ },
17040
+ "inclusionai/ling-3.0-tiny-free": {
17041
+ id: "inclusionai/ling-3.0-tiny-free",
17042
+ name: "Ling 3.0 Tiny (Free)",
17043
+ api: "anthropic-messages",
17044
+ provider: "vercel-ai-gateway",
17045
+ baseUrl: "https://ai-gateway.vercel.sh",
17046
+ reasoning: true,
17047
+ input: ["text"],
15778
17048
  cost: {
15779
17049
  input: 0,
15780
17050
  output: 0,
@@ -15782,7 +17052,7 @@ export const MODELS = {
15782
17052
  cacheWrite: 0,
15783
17053
  },
15784
17054
  contextWindow: 256000,
15785
- maxTokens: 256000,
17055
+ maxTokens: 32000,
15786
17056
  },
15787
17057
  "interfaze/interfaze-beta": {
15788
17058
  id: "interfaze/interfaze-beta",
@@ -15808,7 +17078,7 @@ export const MODELS = {
15808
17078
  provider: "vercel-ai-gateway",
15809
17079
  baseUrl: "https://ai-gateway.vercel.sh",
15810
17080
  reasoning: true,
15811
- input: ["text"],
17081
+ input: ["text", "image"],
15812
17082
  cost: {
15813
17083
  input: 0.15,
15814
17084
  output: 0.6,
@@ -15859,7 +17129,7 @@ export const MODELS = {
15859
17129
  provider: "vercel-ai-gateway",
15860
17130
  baseUrl: "https://ai-gateway.vercel.sh",
15861
17131
  reasoning: true,
15862
- input: ["text"],
17132
+ input: ["text", "image"],
15863
17133
  cost: {
15864
17134
  input: 0.74,
15865
17135
  output: 2.96,
@@ -15971,6 +17241,40 @@ export const MODELS = {
15971
17241
  contextWindow: 1048576,
15972
17242
  maxTokens: 1048576,
15973
17243
  },
17244
+ "meta/muse-spark-1.2": {
17245
+ id: "meta/muse-spark-1.2",
17246
+ name: "Muse Spark 1.2",
17247
+ api: "anthropic-messages",
17248
+ provider: "vercel-ai-gateway",
17249
+ baseUrl: "https://ai-gateway.vercel.sh",
17250
+ reasoning: true,
17251
+ input: ["text", "image"],
17252
+ cost: {
17253
+ input: 1.25,
17254
+ output: 4.25,
17255
+ cacheRead: 0.15,
17256
+ cacheWrite: 0,
17257
+ },
17258
+ contextWindow: 1048576,
17259
+ maxTokens: 1048576,
17260
+ },
17261
+ "meta/muse-spark-1.2-contributor": {
17262
+ id: "meta/muse-spark-1.2-contributor",
17263
+ name: "Muse Spark 1.2 Contributor",
17264
+ api: "anthropic-messages",
17265
+ provider: "vercel-ai-gateway",
17266
+ baseUrl: "https://ai-gateway.vercel.sh",
17267
+ reasoning: true,
17268
+ input: ["text", "image"],
17269
+ cost: {
17270
+ input: 0.09999999999999999,
17271
+ output: 0.19999999999999998,
17272
+ cacheRead: 0.002,
17273
+ cacheWrite: 0,
17274
+ },
17275
+ contextWindow: 1048576,
17276
+ maxTokens: 1048576,
17277
+ },
15974
17278
  "minimax/minimax-m2": {
15975
17279
  id: "minimax/minimax-m2",
15976
17280
  name: "MiniMax M2",
@@ -16058,7 +17362,7 @@ export const MODELS = {
16058
17362
  },
16059
17363
  "minimax/minimax-m2.7": {
16060
17364
  id: "minimax/minimax-m2.7",
16061
- name: "MiniMax M2.7",
17365
+ name: "Minimax M2.7",
16062
17366
  api: "anthropic-messages",
16063
17367
  provider: "vercel-ai-gateway",
16064
17368
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -16216,7 +17520,7 @@ export const MODELS = {
16216
17520
  provider: "vercel-ai-gateway",
16217
17521
  baseUrl: "https://ai-gateway.vercel.sh",
16218
17522
  reasoning: false,
16219
- input: ["text"],
17523
+ input: ["text", "image"],
16220
17524
  cost: {
16221
17525
  input: 0.09999999999999999,
16222
17526
  output: 0.09999999999999999,
@@ -16233,7 +17537,7 @@ export const MODELS = {
16233
17537
  provider: "vercel-ai-gateway",
16234
17538
  baseUrl: "https://ai-gateway.vercel.sh",
16235
17539
  reasoning: false,
16236
- input: ["text"],
17540
+ input: ["text", "image"],
16237
17541
  cost: {
16238
17542
  input: 0.15,
16239
17543
  output: 0.15,
@@ -16301,7 +17605,7 @@ export const MODELS = {
16301
17605
  provider: "vercel-ai-gateway",
16302
17606
  baseUrl: "https://ai-gateway.vercel.sh",
16303
17607
  reasoning: false,
16304
- input: ["text"],
17608
+ input: ["text", "image"],
16305
17609
  cost: {
16306
17610
  input: 0.15,
16307
17611
  output: 0.15,
@@ -16464,6 +17768,23 @@ export const MODELS = {
16464
17768
  contextWindow: 1000000,
16465
17769
  maxTokens: 131072,
16466
17770
  },
17771
+ "moonshotai/kimi-k3-fast": {
17772
+ id: "moonshotai/kimi-k3-fast",
17773
+ name: "Kimi K3 Fast",
17774
+ api: "anthropic-messages",
17775
+ provider: "vercel-ai-gateway",
17776
+ baseUrl: "https://ai-gateway.vercel.sh",
17777
+ reasoning: true,
17778
+ input: ["text", "image"],
17779
+ cost: {
17780
+ input: 4.5,
17781
+ output: 22.5,
17782
+ cacheRead: 0.44999999999999996,
17783
+ cacheWrite: 0,
17784
+ },
17785
+ contextWindow: 1000000,
17786
+ maxTokens: 131072,
17787
+ },
16467
17788
  "nvidia/nemotron-3-nano-30b-a3b": {
16468
17789
  id: "nvidia/nemotron-3-nano-30b-a3b",
16469
17790
  name: "Nemotron 3 Nano 30B A3B",
@@ -16668,23 +17989,6 @@ export const MODELS = {
16668
17989
  contextWindow: 400000,
16669
17990
  maxTokens: 128000,
16670
17991
  },
16671
- "openai/gpt-5-chat": {
16672
- id: "openai/gpt-5-chat",
16673
- name: "GPT 5 Chat",
16674
- api: "anthropic-messages",
16675
- provider: "vercel-ai-gateway",
16676
- baseUrl: "https://ai-gateway.vercel.sh",
16677
- reasoning: false,
16678
- input: ["text", "image"],
16679
- cost: {
16680
- input: 1.25,
16681
- output: 10,
16682
- cacheRead: 0.125,
16683
- cacheWrite: 0,
16684
- },
16685
- contextWindow: 128000,
16686
- maxTokens: 16384,
16687
- },
16688
17992
  "openai/gpt-5-codex": {
16689
17993
  id: "openai/gpt-5-codex",
16690
17994
  name: "GPT-5-Codex",
@@ -16696,7 +18000,7 @@ export const MODELS = {
16696
18000
  cost: {
16697
18001
  input: 1.25,
16698
18002
  output: 10,
16699
- cacheRead: 0.125,
18003
+ cacheRead: 0.13,
16700
18004
  cacheWrite: 0,
16701
18005
  },
16702
18006
  contextWindow: 400000,
@@ -16764,7 +18068,7 @@ export const MODELS = {
16764
18068
  cost: {
16765
18069
  input: 1.25,
16766
18070
  output: 10,
16767
- cacheRead: 0.125,
18071
+ cacheRead: 0.13,
16768
18072
  cacheWrite: 0,
16769
18073
  },
16770
18074
  contextWindow: 400000,
@@ -16798,7 +18102,7 @@ export const MODELS = {
16798
18102
  cost: {
16799
18103
  input: 0.25,
16800
18104
  output: 2,
16801
- cacheRead: 0.024999999999999998,
18105
+ cacheRead: 0.03,
16802
18106
  cacheWrite: 0,
16803
18107
  },
16804
18108
  contextWindow: 400000,
@@ -16815,7 +18119,7 @@ export const MODELS = {
16815
18119
  cost: {
16816
18120
  input: 1.25,
16817
18121
  output: 10,
16818
- cacheRead: 0.125,
18122
+ cacheRead: 0.13,
16819
18123
  cacheWrite: 0,
16820
18124
  },
16821
18125
  contextWindow: 128000,
@@ -16856,24 +18160,6 @@ export const MODELS = {
16856
18160
  contextWindow: 400000,
16857
18161
  maxTokens: 128000,
16858
18162
  },
16859
- "openai/gpt-5.2-chat": {
16860
- id: "openai/gpt-5.2-chat",
16861
- name: "GPT 5.2 Chat",
16862
- api: "anthropic-messages",
16863
- provider: "vercel-ai-gateway",
16864
- baseUrl: "https://ai-gateway.vercel.sh",
16865
- reasoning: false,
16866
- thinkingLevelMap: { "xhigh": "xhigh" },
16867
- input: ["text", "image"],
16868
- cost: {
16869
- input: 1.75,
16870
- output: 14,
16871
- cacheRead: 0.175,
16872
- cacheWrite: 0,
16873
- },
16874
- contextWindow: 128000,
16875
- maxTokens: 16384,
16876
- },
16877
18163
  "openai/gpt-5.2-codex": {
16878
18164
  id: "openai/gpt-5.2-codex",
16879
18165
  name: "GPT 5.2 Codex",
@@ -17063,10 +18349,10 @@ export const MODELS = {
17063
18349
  reasoning: true,
17064
18350
  input: ["text", "image"],
17065
18351
  cost: {
17066
- input: 1,
17067
- output: 6,
17068
- cacheRead: 0.09999999999999999,
17069
- cacheWrite: 1.25,
18352
+ input: 0.19999999999999998,
18353
+ output: 1.2,
18354
+ cacheRead: 0.02,
18355
+ cacheWrite: 0.25,
17070
18356
  },
17071
18357
  contextWindow: 1050000,
17072
18358
  maxTokens: 128000,
@@ -17097,10 +18383,10 @@ export const MODELS = {
17097
18383
  reasoning: true,
17098
18384
  input: ["text", "image"],
17099
18385
  cost: {
17100
- input: 2.5,
17101
- output: 15,
17102
- cacheRead: 0.25,
17103
- cacheWrite: 3.125,
18386
+ input: 2,
18387
+ output: 12,
18388
+ cacheRead: 0.19999999999999998,
18389
+ cacheWrite: 2.5,
17104
18390
  },
17105
18391
  contextWindow: 1050000,
17106
18392
  maxTokens: 128000,
@@ -17316,7 +18602,7 @@ export const MODELS = {
17316
18602
  provider: "vercel-ai-gateway",
17317
18603
  baseUrl: "https://ai-gateway.vercel.sh",
17318
18604
  reasoning: true,
17319
- input: ["text"],
18605
+ input: ["text", "image"],
17320
18606
  cost: {
17321
18607
  input: 0.09,
17322
18608
  output: 0.3,
@@ -17377,6 +18663,23 @@ export const MODELS = {
17377
18663
  contextWindow: 256000,
17378
18664
  maxTokens: 256000,
17379
18665
  },
18666
+ "thinkingmachines/inkling-small": {
18667
+ id: "thinkingmachines/inkling-small",
18668
+ name: "Inkling Small",
18669
+ api: "anthropic-messages",
18670
+ provider: "vercel-ai-gateway",
18671
+ baseUrl: "https://ai-gateway.vercel.sh",
18672
+ reasoning: true,
18673
+ input: ["text", "image"],
18674
+ cost: {
18675
+ input: 0.5,
18676
+ output: 1.2,
18677
+ cacheRead: 0.09999999999999999,
18678
+ cacheWrite: 0,
18679
+ },
18680
+ contextWindow: 1000000,
18681
+ maxTokens: 1000000,
18682
+ },
17380
18683
  "xai/grok-4.1-fast-non-reasoning": {
17381
18684
  id: "xai/grok-4.1-fast-non-reasoning",
17382
18685
  name: "Grok 4.1 Fast Non-Reasoning",
@@ -17760,9 +19063,9 @@ export const MODELS = {
17760
19063
  reasoning: true,
17761
19064
  input: ["text"],
17762
19065
  cost: {
17763
- input: 0.95,
17764
- output: 3.15,
17765
- cacheRead: 0.19999999999999998,
19066
+ input: 1,
19067
+ output: 3.1999999999999997,
19068
+ cacheRead: 0,
17766
19069
  cacheWrite: 0,
17767
19070
  },
17768
19071
  contextWindow: 202800,
@@ -17794,13 +19097,13 @@ export const MODELS = {
17794
19097
  reasoning: true,
17795
19098
  input: ["text"],
17796
19099
  cost: {
17797
- input: 1.3,
17798
- output: 4.300000000000001,
19100
+ input: 1.4,
19101
+ output: 4.4,
17799
19102
  cacheRead: 0.26,
17800
19103
  cacheWrite: 0,
17801
19104
  },
17802
- contextWindow: 202000,
17803
- maxTokens: 202000,
19105
+ contextWindow: 202800,
19106
+ maxTokens: 64000,
17804
19107
  },
17805
19108
  "zai/glm-5.2": {
17806
19109
  id: "zai/glm-5.2",
@@ -17811,12 +19114,12 @@ export const MODELS = {
17811
19114
  reasoning: true,
17812
19115
  input: ["text"],
17813
19116
  cost: {
17814
- input: 1.4,
17815
- output: 4.4,
17816
- cacheRead: 0.26,
19117
+ input: 1.1,
19118
+ output: 3.851,
19119
+ cacheRead: 0.275,
17817
19120
  cacheWrite: 0,
17818
19121
  },
17819
- contextWindow: 1040000,
19122
+ contextWindow: 1000000,
17820
19123
  maxTokens: 128000,
17821
19124
  },
17822
19125
  "zai/glm-5.2-fast": {
@@ -18171,24 +19474,6 @@ export const MODELS = {
18171
19474
  },
18172
19475
  },
18173
19476
  "zai": {
18174
- "glm-4.5-air": {
18175
- id: "glm-4.5-air",
18176
- name: "GLM-4.5-Air",
18177
- api: "openai-completions",
18178
- provider: "zai",
18179
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
18180
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
18181
- reasoning: true,
18182
- input: ["text"],
18183
- cost: {
18184
- input: 0,
18185
- output: 0,
18186
- cacheRead: 0,
18187
- cacheWrite: 0,
18188
- },
18189
- contextWindow: 131072,
18190
- maxTokens: 98304,
18191
- },
18192
19477
  "glm-4.7": {
18193
19478
  id: "glm-4.7",
18194
19479
  name: "GLM-4.7",
@@ -18225,24 +19510,6 @@ export const MODELS = {
18225
19510
  contextWindow: 200000,
18226
19511
  maxTokens: 131072,
18227
19512
  },
18228
- "glm-5.1": {
18229
- id: "glm-5.1",
18230
- name: "GLM-5.1",
18231
- api: "openai-completions",
18232
- provider: "zai",
18233
- baseUrl: "https://api.z.ai/api/coding/paas/v4",
18234
- compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
18235
- reasoning: true,
18236
- input: ["text"],
18237
- cost: {
18238
- input: 0,
18239
- output: 0,
18240
- cacheRead: 0,
18241
- cacheWrite: 0,
18242
- },
18243
- contextWindow: 200000,
18244
- maxTokens: 131072,
18245
- },
18246
19513
  "glm-5.2": {
18247
19514
  id: "glm-5.2",
18248
19515
  name: "GLM-5.2",
@@ -18261,22 +19528,22 @@ export const MODELS = {
18261
19528
  contextWindow: 1000000,
18262
19529
  maxTokens: 131072,
18263
19530
  },
18264
- "glm-5v-turbo": {
18265
- id: "glm-5v-turbo",
18266
- name: "GLM-5V-Turbo",
19531
+ "glm-5.2-highspeed": {
19532
+ id: "glm-5.2-highspeed",
19533
+ name: "GLM-5.2 Highspeed",
18267
19534
  api: "openai-completions",
18268
19535
  provider: "zai",
18269
19536
  baseUrl: "https://api.z.ai/api/coding/paas/v4",
18270
19537
  compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
18271
19538
  reasoning: true,
18272
- input: ["text", "image"],
19539
+ input: ["text"],
18273
19540
  cost: {
18274
19541
  input: 0,
18275
19542
  output: 0,
18276
19543
  cacheRead: 0,
18277
19544
  cacheWrite: 0,
18278
19545
  },
18279
- contextWindow: 200000,
19546
+ contextWindow: 1000000,
18280
19547
  maxTokens: 131072,
18281
19548
  },
18282
19549
  },