@elyracode/ai 0.9.55 → 0.9.56

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.
@@ -597,6 +597,24 @@ export const MODELS = {
597
597
  contextWindow: 1000000,
598
598
  maxTokens: 128000,
599
599
  },
600
+ "au.anthropic.claude-sonnet-5-5": {
601
+ id: "au.anthropic.claude-sonnet-5-5",
602
+ name: "Claude Sonnet 5.5 (AU)",
603
+ api: "bedrock-converse-stream",
604
+ provider: "amazon-bedrock",
605
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
606
+ reasoning: true,
607
+ thinkingType: "adaptive",
608
+ input: ["text", "image"],
609
+ cost: {
610
+ input: 2.2,
611
+ output: 11,
612
+ cacheRead: 0.11,
613
+ cacheWrite: 2.75,
614
+ },
615
+ contextWindow: 1000000,
616
+ maxTokens: 128000,
617
+ },
600
618
  "ca.amazon.nova-lite-v1:0": {
601
619
  id: "ca.amazon.nova-lite-v1:0",
602
620
  name: "Nova Lite (CA)",
@@ -1417,6 +1435,23 @@ export const MODELS = {
1417
1435
  contextWindow: 1050000,
1418
1436
  maxTokens: 128000,
1419
1437
  },
1438
+ "global.openai.gpt-6.1-terra": {
1439
+ id: "global.openai.gpt-6.1-terra",
1440
+ name: "GPT-6.1 Terra (Global)",
1441
+ api: "bedrock-converse-stream",
1442
+ provider: "amazon-bedrock",
1443
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
1444
+ reasoning: true,
1445
+ input: ["text", "image"],
1446
+ cost: {
1447
+ input: 1,
1448
+ output: 5,
1449
+ cacheRead: 0.05,
1450
+ cacheWrite: 1.25,
1451
+ },
1452
+ contextWindow: 1050000,
1453
+ maxTokens: 128000,
1454
+ },
1420
1455
  "global.xai.grok-4.6": {
1421
1456
  id: "global.xai.grok-4.6",
1422
1457
  name: "Grok 4.6 (Global)",
@@ -2334,6 +2369,23 @@ export const MODELS = {
2334
2369
  contextWindow: 1050000,
2335
2370
  maxTokens: 128000,
2336
2371
  },
2372
+ "openai.gpt-6.1-terra": {
2373
+ id: "openai.gpt-6.1-terra",
2374
+ name: "GPT-6.1 Terra",
2375
+ api: "bedrock-converse-stream",
2376
+ provider: "amazon-bedrock",
2377
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
2378
+ reasoning: true,
2379
+ input: ["text", "image"],
2380
+ cost: {
2381
+ input: 1.1,
2382
+ output: 5.5,
2383
+ cacheRead: 0.055,
2384
+ cacheWrite: 1.375,
2385
+ },
2386
+ contextWindow: 1050000,
2387
+ maxTokens: 128000,
2388
+ },
2337
2389
  "openai.gpt-oss-120b": {
2338
2390
  id: "openai.gpt-oss-120b",
2339
2391
  name: "gpt-oss-120b",
@@ -3205,6 +3257,23 @@ export const MODELS = {
3205
3257
  contextWindow: 1050000,
3206
3258
  maxTokens: 128000,
3207
3259
  },
3260
+ "us.openai.gpt-6.1-terra": {
3261
+ id: "us.openai.gpt-6.1-terra",
3262
+ name: "GPT-6.1 Terra (US)",
3263
+ api: "bedrock-converse-stream",
3264
+ provider: "amazon-bedrock",
3265
+ baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
3266
+ reasoning: true,
3267
+ input: ["text", "image"],
3268
+ cost: {
3269
+ input: 1.1,
3270
+ output: 5.5,
3271
+ cacheRead: 0.055,
3272
+ cacheWrite: 1.375,
3273
+ },
3274
+ contextWindow: 1050000,
3275
+ maxTokens: 128000,
3276
+ },
3208
3277
  "us.writer.palmyra-x4-v1:0": {
3209
3278
  id: "us.writer.palmyra-x4-v1:0",
3210
3279
  name: "Palmyra X4 (US)",
@@ -4290,6 +4359,23 @@ export const MODELS = {
4290
4359
  contextWindow: 1050000,
4291
4360
  maxTokens: 128000,
4292
4361
  },
4362
+ "gpt-6.1-terra": {
4363
+ id: "gpt-6.1-terra",
4364
+ name: "GPT-6.1 Terra",
4365
+ api: "azure-openai-responses",
4366
+ provider: "azure-openai-responses",
4367
+ baseUrl: "",
4368
+ reasoning: true,
4369
+ input: ["text", "image"],
4370
+ cost: {
4371
+ input: 1,
4372
+ output: 5,
4373
+ cacheRead: 0.05,
4374
+ cacheWrite: 1.25,
4375
+ },
4376
+ contextWindow: 1050000,
4377
+ maxTokens: 128000,
4378
+ },
4293
4379
  "gpt-daybreak-blue-latest": {
4294
4380
  id: "gpt-daybreak-blue-latest",
4295
4381
  name: "Daybreak Blue",
@@ -4456,7 +4542,7 @@ export const MODELS = {
4456
4542
  cost: {
4457
4543
  input: 0.35,
4458
4544
  output: 0.75,
4459
- cacheRead: 0,
4545
+ cacheRead: 0.35,
4460
4546
  cacheWrite: 0,
4461
4547
  },
4462
4548
  contextWindow: 131072,
@@ -4718,7 +4804,7 @@ export const MODELS = {
4718
4804
  cost: {
4719
4805
  input: 2,
4720
4806
  output: 10,
4721
- cacheRead: 0.2,
4807
+ cacheRead: 0.1,
4722
4808
  cacheWrite: 2.5,
4723
4809
  },
4724
4810
  contextWindow: 1000000,
@@ -5017,10 +5103,10 @@ export const MODELS = {
5017
5103
  thinkingLevelMap: { "off": null },
5018
5104
  input: ["text", "image"],
5019
5105
  cost: {
5020
- input: 2,
5021
- output: 10,
5022
- cacheRead: 0.25,
5023
- cacheWrite: 3.125,
5106
+ input: 4,
5107
+ output: 20,
5108
+ cacheRead: 0.4,
5109
+ cacheWrite: 5,
5024
5110
  },
5025
5111
  contextWindow: 1050000,
5026
5112
  maxTokens: 128000,
@@ -5111,6 +5197,23 @@ export const MODELS = {
5111
5197
  contextWindow: 1050000,
5112
5198
  maxTokens: 128000,
5113
5199
  },
5200
+ "gpt-6.1-terra": {
5201
+ id: "gpt-6.1-terra",
5202
+ name: "GPT-6.1 Terra",
5203
+ api: "openai-responses",
5204
+ provider: "cloudflare-ai-gateway",
5205
+ baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
5206
+ reasoning: true,
5207
+ input: ["text", "image"],
5208
+ cost: {
5209
+ input: 1,
5210
+ output: 5,
5211
+ cacheRead: 0.05,
5212
+ cacheWrite: 1.25,
5213
+ },
5214
+ contextWindow: 1050000,
5215
+ maxTokens: 128000,
5216
+ },
5114
5217
  "o3": {
5115
5218
  id: "o3",
5116
5219
  name: "o3",
@@ -5204,7 +5307,7 @@ export const MODELS = {
5204
5307
  },
5205
5308
  "@cf/deepseek-ai/deepseek-v4.1-flash-1017": {
5206
5309
  id: "@cf/deepseek-ai/deepseek-v4.1-flash-1017",
5207
- name: "Deepseek V4.1 Flash 1017",
5310
+ name: "DeepSeek V4.1 Flash 1017",
5208
5311
  api: "openai-completions",
5209
5312
  provider: "cloudflare-workers-ai",
5210
5313
  baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
@@ -5704,6 +5807,23 @@ export const MODELS = {
5704
5807
  contextWindow: 512000,
5705
5808
  maxTokens: 512000,
5706
5809
  },
5810
+ "accounts/fireworks/models/minimax-m3p1-flash": {
5811
+ id: "accounts/fireworks/models/minimax-m3p1-flash",
5812
+ name: "MiniMax-M3.1-Flash",
5813
+ api: "anthropic-messages",
5814
+ provider: "fireworks",
5815
+ baseUrl: "https://api.fireworks.ai/inference",
5816
+ reasoning: true,
5817
+ input: ["text", "image"],
5818
+ cost: {
5819
+ input: 0.15,
5820
+ output: 0.6,
5821
+ cacheRead: 0.015,
5822
+ cacheWrite: 0,
5823
+ },
5824
+ contextWindow: 1000000,
5825
+ maxTokens: 512000,
5826
+ },
5707
5827
  "accounts/fireworks/models/muse-spark-open": {
5708
5828
  id: "accounts/fireworks/models/muse-spark-open",
5709
5829
  name: "Muse Spark Open",
@@ -5806,6 +5926,40 @@ export const MODELS = {
5806
5926
  contextWindow: 1000000,
5807
5927
  maxTokens: 384000,
5808
5928
  },
5929
+ "accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot": {
5930
+ id: "accounts/fireworks/routers/deepseek-v4p1-flash-1017-spot",
5931
+ name: "DeepSeek V4.1 Flash 1017 Spot",
5932
+ api: "anthropic-messages",
5933
+ provider: "fireworks",
5934
+ baseUrl: "https://api.fireworks.ai/inference",
5935
+ reasoning: true,
5936
+ input: ["text", "image"],
5937
+ cost: {
5938
+ input: 0.21,
5939
+ output: 0.84,
5940
+ cacheRead: 0.0042,
5941
+ cacheWrite: 0,
5942
+ },
5943
+ contextWindow: 1000000,
5944
+ maxTokens: 384000,
5945
+ },
5946
+ "accounts/fireworks/routers/deepseek-v4p1-flash-spot": {
5947
+ id: "accounts/fireworks/routers/deepseek-v4p1-flash-spot",
5948
+ name: "DeepSeek V4.1 Flash Spot",
5949
+ api: "anthropic-messages",
5950
+ provider: "fireworks",
5951
+ baseUrl: "https://api.fireworks.ai/inference",
5952
+ reasoning: true,
5953
+ input: ["text", "image"],
5954
+ cost: {
5955
+ input: 0.21,
5956
+ output: 0.84,
5957
+ cacheRead: 0.0042,
5958
+ cacheWrite: 0,
5959
+ },
5960
+ contextWindow: 1000000,
5961
+ maxTokens: 384000,
5962
+ },
5809
5963
  "accounts/fireworks/routers/glm-5p3-fast": {
5810
5964
  id: "accounts/fireworks/routers/glm-5p3-fast",
5811
5965
  name: "GLM 5.3 Fast",
@@ -5823,6 +5977,23 @@ export const MODELS = {
5823
5977
  contextWindow: 1048572,
5824
5978
  maxTokens: 262144,
5825
5979
  },
5980
+ "accounts/fireworks/routers/glm-5p3-spot": {
5981
+ id: "accounts/fireworks/routers/glm-5p3-spot",
5982
+ name: "GLM 5.3 Spot",
5983
+ api: "anthropic-messages",
5984
+ provider: "fireworks",
5985
+ baseUrl: "https://api.fireworks.ai/inference",
5986
+ reasoning: true,
5987
+ input: ["text"],
5988
+ cost: {
5989
+ input: 0.98,
5990
+ output: 3.08,
5991
+ cacheRead: 0.182,
5992
+ cacheWrite: 0,
5993
+ },
5994
+ contextWindow: 1048573,
5995
+ maxTokens: 262144,
5996
+ },
5826
5997
  "accounts/fireworks/routers/glm-fast-latest": {
5827
5998
  id: "accounts/fireworks/routers/glm-fast-latest",
5828
5999
  name: "GLM 5.3 Fast (Latest)",
@@ -5908,6 +6079,23 @@ export const MODELS = {
5908
6079
  contextWindow: 1048576,
5909
6080
  maxTokens: 131072,
5910
6081
  },
6082
+ "accounts/fireworks/routers/kimi-k3-spot": {
6083
+ id: "accounts/fireworks/routers/kimi-k3-spot",
6084
+ name: "Kimi K3 Spot",
6085
+ api: "anthropic-messages",
6086
+ provider: "fireworks",
6087
+ baseUrl: "https://api.fireworks.ai/inference",
6088
+ reasoning: true,
6089
+ input: ["text", "image"],
6090
+ cost: {
6091
+ input: 2.1,
6092
+ output: 10.5,
6093
+ cacheRead: 0.21,
6094
+ cacheWrite: 0,
6095
+ },
6096
+ contextWindow: 1048576,
6097
+ maxTokens: 131072,
6098
+ },
5911
6099
  "accounts/fireworks/routers/kimi-latest": {
5912
6100
  id: "accounts/fireworks/routers/kimi-latest",
5913
6101
  name: "Kimi Latest",
@@ -6039,25 +6227,6 @@ export const MODELS = {
6039
6227
  contextWindow: 1000000,
6040
6228
  maxTokens: 128000,
6041
6229
  },
6042
- "claude-opus-4.7": {
6043
- id: "claude-opus-4.7",
6044
- name: "Claude Opus 4.7",
6045
- api: "anthropic-messages",
6046
- provider: "github-copilot",
6047
- baseUrl: "https://api.individual.githubcopilot.com",
6048
- 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" },
6049
- reasoning: true,
6050
- thinkingLevelMap: { "xhigh": "xhigh" },
6051
- input: ["text", "image"],
6052
- cost: {
6053
- input: 5,
6054
- output: 25,
6055
- cacheRead: 0.5,
6056
- cacheWrite: 6.25,
6057
- },
6058
- contextWindow: 200000,
6059
- maxTokens: 32000,
6060
- },
6061
6230
  "claude-opus-4.8": {
6062
6231
  id: "claude-opus-4.8",
6063
6232
  name: "Claude Opus 4.8",
@@ -6171,63 +6340,6 @@ export const MODELS = {
6171
6340
  contextWindow: 1000000,
6172
6341
  maxTokens: 128000,
6173
6342
  },
6174
- "gemini-3.5-flash": {
6175
- id: "gemini-3.5-flash",
6176
- name: "Gemini 3.5 Flash",
6177
- api: "openai-completions",
6178
- provider: "github-copilot",
6179
- baseUrl: "https://api.individual.githubcopilot.com",
6180
- 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" },
6181
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6182
- reasoning: true,
6183
- input: ["text", "image"],
6184
- cost: {
6185
- input: 1.5,
6186
- output: 9,
6187
- cacheRead: 0.15,
6188
- cacheWrite: 0,
6189
- },
6190
- contextWindow: 200000,
6191
- maxTokens: 64000,
6192
- },
6193
- "gemini-3.6-flash": {
6194
- id: "gemini-3.6-flash",
6195
- name: "Gemini 3.6 Flash",
6196
- api: "openai-completions",
6197
- provider: "github-copilot",
6198
- baseUrl: "https://api.individual.githubcopilot.com",
6199
- 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" },
6200
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6201
- reasoning: true,
6202
- input: ["text", "image"],
6203
- cost: {
6204
- input: 0.75,
6205
- output: 3.75,
6206
- cacheRead: 0.075,
6207
- cacheWrite: 0,
6208
- },
6209
- contextWindow: 1000000,
6210
- maxTokens: 64000,
6211
- },
6212
- "gemini-3.7-flash": {
6213
- id: "gemini-3.7-flash",
6214
- name: "Gemini 3.7 Flash",
6215
- api: "openai-completions",
6216
- provider: "github-copilot",
6217
- baseUrl: "https://api.individual.githubcopilot.com",
6218
- 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" },
6219
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6220
- reasoning: true,
6221
- input: ["text", "image"],
6222
- cost: {
6223
- input: 0.75,
6224
- output: 3.75,
6225
- cacheRead: 0.075,
6226
- cacheWrite: 0,
6227
- },
6228
- contextWindow: 1000000,
6229
- maxTokens: 64000,
6230
- },
6231
6343
  "gemini-3.8-flash": {
6232
6344
  id: "gemini-3.8-flash",
6233
6345
  name: "Gemini 3.8 Flash",
@@ -6266,25 +6378,6 @@ export const MODELS = {
6266
6378
  contextWindow: 1048576,
6267
6379
  maxTokens: 65536,
6268
6380
  },
6269
- "gpt-5-mini": {
6270
- id: "gpt-5-mini",
6271
- name: "GPT-5 Mini",
6272
- api: "openai-responses",
6273
- provider: "github-copilot",
6274
- baseUrl: "https://api.individual.githubcopilot.com",
6275
- 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" },
6276
- reasoning: true,
6277
- thinkingLevelMap: { "off": null },
6278
- input: ["text", "image"],
6279
- cost: {
6280
- input: 0.25,
6281
- output: 2,
6282
- cacheRead: 0.025,
6283
- cacheWrite: 0,
6284
- },
6285
- contextWindow: 264000,
6286
- maxTokens: 64000,
6287
- },
6288
6381
  "gpt-5.3-codex": {
6289
6382
  id: "gpt-5.3-codex",
6290
6383
  name: "GPT-5.3 Codex",
@@ -6304,44 +6397,6 @@ export const MODELS = {
6304
6397
  contextWindow: 400000,
6305
6398
  maxTokens: 128000,
6306
6399
  },
6307
- "gpt-5.4": {
6308
- id: "gpt-5.4",
6309
- name: "GPT-5.4",
6310
- api: "openai-responses",
6311
- provider: "github-copilot",
6312
- baseUrl: "https://api.individual.githubcopilot.com",
6313
- 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" },
6314
- reasoning: true,
6315
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6316
- input: ["text", "image"],
6317
- cost: {
6318
- input: 2.5,
6319
- output: 15,
6320
- cacheRead: 0.25,
6321
- cacheWrite: 0,
6322
- },
6323
- contextWindow: 1050000,
6324
- maxTokens: 128000,
6325
- },
6326
- "gpt-5.4-mini": {
6327
- id: "gpt-5.4-mini",
6328
- name: "GPT-5.4 mini",
6329
- api: "openai-responses",
6330
- provider: "github-copilot",
6331
- baseUrl: "https://api.individual.githubcopilot.com",
6332
- 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" },
6333
- reasoning: true,
6334
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6335
- input: ["text", "image"],
6336
- cost: {
6337
- input: 0.75,
6338
- output: 4.5,
6339
- cacheRead: 0.075,
6340
- cacheWrite: 0,
6341
- },
6342
- contextWindow: 400000,
6343
- maxTokens: 128000,
6344
- },
6345
6400
  "gpt-5.4-nano": {
6346
6401
  id: "gpt-5.4-nano",
6347
6402
  name: "GPT-5.4 nano",
@@ -6361,25 +6416,6 @@ export const MODELS = {
6361
6416
  contextWindow: 400000,
6362
6417
  maxTokens: 128000,
6363
6418
  },
6364
- "gpt-5.5": {
6365
- id: "gpt-5.5",
6366
- name: "GPT-5.5",
6367
- api: "openai-responses",
6368
- provider: "github-copilot",
6369
- baseUrl: "https://api.individual.githubcopilot.com",
6370
- 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" },
6371
- reasoning: true,
6372
- thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
6373
- input: ["text", "image"],
6374
- cost: {
6375
- input: 5,
6376
- output: 30,
6377
- cacheRead: 0.5,
6378
- cacheWrite: 0,
6379
- },
6380
- contextWindow: 1050000,
6381
- maxTokens: 128000,
6382
- },
6383
6419
  "gpt-5.6-luna": {
6384
6420
  id: "gpt-5.6-luna",
6385
6421
  name: "GPT-5.6 Luna",
@@ -6513,6 +6549,25 @@ export const MODELS = {
6513
6549
  contextWindow: 1050000,
6514
6550
  maxTokens: 128000,
6515
6551
  },
6552
+ "gpt-6.1-terra": {
6553
+ id: "gpt-6.1-terra",
6554
+ name: "GPT-6.1 Terra",
6555
+ api: "openai-completions",
6556
+ provider: "github-copilot",
6557
+ baseUrl: "https://api.individual.githubcopilot.com",
6558
+ 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" },
6559
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6560
+ reasoning: true,
6561
+ input: ["text", "image"],
6562
+ cost: {
6563
+ input: 1,
6564
+ output: 5,
6565
+ cacheRead: 0.05,
6566
+ cacheWrite: 1.25,
6567
+ },
6568
+ contextWindow: 1050000,
6569
+ maxTokens: 128000,
6570
+ },
6516
6571
  "grok-4.5": {
6517
6572
  id: "grok-4.5",
6518
6573
  name: "Grok 4.5",
@@ -6570,25 +6625,6 @@ export const MODELS = {
6570
6625
  contextWindow: 500000,
6571
6626
  maxTokens: 128000,
6572
6627
  },
6573
- "kimi-k2.7-code": {
6574
- id: "kimi-k2.7-code",
6575
- name: "Kimi K2.7 Code",
6576
- api: "openai-completions",
6577
- provider: "github-copilot",
6578
- baseUrl: "https://api.individual.githubcopilot.com",
6579
- 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" },
6580
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6581
- reasoning: true,
6582
- input: ["text", "image"],
6583
- cost: {
6584
- input: 0.95,
6585
- output: 4,
6586
- cacheRead: 0.19,
6587
- cacheWrite: 0,
6588
- },
6589
- contextWindow: 256000,
6590
- maxTokens: 32000,
6591
- },
6592
6628
  "kimi-k3": {
6593
6629
  id: "kimi-k3",
6594
6630
  name: "Kimi K3",
@@ -6608,25 +6644,6 @@ export const MODELS = {
6608
6644
  contextWindow: 1048576,
6609
6645
  maxTokens: 131072,
6610
6646
  },
6611
- "mai-code-1-flash-picker": {
6612
- id: "mai-code-1-flash-picker",
6613
- name: "MAI-Code-1-Flash",
6614
- api: "openai-completions",
6615
- provider: "github-copilot",
6616
- baseUrl: "https://api.individual.githubcopilot.com",
6617
- 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" },
6618
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
6619
- reasoning: true,
6620
- input: ["text"],
6621
- cost: {
6622
- input: 0.75,
6623
- output: 4.5,
6624
- cacheRead: 0.075,
6625
- cacheWrite: 0,
6626
- },
6627
- contextWindow: 256000,
6628
- maxTokens: 128000,
6629
- },
6630
6647
  "mai-code-1.1-flash": {
6631
6648
  id: "mai-code-1.1-flash",
6632
6649
  name: "MAI-Code-1.1-Flash",
@@ -7526,7 +7543,7 @@ export const MODELS = {
7526
7543
  cost: {
7527
7544
  input: 0.075,
7528
7545
  output: 0.3,
7529
- cacheRead: 0,
7546
+ cacheRead: 0.0375,
7530
7547
  cacheWrite: 0,
7531
7548
  },
7532
7549
  contextWindow: 131072,
@@ -7563,7 +7580,7 @@ export const MODELS = {
7563
7580
  cacheRead: 0,
7564
7581
  cacheWrite: 0,
7565
7582
  },
7566
- contextWindow: 131042,
7583
+ contextWindow: 131072,
7567
7584
  maxTokens: 16384,
7568
7585
  },
7569
7586
  },
@@ -7676,6 +7693,24 @@ export const MODELS = {
7676
7693
  contextWindow: 524288,
7677
7694
  maxTokens: 512000,
7678
7695
  },
7696
+ "MiniMaxAI/MiniMax-M3.1-Flash": {
7697
+ id: "MiniMaxAI/MiniMax-M3.1-Flash",
7698
+ name: "MiniMax-M3.1-Flash",
7699
+ api: "openai-completions",
7700
+ provider: "huggingface",
7701
+ baseUrl: "https://router.huggingface.co/v1",
7702
+ compat: { "supportsDeveloperRole": false },
7703
+ reasoning: true,
7704
+ input: ["text", "image"],
7705
+ cost: {
7706
+ input: 0.15,
7707
+ output: 0.6,
7708
+ cacheRead: 0,
7709
+ cacheWrite: 0,
7710
+ },
7711
+ contextWindow: 1000000,
7712
+ maxTokens: 512000,
7713
+ },
7679
7714
  "Qwen/Qwen2.5-Coder-32B-Instruct": {
7680
7715
  id: "Qwen/Qwen2.5-Coder-32B-Instruct",
7681
7716
  name: "Qwen2.5-Coder-32B-Instruct",
@@ -7784,6 +7819,24 @@ export const MODELS = {
7784
7819
  contextWindow: 131072,
7785
7820
  maxTokens: 16384,
7786
7821
  },
7822
+ "Qwen/Qwen3-8B": {
7823
+ id: "Qwen/Qwen3-8B",
7824
+ name: "Qwen3 8B",
7825
+ api: "openai-completions",
7826
+ provider: "huggingface",
7827
+ baseUrl: "https://router.huggingface.co/v1",
7828
+ compat: { "supportsDeveloperRole": false },
7829
+ reasoning: true,
7830
+ input: ["text"],
7831
+ cost: {
7832
+ input: 0.07,
7833
+ output: 0.18,
7834
+ cacheRead: 0,
7835
+ cacheWrite: 0,
7836
+ },
7837
+ contextWindow: 40960,
7838
+ maxTokens: 32768,
7839
+ },
7787
7840
  "Qwen/Qwen3-Coder-30B-A3B-Instruct": {
7788
7841
  id: "Qwen/Qwen3-Coder-30B-A3B-Instruct",
7789
7842
  name: "Qwen3-Coder 30B-A3B Instruct",
@@ -7856,24 +7909,6 @@ export const MODELS = {
7856
7909
  contextWindow: 262144,
7857
7910
  maxTokens: 32768,
7858
7911
  },
7859
- "Qwen/Qwen3-Next-80B-A3B-Thinking": {
7860
- id: "Qwen/Qwen3-Next-80B-A3B-Thinking",
7861
- name: "Qwen3-Next-80B-A3B-Thinking",
7862
- api: "openai-completions",
7863
- provider: "huggingface",
7864
- baseUrl: "https://router.huggingface.co/v1",
7865
- compat: { "supportsDeveloperRole": false },
7866
- reasoning: true,
7867
- input: ["text"],
7868
- cost: {
7869
- input: 0.3,
7870
- output: 2,
7871
- cacheRead: 0,
7872
- cacheWrite: 0,
7873
- },
7874
- contextWindow: 262144,
7875
- maxTokens: 32768,
7876
- },
7877
7912
  "Qwen/Qwen3-VL-235B-A22B-Instruct": {
7878
7913
  id: "Qwen/Qwen3-VL-235B-A22B-Instruct",
7879
7914
  name: "Qwen3 VL 235B A22B Instruct",
@@ -8756,24 +8791,6 @@ export const MODELS = {
8756
8791
  contextWindow: 524288,
8757
8792
  maxTokens: 1048576,
8758
8793
  },
8759
- "zai-org/GLM-4.5": {
8760
- id: "zai-org/GLM-4.5",
8761
- name: "GLM-4.5",
8762
- api: "openai-completions",
8763
- provider: "huggingface",
8764
- baseUrl: "https://router.huggingface.co/v1",
8765
- compat: { "supportsDeveloperRole": false },
8766
- reasoning: true,
8767
- input: ["text"],
8768
- cost: {
8769
- input: 0.6,
8770
- output: 2.2,
8771
- cacheRead: 0,
8772
- cacheWrite: 0,
8773
- },
8774
- contextWindow: 131072,
8775
- maxTokens: 98304,
8776
- },
8777
8794
  "zai-org/GLM-4.5-Air": {
8778
8795
  id: "zai-org/GLM-4.5-Air",
8779
8796
  name: "GLM-4.5-Air",
@@ -9010,6 +9027,42 @@ export const MODELS = {
9010
9027
  contextWindow: 262144,
9011
9028
  maxTokens: 131072,
9012
9029
  },
9030
+ "k3.1-pro": {
9031
+ id: "k3.1-pro",
9032
+ name: "Kimi K3.1 Pro",
9033
+ api: "anthropic-messages",
9034
+ provider: "kimi-coding",
9035
+ baseUrl: "https://api.kimi.com/coding",
9036
+ headers: { "User-Agent": "KimiCLI/1.5" },
9037
+ reasoning: true,
9038
+ input: ["text", "image"],
9039
+ cost: {
9040
+ input: 0,
9041
+ output: 0,
9042
+ cacheRead: 0,
9043
+ cacheWrite: 0,
9044
+ },
9045
+ contextWindow: 1048576,
9046
+ maxTokens: 131072,
9047
+ },
9048
+ "k3.1-pro-highspeed": {
9049
+ id: "k3.1-pro-highspeed",
9050
+ name: "Kimi K3.1 Pro Highspeed",
9051
+ api: "anthropic-messages",
9052
+ provider: "kimi-coding",
9053
+ baseUrl: "https://api.kimi.com/coding",
9054
+ headers: { "User-Agent": "KimiCLI/1.5" },
9055
+ reasoning: true,
9056
+ input: ["text", "image"],
9057
+ cost: {
9058
+ input: 0,
9059
+ output: 0,
9060
+ cacheRead: 0,
9061
+ cacheWrite: 0,
9062
+ },
9063
+ contextWindow: 1048576,
9064
+ maxTokens: 131072,
9065
+ },
9013
9066
  "kimi-for-coding": {
9014
9067
  id: "kimi-for-coding",
9015
9068
  name: "Kimi K2.8 Preview",
@@ -9188,25 +9241,25 @@ export const MODELS = {
9188
9241
  contextWindow: 256000,
9189
9242
  maxTokens: 4096,
9190
9243
  },
9191
- "devstral-2512": {
9192
- id: "devstral-2512",
9193
- name: "Devstral 2",
9244
+ "deepseek-v4-1-flash-1017": {
9245
+ id: "deepseek-v4-1-flash-1017",
9246
+ name: "DeepSeek V4.1 Flash 1017",
9194
9247
  api: "mistral-conversations",
9195
9248
  provider: "mistral",
9196
9249
  baseUrl: "https://api.mistral.ai",
9197
- reasoning: false,
9250
+ reasoning: true,
9198
9251
  input: ["text"],
9199
9252
  cost: {
9200
- input: 0.4,
9201
- output: 2,
9202
- cacheRead: 0,
9253
+ input: 0.3,
9254
+ output: 1.2,
9255
+ cacheRead: 0.007,
9203
9256
  cacheWrite: 0,
9204
9257
  },
9205
- contextWindow: 262144,
9206
- maxTokens: 262144,
9258
+ contextWindow: 1048576,
9259
+ maxTokens: 128000,
9207
9260
  },
9208
- "devstral-latest": {
9209
- id: "devstral-latest",
9261
+ "devstral-2512": {
9262
+ id: "devstral-2512",
9210
9263
  name: "Devstral 2",
9211
9264
  api: "mistral-conversations",
9212
9265
  provider: "mistral",
@@ -9222,9 +9275,9 @@ export const MODELS = {
9222
9275
  contextWindow: 262144,
9223
9276
  maxTokens: 262144,
9224
9277
  },
9225
- "devstral-medium-2507": {
9226
- id: "devstral-medium-2507",
9227
- name: "Devstral Medium",
9278
+ "devstral-latest": {
9279
+ id: "devstral-latest",
9280
+ name: "Devstral 2",
9228
9281
  api: "mistral-conversations",
9229
9282
  provider: "mistral",
9230
9283
  baseUrl: "https://api.mistral.ai",
@@ -9236,8 +9289,8 @@ export const MODELS = {
9236
9289
  cacheRead: 0,
9237
9290
  cacheWrite: 0,
9238
9291
  },
9239
- contextWindow: 128000,
9240
- maxTokens: 128000,
9292
+ contextWindow: 262144,
9293
+ maxTokens: 262144,
9241
9294
  },
9242
9295
  "devstral-medium-latest": {
9243
9296
  id: "devstral-medium-latest",
@@ -9256,40 +9309,6 @@ export const MODELS = {
9256
9309
  contextWindow: 262144,
9257
9310
  maxTokens: 262144,
9258
9311
  },
9259
- "devstral-small-2505": {
9260
- id: "devstral-small-2505",
9261
- name: "Devstral Small 2505",
9262
- api: "mistral-conversations",
9263
- provider: "mistral",
9264
- baseUrl: "https://api.mistral.ai",
9265
- reasoning: false,
9266
- input: ["text"],
9267
- cost: {
9268
- input: 0.1,
9269
- output: 0.3,
9270
- cacheRead: 0,
9271
- cacheWrite: 0,
9272
- },
9273
- contextWindow: 128000,
9274
- maxTokens: 128000,
9275
- },
9276
- "devstral-small-2507": {
9277
- id: "devstral-small-2507",
9278
- name: "Devstral Small",
9279
- api: "mistral-conversations",
9280
- provider: "mistral",
9281
- baseUrl: "https://api.mistral.ai",
9282
- reasoning: false,
9283
- input: ["text"],
9284
- cost: {
9285
- input: 0.1,
9286
- output: 0.3,
9287
- cacheRead: 0,
9288
- cacheWrite: 0,
9289
- },
9290
- contextWindow: 128000,
9291
- maxTokens: 128000,
9292
- },
9293
9312
  "glm-5-2": {
9294
9313
  id: "glm-5-2",
9295
9314
  name: "GLM-5.2",
@@ -9443,23 +9462,6 @@ export const MODELS = {
9443
9462
  contextWindow: 262144,
9444
9463
  maxTokens: 128000,
9445
9464
  },
9446
- "mistral-large-2411": {
9447
- id: "mistral-large-2411",
9448
- name: "Mistral Large 2.1",
9449
- api: "mistral-conversations",
9450
- provider: "mistral",
9451
- baseUrl: "https://api.mistral.ai",
9452
- reasoning: false,
9453
- input: ["text"],
9454
- cost: {
9455
- input: 2,
9456
- output: 6,
9457
- cacheRead: 0,
9458
- cacheWrite: 0,
9459
- },
9460
- contextWindow: 131072,
9461
- maxTokens: 16384,
9462
- },
9463
9465
  "mistral-large-2512": {
9464
9466
  id: "mistral-large-2512",
9465
9467
  name: "Mistral Large 3",
@@ -9486,8 +9488,25 @@ export const MODELS = {
9486
9488
  reasoning: true,
9487
9489
  input: ["text", "image"],
9488
9490
  cost: {
9489
- input: 0.68,
9490
- output: 2.09,
9491
+ input: 0.7,
9492
+ output: 2.1,
9493
+ cacheRead: 0.07,
9494
+ cacheWrite: 0,
9495
+ },
9496
+ contextWindow: 1048576,
9497
+ maxTokens: 262144,
9498
+ },
9499
+ "mistral-large-4-0-8": {
9500
+ id: "mistral-large-4-0-8",
9501
+ name: "Mistral Large 4.0.8",
9502
+ api: "mistral-conversations",
9503
+ provider: "mistral",
9504
+ baseUrl: "https://api.mistral.ai",
9505
+ reasoning: true,
9506
+ input: ["text", "image"],
9507
+ cost: {
9508
+ input: 0.7,
9509
+ output: 2.1,
9491
9510
  cacheRead: 0.07,
9492
9511
  cacheWrite: 0,
9493
9512
  },
@@ -9596,23 +9615,6 @@ export const MODELS = {
9596
9615
  contextWindow: 262144,
9597
9616
  maxTokens: 262144,
9598
9617
  },
9599
- "mistral-nemo": {
9600
- id: "mistral-nemo",
9601
- name: "Mistral Nemo",
9602
- api: "mistral-conversations",
9603
- provider: "mistral",
9604
- baseUrl: "https://api.mistral.ai",
9605
- reasoning: false,
9606
- input: ["text"],
9607
- cost: {
9608
- input: 0.15,
9609
- output: 0.15,
9610
- cacheRead: 0,
9611
- cacheWrite: 0,
9612
- },
9613
- contextWindow: 128000,
9614
- maxTokens: 128000,
9615
- },
9616
9618
  "mistral-small-2506": {
9617
9619
  id: "mistral-small-2506",
9618
9620
  name: "Mistral Small 3.2",
@@ -9698,23 +9700,6 @@ export const MODELS = {
9698
9700
  contextWindow: 128000,
9699
9701
  maxTokens: 128000,
9700
9702
  },
9701
- "pixtral-large-latest": {
9702
- id: "pixtral-large-latest",
9703
- name: "Pixtral Large (latest)",
9704
- api: "mistral-conversations",
9705
- provider: "mistral",
9706
- baseUrl: "https://api.mistral.ai",
9707
- reasoning: false,
9708
- input: ["text", "image"],
9709
- cost: {
9710
- input: 2,
9711
- output: 6,
9712
- cacheRead: 0,
9713
- cacheWrite: 0,
9714
- },
9715
- contextWindow: 128000,
9716
- maxTokens: 128000,
9717
- },
9718
9703
  "voxtral-small-2507": {
9719
9704
  id: "voxtral-small-2507",
9720
9705
  name: "Voxtral Small",
@@ -9783,6 +9768,23 @@ export const MODELS = {
9783
9768
  contextWindow: 1048576,
9784
9769
  maxTokens: 131072,
9785
9770
  },
9771
+ "zai-glm-5-3-flash": {
9772
+ id: "zai-glm-5-3-flash",
9773
+ name: "GLM-5.3-Flash",
9774
+ api: "mistral-conversations",
9775
+ provider: "mistral",
9776
+ baseUrl: "https://api.mistral.ai",
9777
+ reasoning: true,
9778
+ input: ["text", "image"],
9779
+ cost: {
9780
+ input: 0.15,
9781
+ output: 0.5,
9782
+ cacheRead: 0.03,
9783
+ cacheWrite: 0,
9784
+ },
9785
+ contextWindow: 1048576,
9786
+ maxTokens: 131072,
9787
+ },
9786
9788
  },
9787
9789
  "moonshotai": {
9788
9790
  "kimi-k2.6": {
@@ -9857,6 +9859,42 @@ export const MODELS = {
9857
9859
  contextWindow: 1048576,
9858
9860
  maxTokens: 1048576,
9859
9861
  },
9862
+ "kimi-k3.1-pro": {
9863
+ id: "kimi-k3.1-pro",
9864
+ name: "Kimi K3.1 Pro",
9865
+ api: "openai-completions",
9866
+ provider: "moonshotai",
9867
+ baseUrl: "https://api.moonshot.ai/v1",
9868
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
9869
+ reasoning: true,
9870
+ input: ["text", "image"],
9871
+ cost: {
9872
+ input: 2,
9873
+ output: 10,
9874
+ cacheRead: 0.2,
9875
+ cacheWrite: 2,
9876
+ },
9877
+ contextWindow: 1048576,
9878
+ maxTokens: 1048576,
9879
+ },
9880
+ "kimi-k3.1-pro-highspeed": {
9881
+ id: "kimi-k3.1-pro-highspeed",
9882
+ name: "Kimi K3.1 Pro Highspeed",
9883
+ api: "openai-completions",
9884
+ provider: "moonshotai",
9885
+ baseUrl: "https://api.moonshot.ai/v1",
9886
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
9887
+ reasoning: true,
9888
+ input: ["text", "image"],
9889
+ cost: {
9890
+ input: 4,
9891
+ output: 20,
9892
+ cacheRead: 0.2,
9893
+ cacheWrite: 4,
9894
+ },
9895
+ contextWindow: 1048576,
9896
+ maxTokens: 1048576,
9897
+ },
9860
9898
  },
9861
9899
  "moonshotai-cn": {
9862
9900
  "kimi-k2.6": {
@@ -9931,6 +9969,42 @@ export const MODELS = {
9931
9969
  contextWindow: 1048576,
9932
9970
  maxTokens: 1048576,
9933
9971
  },
9972
+ "kimi-k3.1-pro": {
9973
+ id: "kimi-k3.1-pro",
9974
+ name: "Kimi K3.1 Pro",
9975
+ api: "openai-completions",
9976
+ provider: "moonshotai-cn",
9977
+ baseUrl: "https://api.moonshot.cn/v1",
9978
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
9979
+ reasoning: true,
9980
+ input: ["text", "image"],
9981
+ cost: {
9982
+ input: 1.9437,
9983
+ output: 10.1671,
9984
+ cacheRead: 0.1944,
9985
+ cacheWrite: 1.9437,
9986
+ },
9987
+ contextWindow: 1048576,
9988
+ maxTokens: 1048576,
9989
+ },
9990
+ "kimi-k3.1-pro-highspeed": {
9991
+ id: "kimi-k3.1-pro-highspeed",
9992
+ name: "Kimi K3.1 Pro Highspeed",
9993
+ api: "openai-completions",
9994
+ provider: "moonshotai-cn",
9995
+ baseUrl: "https://api.moonshot.cn/v1",
9996
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
9997
+ reasoning: true,
9998
+ input: ["text", "image"],
9999
+ cost: {
10000
+ input: 3.8874,
10001
+ output: 20.3342,
10002
+ cacheRead: 0.1944,
10003
+ cacheWrite: 3.8874,
10004
+ },
10005
+ contextWindow: 1048576,
10006
+ maxTokens: 1048576,
10007
+ },
9934
10008
  },
9935
10009
  "openai": {
9936
10010
  "gpt-4": {
@@ -10499,6 +10573,23 @@ export const MODELS = {
10499
10573
  contextWindow: 1050000,
10500
10574
  maxTokens: 128000,
10501
10575
  },
10576
+ "gpt-6.1-terra": {
10577
+ id: "gpt-6.1-terra",
10578
+ name: "GPT-6.1 Terra",
10579
+ api: "openai-responses",
10580
+ provider: "openai",
10581
+ baseUrl: "https://api.openai.com/v1",
10582
+ reasoning: true,
10583
+ input: ["text", "image"],
10584
+ cost: {
10585
+ input: 1,
10586
+ output: 5,
10587
+ cacheRead: 0.05,
10588
+ cacheWrite: 1.25,
10589
+ },
10590
+ contextWindow: 1050000,
10591
+ maxTokens: 128000,
10592
+ },
10502
10593
  "gpt-daybreak-blue-latest": {
10503
10594
  id: "gpt-daybreak-blue-latest",
10504
10595
  name: "Daybreak Blue",
@@ -11043,23 +11134,6 @@ export const MODELS = {
11043
11134
  contextWindow: 1000000,
11044
11135
  maxTokens: 128000,
11045
11136
  },
11046
- "claude-sonnet-4": {
11047
- id: "claude-sonnet-4",
11048
- name: "Claude Sonnet 4",
11049
- api: "anthropic-messages",
11050
- provider: "opencode",
11051
- baseUrl: "https://opencode.ai/zen",
11052
- reasoning: true,
11053
- input: ["text", "image"],
11054
- cost: {
11055
- input: 3,
11056
- output: 15,
11057
- cacheRead: 0.3,
11058
- cacheWrite: 3.75,
11059
- },
11060
- contextWindow: 200000,
11061
- maxTokens: 64000,
11062
- },
11063
11137
  "claude-sonnet-4-5": {
11064
11138
  id: "claude-sonnet-4-5",
11065
11139
  name: "Claude Sonnet 4.5",
@@ -11128,44 +11202,6 @@ export const MODELS = {
11128
11202
  contextWindow: 1000000,
11129
11203
  maxTokens: 128000,
11130
11204
  },
11131
- "deepseek-v4-flash": {
11132
- id: "deepseek-v4-flash",
11133
- name: "DeepSeek V4 Flash",
11134
- api: "openai-completions",
11135
- provider: "opencode",
11136
- baseUrl: "https://opencode.ai/zen/v1",
11137
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11138
- reasoning: true,
11139
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11140
- input: ["text"],
11141
- cost: {
11142
- input: 0.14,
11143
- output: 0.28,
11144
- cacheRead: 0.028,
11145
- cacheWrite: 0,
11146
- },
11147
- contextWindow: 1000000,
11148
- maxTokens: 384000,
11149
- },
11150
- "deepseek-v4-flash-vision-exp": {
11151
- id: "deepseek-v4-flash-vision-exp",
11152
- name: "DeepSeek V4 Flash Vision Exp",
11153
- api: "openai-completions",
11154
- provider: "opencode",
11155
- baseUrl: "https://opencode.ai/zen/v1",
11156
- compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
11157
- reasoning: true,
11158
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
11159
- input: ["text", "image"],
11160
- cost: {
11161
- input: 0.14,
11162
- output: 0.28,
11163
- cacheRead: 0.028,
11164
- cacheWrite: 0,
11165
- },
11166
- contextWindow: 1000000,
11167
- maxTokens: 384000,
11168
- },
11169
11205
  "deepseek-v4-pro": {
11170
11206
  id: "deepseek-v4-pro",
11171
11207
  name: "DeepSeek V4 Pro",
@@ -11178,7 +11214,7 @@ export const MODELS = {
11178
11214
  input: ["text"],
11179
11215
  cost: {
11180
11216
  input: 1.74,
11181
- output: 3.84,
11217
+ output: 3.48,
11182
11218
  cacheRead: 0.145,
11183
11219
  cacheWrite: 0,
11184
11220
  },
@@ -11223,6 +11259,23 @@ export const MODELS = {
11223
11259
  contextWindow: 200000,
11224
11260
  maxTokens: 32000,
11225
11261
  },
11262
+ "flint-40b-free": {
11263
+ id: "flint-40b-free",
11264
+ name: "Flint 40B Free",
11265
+ api: "openai-completions",
11266
+ provider: "opencode",
11267
+ baseUrl: "https://opencode.ai/zen/v1",
11268
+ reasoning: true,
11269
+ input: ["text"],
11270
+ cost: {
11271
+ input: 0,
11272
+ output: 0,
11273
+ cacheRead: 0,
11274
+ cacheWrite: 0,
11275
+ },
11276
+ contextWindow: 262144,
11277
+ maxTokens: 65536,
11278
+ },
11226
11279
  "gemini-3-flash": {
11227
11280
  id: "gemini-3-flash",
11228
11281
  name: "Gemini 3 Flash",
@@ -11802,10 +11855,10 @@ export const MODELS = {
11802
11855
  thinkingLevelMap: { "off": null },
11803
11856
  input: ["text", "image"],
11804
11857
  cost: {
11805
- input: 2.5,
11806
- output: 15,
11807
- cacheRead: 0.25,
11808
- cacheWrite: 3.125,
11858
+ input: 2,
11859
+ output: 12,
11860
+ cacheRead: 0.2,
11861
+ cacheWrite: 2.5,
11809
11862
  },
11810
11863
  contextWindow: 1050000,
11811
11864
  maxTokens: 128000,
@@ -11957,7 +12010,7 @@ export const MODELS = {
11957
12010
  cost: {
11958
12011
  input: 0.6,
11959
12012
  output: 3,
11960
- cacheRead: 0.08,
12013
+ cacheRead: 0.1,
11961
12014
  cacheWrite: 0,
11962
12015
  },
11963
12016
  contextWindow: 262144,
@@ -12009,28 +12062,11 @@ export const MODELS = {
12009
12062
  input: 3,
12010
12063
  output: 15,
12011
12064
  cacheRead: 0.3,
12012
- cacheWrite: 0,
12065
+ cacheWrite: 3,
12013
12066
  },
12014
12067
  contextWindow: 1048576,
12015
12068
  maxTokens: 131072,
12016
12069
  },
12017
- "longcat-2.5-preview-free": {
12018
- id: "longcat-2.5-preview-free",
12019
- name: "LongCat 2.5 Preview Free",
12020
- api: "openai-completions",
12021
- provider: "opencode",
12022
- baseUrl: "https://opencode.ai/zen/v1",
12023
- reasoning: true,
12024
- input: ["text", "image"],
12025
- cost: {
12026
- input: 0,
12027
- output: 0,
12028
- cacheRead: 0,
12029
- cacheWrite: 0,
12030
- },
12031
- contextWindow: 1000000,
12032
- maxTokens: 131072,
12033
- },
12034
12070
  "mimo-v2.6-flash-free": {
12035
12071
  id: "mimo-v2.6-flash-free",
12036
12072
  name: "MiMo-V2.6-Flash Free",
@@ -12099,23 +12135,6 @@ export const MODELS = {
12099
12135
  contextWindow: 512000,
12100
12136
  maxTokens: 128000,
12101
12137
  },
12102
- "minimax-m3.1-flash-free": {
12103
- id: "minimax-m3.1-flash-free",
12104
- name: "MiniMax M3.1 Flash Free",
12105
- api: "openai-completions",
12106
- provider: "opencode",
12107
- baseUrl: "https://opencode.ai/zen/v1",
12108
- reasoning: true,
12109
- input: ["text", "image"],
12110
- cost: {
12111
- input: 0,
12112
- output: 0,
12113
- cacheRead: 0,
12114
- cacheWrite: 0,
12115
- },
12116
- contextWindow: 1000000,
12117
- maxTokens: 512000,
12118
- },
12119
12138
  "mistral-large-4": {
12120
12139
  id: "mistral-large-4",
12121
12140
  name: "Mistral Large 4",
@@ -12184,23 +12203,6 @@ export const MODELS = {
12184
12203
  contextWindow: 1048576,
12185
12204
  maxTokens: 131072,
12186
12205
  },
12187
- "nemotron-3-ultra-free": {
12188
- id: "nemotron-3-ultra-free",
12189
- name: "Nemotron 3 Ultra Free",
12190
- api: "openai-completions",
12191
- provider: "opencode",
12192
- baseUrl: "https://opencode.ai/zen/v1",
12193
- reasoning: true,
12194
- input: ["text"],
12195
- cost: {
12196
- input: 0,
12197
- output: 0,
12198
- cacheRead: 0,
12199
- cacheWrite: 0,
12200
- },
12201
- contextWindow: 1000000,
12202
- maxTokens: 128000,
12203
- },
12204
12206
  "nemotron-3.5-lightning-free": {
12205
12207
  id: "nemotron-3.5-lightning-free",
12206
12208
  name: "Nemotron 3.5 Lightning Free",
@@ -12377,18 +12379,18 @@ export const MODELS = {
12377
12379
  contextWindow: 1000000,
12378
12380
  maxTokens: 384000,
12379
12381
  },
12380
- "gemini-4-argon-contributor": {
12381
- id: "gemini-4-argon-contributor",
12382
- name: "Gemini 4 Argon Contributor",
12383
- api: "google-generative-ai",
12382
+ "gemini-4-argon": {
12383
+ id: "gemini-4-argon",
12384
+ name: "Gemini 4 Argon",
12385
+ api: "google-generative-ai",
12384
12386
  provider: "opencode-go",
12385
12387
  baseUrl: "https://opencode.ai/zen/go/v1",
12386
12388
  reasoning: true,
12387
12389
  input: ["text", "image"],
12388
12390
  cost: {
12389
- input: 4,
12390
- output: 20,
12391
- cacheRead: 0.2,
12391
+ input: 2,
12392
+ output: 10,
12393
+ cacheRead: 0.1,
12392
12394
  cacheWrite: 0,
12393
12395
  },
12394
12396
  contextWindow: 1048576,
@@ -12531,6 +12533,23 @@ export const MODELS = {
12531
12533
  contextWindow: 1024000,
12532
12534
  maxTokens: 64000,
12533
12535
  },
12536
+ "iceman-contributor-free": {
12537
+ id: "iceman-contributor-free",
12538
+ name: "Iceman Contributor Free",
12539
+ api: "openai-completions",
12540
+ provider: "opencode-go",
12541
+ baseUrl: "https://opencode.ai/zen/go/v1",
12542
+ reasoning: true,
12543
+ input: ["text"],
12544
+ cost: {
12545
+ input: 0,
12546
+ output: 0,
12547
+ cacheRead: 0,
12548
+ cacheWrite: 0,
12549
+ },
12550
+ contextWindow: 262144,
12551
+ maxTokens: 131072,
12552
+ },
12534
12553
  "kimi-k2.7-code": {
12535
12554
  id: "kimi-k2.7-code",
12536
12555
  name: "Kimi K2.7 Code",
@@ -12560,40 +12579,40 @@ export const MODELS = {
12560
12579
  input: 3,
12561
12580
  output: 15,
12562
12581
  cacheRead: 0.3,
12563
- cacheWrite: 0,
12582
+ cacheWrite: 3,
12564
12583
  },
12565
12584
  contextWindow: 1048576,
12566
12585
  maxTokens: 131072,
12567
12586
  },
12568
- "longcat-2.0": {
12569
- id: "longcat-2.0",
12570
- name: "LongCat-2.0",
12587
+ "kimi-k3.1-pro": {
12588
+ id: "kimi-k3.1-pro",
12589
+ name: "Kimi K3.1 Pro",
12571
12590
  api: "openai-completions",
12572
12591
  provider: "opencode-go",
12573
12592
  baseUrl: "https://opencode.ai/zen/go/v1",
12574
12593
  reasoning: true,
12575
- input: ["text"],
12594
+ input: ["text", "image"],
12576
12595
  cost: {
12577
- input: 0.3,
12578
- output: 1.2,
12579
- cacheRead: 0.006,
12580
- cacheWrite: 0,
12596
+ input: 2,
12597
+ output: 10,
12598
+ cacheRead: 0.2,
12599
+ cacheWrite: 2,
12581
12600
  },
12582
- contextWindow: 1000000,
12601
+ contextWindow: 1048576,
12583
12602
  maxTokens: 131072,
12584
12603
  },
12585
- "longcat-2.5-preview-free": {
12586
- id: "longcat-2.5-preview-free",
12587
- name: "LongCat 2.5 Preview Free",
12604
+ "longcat-2.0": {
12605
+ id: "longcat-2.0",
12606
+ name: "LongCat-2.0",
12588
12607
  api: "openai-completions",
12589
12608
  provider: "opencode-go",
12590
12609
  baseUrl: "https://opencode.ai/zen/go/v1",
12591
12610
  reasoning: true,
12592
- input: ["text", "image"],
12611
+ input: ["text"],
12593
12612
  cost: {
12594
- input: 0,
12595
- output: 0,
12596
- cacheRead: 0,
12613
+ input: 0.3,
12614
+ output: 1.2,
12615
+ cacheRead: 0.006,
12597
12616
  cacheWrite: 0,
12598
12617
  },
12599
12618
  contextWindow: 1000000,
@@ -12684,18 +12703,18 @@ export const MODELS = {
12684
12703
  contextWindow: 1000000,
12685
12704
  maxTokens: 131072,
12686
12705
  },
12687
- "minimax-m3.1-flash-free": {
12688
- id: "minimax-m3.1-flash-free",
12689
- name: "MiniMax M3.1 Flash Free",
12706
+ "minimax-m3.1-flash": {
12707
+ id: "minimax-m3.1-flash",
12708
+ name: "MiniMax M3.1 Flash",
12690
12709
  api: "openai-completions",
12691
12710
  provider: "opencode-go",
12692
12711
  baseUrl: "https://opencode.ai/zen/go/v1",
12693
12712
  reasoning: true,
12694
12713
  input: ["text", "image"],
12695
12714
  cost: {
12696
- input: 0,
12697
- output: 0,
12698
- cacheRead: 0,
12715
+ input: 0.15,
12716
+ output: 0.6,
12717
+ cacheRead: 0.015,
12699
12718
  cacheWrite: 0,
12700
12719
  },
12701
12720
  contextWindow: 1000000,
@@ -13495,23 +13514,6 @@ export const MODELS = {
13495
13514
  contextWindow: 1000000,
13496
13515
  maxTokens: 128000,
13497
13516
  },
13498
- "arcee-ai/trinity-large-thinking": {
13499
- id: "arcee-ai/trinity-large-thinking",
13500
- name: "Arcee AI: Trinity Large Thinking",
13501
- api: "openai-completions",
13502
- provider: "openrouter",
13503
- baseUrl: "https://openrouter.ai/api/v1",
13504
- reasoning: true,
13505
- input: ["text"],
13506
- cost: {
13507
- input: 0.25,
13508
- output: 0.7999999999999999,
13509
- cacheRead: 0.06,
13510
- cacheWrite: 0,
13511
- },
13512
- contextWindow: 262144,
13513
- maxTokens: 80000,
13514
- },
13515
13517
  "auto": {
13516
13518
  id: "auto",
13517
13519
  name: "Auto",
@@ -13748,7 +13750,7 @@ export const MODELS = {
13748
13750
  cacheWrite: 0,
13749
13751
  },
13750
13752
  contextWindow: 163840,
13751
- maxTokens: 32768,
13753
+ maxTokens: 147456,
13752
13754
  },
13753
13755
  "deepseek/deepseek-r1-0528": {
13754
13756
  id: "deepseek/deepseek-r1-0528",
@@ -13793,13 +13795,13 @@ export const MODELS = {
13793
13795
  reasoning: true,
13794
13796
  input: ["text"],
13795
13797
  cost: {
13796
- input: 0.28,
13797
- output: 0.42,
13798
- cacheRead: 0.028,
13798
+ input: 0.26,
13799
+ output: 0.38,
13800
+ cacheRead: 0.13,
13799
13801
  cacheWrite: 0,
13800
13802
  },
13801
13803
  contextWindow: 163840,
13802
- maxTokens: 65536,
13804
+ maxTokens: 147456,
13803
13805
  },
13804
13806
  "deepseek/deepseek-v3.2-exp": {
13805
13807
  id: "deepseek/deepseek-v3.2-exp",
@@ -13848,13 +13850,13 @@ export const MODELS = {
13848
13850
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13849
13851
  input: ["text"],
13850
13852
  cost: {
13851
- input: 0.44,
13852
- output: 1.32,
13853
- cacheRead: 0.014,
13853
+ input: 0.119,
13854
+ output: 0.238,
13855
+ cacheRead: 0.0238,
13854
13856
  cacheWrite: 0,
13855
13857
  },
13856
13858
  contextWindow: 1048576,
13857
- maxTokens: 131072,
13859
+ maxTokens: 943718,
13858
13860
  },
13859
13861
  "deepseek/deepseek-v4-flash-vision-exp": {
13860
13862
  id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -13886,13 +13888,13 @@ export const MODELS = {
13886
13888
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13887
13889
  input: ["text"],
13888
13890
  cost: {
13889
- input: 0.9552599999999999,
13890
- output: 1.9105199999999998,
13891
- cacheRead: 0.07960500000000001,
13891
+ input: 1.5999999999999999,
13892
+ output: 3.1999999999999997,
13893
+ cacheRead: 0.135,
13892
13894
  cacheWrite: 0,
13893
13895
  },
13894
13896
  contextWindow: 1048576,
13895
- maxTokens: 384000,
13897
+ maxTokens: 393216,
13896
13898
  },
13897
13899
  "deepseek/deepseek-v4-pro-0813": {
13898
13900
  id: "deepseek/deepseek-v4-pro-0813",
@@ -13905,13 +13907,13 @@ export const MODELS = {
13905
13907
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13906
13908
  input: ["text"],
13907
13909
  cost: {
13908
- input: 0.66,
13909
- output: 1.9800000000000002,
13910
- cacheRead: 0.022,
13910
+ input: 0.11499999999999999,
13911
+ output: 4,
13912
+ cacheRead: 0.11,
13911
13913
  cacheWrite: 0,
13912
13914
  },
13913
13915
  contextWindow: 1048576,
13914
- maxTokens: 384000,
13916
+ maxTokens: 943718,
13915
13917
  },
13916
13918
  "deepseek/deepseek-v4.1-flash": {
13917
13919
  id: "deepseek/deepseek-v4.1-flash",
@@ -13924,9 +13926,9 @@ export const MODELS = {
13924
13926
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
13925
13927
  input: ["text", "image"],
13926
13928
  cost: {
13927
- input: 0.049,
13928
- output: 0.5249999999999999,
13929
- cacheRead: 0.001,
13929
+ input: 0.045,
13930
+ output: 0.5,
13931
+ cacheRead: 0.006,
13930
13932
  cacheWrite: 0,
13931
13933
  },
13932
13934
  contextWindow: 1048576,
@@ -14055,23 +14057,6 @@ export const MODELS = {
14055
14057
  contextWindow: 1048576,
14056
14058
  maxTokens: 65535,
14057
14059
  },
14058
- "google/gemini-2.5-flash-lite:batch": {
14059
- id: "google/gemini-2.5-flash-lite:batch",
14060
- name: "Google: Gemini 2.5 Flash Lite (batch)",
14061
- api: "openai-completions",
14062
- provider: "openrouter",
14063
- baseUrl: "https://openrouter.ai/api/v1",
14064
- reasoning: true,
14065
- input: ["text", "image"],
14066
- cost: {
14067
- input: 0.049999999999999996,
14068
- output: 0.19999999999999998,
14069
- cacheRead: 0.01,
14070
- cacheWrite: 0,
14071
- },
14072
- contextWindow: 1048576,
14073
- maxTokens: 65535,
14074
- },
14075
14060
  "google/gemini-2.5-pro": {
14076
14061
  id: "google/gemini-2.5-pro",
14077
14062
  name: "Google: Gemini 2.5 Pro",
@@ -14523,9 +14508,9 @@ export const MODELS = {
14523
14508
  reasoning: true,
14524
14509
  input: ["text", "image"],
14525
14510
  cost: {
14526
- input: 0.0765,
14527
- output: 0.255,
14528
- cacheRead: 0.042499999999999996,
14511
+ input: 0.0675,
14512
+ output: 0.22499999999999998,
14513
+ cacheRead: 0.0375,
14529
14514
  cacheWrite: 0,
14530
14515
  },
14531
14516
  contextWindow: 262144,
@@ -14592,7 +14577,7 @@ export const MODELS = {
14592
14577
  input: ["text"],
14593
14578
  cost: {
14594
14579
  input: 0.06,
14595
- output: 0.25,
14580
+ output: 0.15,
14596
14581
  cacheRead: 0.015,
14597
14582
  cacheWrite: 0,
14598
14583
  },
@@ -14698,8 +14683,25 @@ export const MODELS = {
14698
14683
  cacheRead: 0.015,
14699
14684
  cacheWrite: 0,
14700
14685
  },
14701
- contextWindow: 262144,
14702
- maxTokens: 235929,
14686
+ contextWindow: 1000000,
14687
+ maxTokens: 262144,
14688
+ },
14689
+ "liquid/lfm-2.5-2.6b": {
14690
+ id: "liquid/lfm-2.5-2.6b",
14691
+ name: "LiquidAI: LFM2.5-2.6B",
14692
+ api: "openai-completions",
14693
+ provider: "openrouter",
14694
+ baseUrl: "https://openrouter.ai/api/v1",
14695
+ reasoning: true,
14696
+ input: ["text"],
14697
+ cost: {
14698
+ input: 0.35,
14699
+ output: 0.5,
14700
+ cacheRead: 0.04,
14701
+ cacheWrite: 0,
14702
+ },
14703
+ contextWindow: 128000,
14704
+ maxTokens: 8192,
14703
14705
  },
14704
14706
  "liquid/lfm-2.5-2.6b:free": {
14705
14707
  id: "liquid/lfm-2.5-2.6b:free",
@@ -14954,7 +14956,7 @@ export const MODELS = {
14954
14956
  cacheWrite: 0,
14955
14957
  },
14956
14958
  contextWindow: 1048576,
14957
- maxTokens: 943718,
14959
+ maxTokens: 131072,
14958
14960
  },
14959
14961
  "meta/muse-wonder": {
14960
14962
  id: "meta/muse-wonder",
@@ -15075,21 +15077,21 @@ export const MODELS = {
15075
15077
  contextWindow: 1048576,
15076
15078
  maxTokens: 512000,
15077
15079
  },
15078
- "minimax/minimax-m3.1-flash:free": {
15079
- id: "minimax/minimax-m3.1-flash:free",
15080
- name: "MiniMax: MiniMax M3.1 Flash (free)",
15080
+ "minimax/minimax-m3.1-flash": {
15081
+ id: "minimax/minimax-m3.1-flash",
15082
+ name: "MiniMax: MiniMax M3.1 Flash",
15081
15083
  api: "openai-completions",
15082
15084
  provider: "openrouter",
15083
15085
  baseUrl: "https://openrouter.ai/api/v1",
15084
15086
  reasoning: true,
15085
15087
  input: ["text", "image"],
15086
15088
  cost: {
15087
- input: 0,
15088
- output: 0,
15089
- cacheRead: 0,
15089
+ input: 0.075,
15090
+ output: 0.3,
15091
+ cacheRead: 0.0075,
15090
15092
  cacheWrite: 0,
15091
15093
  },
15092
- contextWindow: 1000000,
15094
+ contextWindow: 1048576,
15093
15095
  maxTokens: 524288,
15094
15096
  },
15095
15097
  "mistralai/codestral-2508": {
@@ -15109,23 +15111,6 @@ export const MODELS = {
15109
15111
  contextWindow: 256000,
15110
15112
  maxTokens: 204800,
15111
15113
  },
15112
- "mistralai/codestral-2508:batch": {
15113
- id: "mistralai/codestral-2508:batch",
15114
- name: "Mistral: Codestral 2508 (batch)",
15115
- api: "openai-completions",
15116
- provider: "openrouter",
15117
- baseUrl: "https://openrouter.ai/api/v1",
15118
- reasoning: false,
15119
- input: ["text"],
15120
- cost: {
15121
- input: 0.15,
15122
- output: 0.44999999999999996,
15123
- cacheRead: 0.015,
15124
- cacheWrite: 0,
15125
- },
15126
- contextWindow: 256000,
15127
- maxTokens: 204800,
15128
- },
15129
15114
  "mistralai/devstral-2512": {
15130
15115
  id: "mistralai/devstral-2512",
15131
15116
  name: "Mistral: Devstral 2 2512",
@@ -15194,23 +15179,6 @@ export const MODELS = {
15194
15179
  contextWindow: 262144,
15195
15180
  maxTokens: 209715,
15196
15181
  },
15197
- "mistralai/ministral-8b-2512:batch": {
15198
- id: "mistralai/ministral-8b-2512:batch",
15199
- name: "Mistral: Ministral 3 8B 2512 (batch)",
15200
- api: "openai-completions",
15201
- provider: "openrouter",
15202
- baseUrl: "https://openrouter.ai/api/v1",
15203
- reasoning: false,
15204
- input: ["text", "image"],
15205
- cost: {
15206
- input: 0.075,
15207
- output: 0.075,
15208
- cacheRead: 0.0075,
15209
- cacheWrite: 0,
15210
- },
15211
- contextWindow: 262144,
15212
- maxTokens: 209715,
15213
- },
15214
15182
  "mistralai/mistral-large": {
15215
15183
  id: "mistralai/mistral-large",
15216
15184
  name: "Mistral Large",
@@ -15262,23 +15230,6 @@ export const MODELS = {
15262
15230
  contextWindow: 262144,
15263
15231
  maxTokens: 209715,
15264
15232
  },
15265
- "mistralai/mistral-large-2512:batch": {
15266
- id: "mistralai/mistral-large-2512:batch",
15267
- name: "Mistral: Mistral Large 3 2512 (batch)",
15268
- api: "openai-completions",
15269
- provider: "openrouter",
15270
- baseUrl: "https://openrouter.ai/api/v1",
15271
- reasoning: false,
15272
- input: ["text", "image"],
15273
- cost: {
15274
- input: 0.25,
15275
- output: 0.75,
15276
- cacheRead: 0.024999999999999998,
15277
- cacheWrite: 0,
15278
- },
15279
- contextWindow: 262144,
15280
- maxTokens: 209715,
15281
- },
15282
15233
  "mistralai/mistral-large-4-0": {
15283
15234
  id: "mistralai/mistral-large-4-0",
15284
15235
  name: "Mistral: Mistral Large 4",
@@ -15288,9 +15239,9 @@ export const MODELS = {
15288
15239
  reasoning: true,
15289
15240
  input: ["text", "image"],
15290
15241
  cost: {
15291
- input: 1.3599999999999999,
15292
- output: 4.18,
15293
- cacheRead: 0.14,
15242
+ input: 0.7,
15243
+ output: 2.0999999999999996,
15244
+ cacheRead: 0.07,
15294
15245
  cacheWrite: 0,
15295
15246
  },
15296
15247
  contextWindow: 1048576,
@@ -15364,23 +15315,6 @@ export const MODELS = {
15364
15315
  contextWindow: 131072,
15365
15316
  maxTokens: 104857,
15366
15317
  },
15367
- "mistralai/mistral-medium-3.1:batch": {
15368
- id: "mistralai/mistral-medium-3.1:batch",
15369
- name: "Mistral: Mistral Medium 3.1 (batch)",
15370
- api: "openai-completions",
15371
- provider: "openrouter",
15372
- baseUrl: "https://openrouter.ai/api/v1",
15373
- reasoning: false,
15374
- input: ["text", "image"],
15375
- cost: {
15376
- input: 0.19999999999999998,
15377
- output: 1,
15378
- cacheRead: 0.02,
15379
- cacheWrite: 0,
15380
- },
15381
- contextWindow: 131072,
15382
- maxTokens: 104857,
15383
- },
15384
15318
  "mistralai/mistral-nemo": {
15385
15319
  id: "mistralai/mistral-nemo",
15386
15320
  name: "Mistral: Mistral Nemo",
@@ -15432,23 +15366,6 @@ export const MODELS = {
15432
15366
  contextWindow: 262144,
15433
15367
  maxTokens: 209715,
15434
15368
  },
15435
- "mistralai/mistral-small-2603:batch": {
15436
- id: "mistralai/mistral-small-2603:batch",
15437
- name: "Mistral: Mistral Small 4 (batch)",
15438
- api: "openai-completions",
15439
- provider: "openrouter",
15440
- baseUrl: "https://openrouter.ai/api/v1",
15441
- reasoning: true,
15442
- input: ["text", "image"],
15443
- cost: {
15444
- input: 0.075,
15445
- output: 0.3,
15446
- cacheRead: 0.0075,
15447
- cacheWrite: 0,
15448
- },
15449
- contextWindow: 262144,
15450
- maxTokens: 209715,
15451
- },
15452
15369
  "mistralai/mistral-small-3.1-24b-instruct": {
15453
15370
  id: "mistralai/mistral-small-3.1-24b-instruct",
15454
15371
  name: "Mistral: Mistral Small 3.1 24B",
@@ -15475,8 +15392,8 @@ export const MODELS = {
15475
15392
  reasoning: false,
15476
15393
  input: ["text", "image"],
15477
15394
  cost: {
15478
- input: 0.09375,
15479
- output: 0.25,
15395
+ input: 0.075,
15396
+ output: 0.19999999999999998,
15480
15397
  cacheRead: 0,
15481
15398
  cacheWrite: 0,
15482
15399
  },
@@ -15611,9 +15528,9 @@ export const MODELS = {
15611
15528
  reasoning: true,
15612
15529
  input: ["text", "image"],
15613
15530
  cost: {
15614
- input: 0.6712,
15615
- output: 3.35,
15616
- cacheRead: 0.18,
15531
+ input: 0.6,
15532
+ output: 3.5,
15533
+ cacheRead: 0.15,
15617
15534
  cacheWrite: 0,
15618
15535
  },
15619
15536
  contextWindow: 262144,
@@ -15628,9 +15545,26 @@ export const MODELS = {
15628
15545
  reasoning: true,
15629
15546
  input: ["text", "image"],
15630
15547
  cost: {
15631
- input: 0.23900000000000002,
15632
- output: 11.936,
15633
- cacheRead: 0.21,
15548
+ input: 0.192,
15549
+ output: 15,
15550
+ cacheRead: 0.182,
15551
+ cacheWrite: 0,
15552
+ },
15553
+ contextWindow: 1048576,
15554
+ maxTokens: 943718,
15555
+ },
15556
+ "moonshotai/kimi-k3.1-pro": {
15557
+ id: "moonshotai/kimi-k3.1-pro",
15558
+ name: "MoonshotAI: Kimi K3.1 Pro",
15559
+ api: "openai-completions",
15560
+ provider: "openrouter",
15561
+ baseUrl: "https://openrouter.ai/api/v1",
15562
+ reasoning: true,
15563
+ input: ["text", "image"],
15564
+ cost: {
15565
+ input: 2,
15566
+ output: 10,
15567
+ cacheRead: 0.19999999999999998,
15634
15568
  cacheWrite: 0,
15635
15569
  },
15636
15570
  contextWindow: 1048576,
@@ -15681,7 +15615,7 @@ export const MODELS = {
15681
15615
  cost: {
15682
15616
  input: 0.06,
15683
15617
  output: 0.24,
15684
- cacheRead: 0,
15618
+ cacheRead: 0.012,
15685
15619
  cacheWrite: 0,
15686
15620
  },
15687
15621
  contextWindow: 262144,
@@ -15718,38 +15652,21 @@ export const MODELS = {
15718
15652
  cacheRead: 0.15,
15719
15653
  cacheWrite: 0,
15720
15654
  },
15721
- contextWindow: 262144,
15722
- maxTokens: 235929,
15655
+ contextWindow: 1048576,
15656
+ maxTokens: 262144,
15723
15657
  },
15724
- "nvidia/nemotron-3-super-120b-a12b:free": {
15725
- id: "nvidia/nemotron-3-super-120b-a12b:free",
15726
- name: "NVIDIA: Nemotron 3 Super (free)",
15658
+ "nvidia/nemotron-3-ultra-550b-a55b": {
15659
+ id: "nvidia/nemotron-3-ultra-550b-a55b",
15660
+ name: "NVIDIA: Nemotron 3 Ultra",
15727
15661
  api: "openai-completions",
15728
15662
  provider: "openrouter",
15729
15663
  baseUrl: "https://openrouter.ai/api/v1",
15730
15664
  reasoning: true,
15731
15665
  input: ["text"],
15732
15666
  cost: {
15733
- input: 0,
15734
- output: 0,
15735
- cacheRead: 0,
15736
- cacheWrite: 0,
15737
- },
15738
- contextWindow: 262144,
15739
- maxTokens: 235929,
15740
- },
15741
- "nvidia/nemotron-3-ultra-550b-a55b": {
15742
- id: "nvidia/nemotron-3-ultra-550b-a55b",
15743
- name: "NVIDIA: Nemotron 3 Ultra",
15744
- api: "openai-completions",
15745
- provider: "openrouter",
15746
- baseUrl: "https://openrouter.ai/api/v1",
15747
- reasoning: true,
15748
- input: ["text"],
15749
- cost: {
15750
- input: 0.6,
15751
- output: 2.4,
15752
- cacheRead: 0.12,
15667
+ input: 0.6,
15668
+ output: 2.4,
15669
+ cacheRead: 0.12,
15753
15670
  cacheWrite: 0,
15754
15671
  },
15755
15672
  contextWindow: 262144,
@@ -15840,23 +15757,6 @@ export const MODELS = {
15840
15757
  contextWindow: 1000000,
15841
15758
  maxTokens: 131072,
15842
15759
  },
15843
- "openai/gpt-3.5-turbo": {
15844
- id: "openai/gpt-3.5-turbo",
15845
- name: "OpenAI: GPT-3.5 Turbo",
15846
- api: "openai-completions",
15847
- provider: "openrouter",
15848
- baseUrl: "https://openrouter.ai/api/v1",
15849
- reasoning: false,
15850
- input: ["text"],
15851
- cost: {
15852
- input: 0.5,
15853
- output: 1.5,
15854
- cacheRead: 0,
15855
- cacheWrite: 0,
15856
- },
15857
- contextWindow: 16385,
15858
- maxTokens: 4096,
15859
- },
15860
15760
  "openai/gpt-3.5-turbo-0613": {
15861
15761
  id: "openai/gpt-3.5-turbo-0613",
15862
15762
  name: "OpenAI: GPT-3.5 Turbo (older v0613)",
@@ -15891,23 +15791,6 @@ export const MODELS = {
15891
15791
  contextWindow: 16385,
15892
15792
  maxTokens: 4096,
15893
15793
  },
15894
- "openai/gpt-3.5-turbo:batch": {
15895
- id: "openai/gpt-3.5-turbo:batch",
15896
- name: "OpenAI: GPT-3.5 Turbo (batch)",
15897
- api: "openai-completions",
15898
- provider: "openrouter",
15899
- baseUrl: "https://openrouter.ai/api/v1",
15900
- reasoning: false,
15901
- input: ["text"],
15902
- cost: {
15903
- input: 0.25,
15904
- output: 0.75,
15905
- cacheRead: 0,
15906
- cacheWrite: 0,
15907
- },
15908
- contextWindow: 16385,
15909
- maxTokens: 4096,
15910
- },
15911
15794
  "openai/gpt-4": {
15912
15795
  id: "openai/gpt-4",
15913
15796
  name: "OpenAI: GPT-4",
@@ -16004,11 +15887,11 @@ export const MODELS = {
16004
15887
  cost: {
16005
15888
  input: 0.09999999999999999,
16006
15889
  output: 0.39999999999999997,
16007
- cacheRead: 0.024999999999999998,
15890
+ cacheRead: 0.03,
16008
15891
  cacheWrite: 0,
16009
15892
  },
16010
15893
  contextWindow: 1047576,
16011
- maxTokens: 32768,
15894
+ maxTokens: 942818,
16012
15895
  },
16013
15896
  "openai/gpt-4.1-nano:batch": {
16014
15897
  id: "openai/gpt-4.1-nano:batch",
@@ -17151,6 +17034,74 @@ export const MODELS = {
17151
17034
  contextWindow: 1050000,
17152
17035
  maxTokens: 128000,
17153
17036
  },
17037
+ "openai/gpt-6.1-terra": {
17038
+ id: "openai/gpt-6.1-terra",
17039
+ name: "OpenAI: GPT-6.1 Terra",
17040
+ api: "openai-completions",
17041
+ provider: "openrouter",
17042
+ baseUrl: "https://openrouter.ai/api/v1",
17043
+ reasoning: true,
17044
+ input: ["text", "image"],
17045
+ cost: {
17046
+ input: 1,
17047
+ output: 5,
17048
+ cacheRead: 0.049999999999999996,
17049
+ cacheWrite: 1.25,
17050
+ },
17051
+ contextWindow: 1050000,
17052
+ maxTokens: 128000,
17053
+ },
17054
+ "openai/gpt-6.1-terra-pro": {
17055
+ id: "openai/gpt-6.1-terra-pro",
17056
+ name: "OpenAI: GPT-6.1 Terra Pro",
17057
+ api: "openai-completions",
17058
+ provider: "openrouter",
17059
+ baseUrl: "https://openrouter.ai/api/v1",
17060
+ reasoning: true,
17061
+ input: ["text", "image"],
17062
+ cost: {
17063
+ input: 1,
17064
+ output: 5,
17065
+ cacheRead: 0.049999999999999996,
17066
+ cacheWrite: 1.25,
17067
+ },
17068
+ contextWindow: 1050000,
17069
+ maxTokens: 128000,
17070
+ },
17071
+ "openai/gpt-6.1-terra-pro:batch": {
17072
+ id: "openai/gpt-6.1-terra-pro:batch",
17073
+ name: "OpenAI: GPT-6.1 Terra Pro (batch)",
17074
+ api: "openai-completions",
17075
+ provider: "openrouter",
17076
+ baseUrl: "https://openrouter.ai/api/v1",
17077
+ reasoning: true,
17078
+ input: ["text", "image"],
17079
+ cost: {
17080
+ input: 0.5,
17081
+ output: 2.5,
17082
+ cacheRead: 0.024999999999999998,
17083
+ cacheWrite: 0.625,
17084
+ },
17085
+ contextWindow: 1050000,
17086
+ maxTokens: 128000,
17087
+ },
17088
+ "openai/gpt-6.1-terra:batch": {
17089
+ id: "openai/gpt-6.1-terra:batch",
17090
+ name: "OpenAI: GPT-6.1 Terra (batch)",
17091
+ api: "openai-completions",
17092
+ provider: "openrouter",
17093
+ baseUrl: "https://openrouter.ai/api/v1",
17094
+ reasoning: true,
17095
+ input: ["text", "image"],
17096
+ cost: {
17097
+ input: 0.5,
17098
+ output: 2.5,
17099
+ cacheRead: 0.024999999999999998,
17100
+ cacheWrite: 0.625,
17101
+ },
17102
+ contextWindow: 1050000,
17103
+ maxTokens: 128000,
17104
+ },
17154
17105
  "openai/gpt-audio": {
17155
17106
  id: "openai/gpt-audio",
17156
17107
  name: "OpenAI: GPT Audio",
@@ -17211,9 +17162,9 @@ export const MODELS = {
17211
17162
  reasoning: true,
17212
17163
  input: ["text"],
17213
17164
  cost: {
17214
- input: 0.15,
17215
- output: 0.6,
17216
- cacheRead: 0.075,
17165
+ input: 0.014,
17166
+ output: 0.051,
17167
+ cacheRead: 0,
17217
17168
  cacheWrite: 0,
17218
17169
  },
17219
17170
  contextWindow: 131072,
@@ -17245,13 +17196,13 @@ export const MODELS = {
17245
17196
  reasoning: true,
17246
17197
  input: ["text"],
17247
17198
  cost: {
17248
- input: 0.018,
17249
- output: 0.09,
17250
- cacheRead: 0.009,
17199
+ input: 0.03,
17200
+ output: 0.13,
17201
+ cacheRead: 0.03,
17251
17202
  cacheWrite: 0,
17252
17203
  },
17253
17204
  contextWindow: 131072,
17254
- maxTokens: 32768,
17205
+ maxTokens: 117964,
17255
17206
  },
17256
17207
  "openai/gpt-oss-20b:batch": {
17257
17208
  id: "openai/gpt-oss-20b:batch",
@@ -17287,23 +17238,6 @@ export const MODELS = {
17287
17238
  contextWindow: 131072,
17288
17239
  maxTokens: 65536,
17289
17240
  },
17290
- "openai/o1": {
17291
- id: "openai/o1",
17292
- name: "OpenAI: o1",
17293
- api: "openai-completions",
17294
- provider: "openrouter",
17295
- baseUrl: "https://openrouter.ai/api/v1",
17296
- reasoning: true,
17297
- input: ["text", "image"],
17298
- cost: {
17299
- input: 15,
17300
- output: 60,
17301
- cacheRead: 7.5,
17302
- cacheWrite: 0,
17303
- },
17304
- contextWindow: 200000,
17305
- maxTokens: 100000,
17306
- },
17307
17241
  "openai/o3": {
17308
17242
  id: "openai/o3",
17309
17243
  name: "OpenAI: o3",
@@ -17321,40 +17255,6 @@ export const MODELS = {
17321
17255
  contextWindow: 200000,
17322
17256
  maxTokens: 100000,
17323
17257
  },
17324
- "openai/o3-mini": {
17325
- id: "openai/o3-mini",
17326
- name: "OpenAI: o3 Mini",
17327
- api: "openai-completions",
17328
- provider: "openrouter",
17329
- baseUrl: "https://openrouter.ai/api/v1",
17330
- reasoning: true,
17331
- input: ["text"],
17332
- cost: {
17333
- input: 1.1,
17334
- output: 4.4,
17335
- cacheRead: 0.55,
17336
- cacheWrite: 0,
17337
- },
17338
- contextWindow: 200000,
17339
- maxTokens: 100000,
17340
- },
17341
- "openai/o3-mini-high": {
17342
- id: "openai/o3-mini-high",
17343
- name: "OpenAI: o3 Mini High",
17344
- api: "openai-completions",
17345
- provider: "openrouter",
17346
- baseUrl: "https://openrouter.ai/api/v1",
17347
- reasoning: true,
17348
- input: ["text"],
17349
- cost: {
17350
- input: 1.1,
17351
- output: 4.4,
17352
- cacheRead: 0.55,
17353
- cacheWrite: 0,
17354
- },
17355
- contextWindow: 200000,
17356
- maxTokens: 100000,
17357
- },
17358
17258
  "openai/o3-mini:batch": {
17359
17259
  id: "openai/o3-mini:batch",
17360
17260
  name: "OpenAI: o3 Mini (batch)",
@@ -17406,40 +17306,6 @@ export const MODELS = {
17406
17306
  contextWindow: 200000,
17407
17307
  maxTokens: 100000,
17408
17308
  },
17409
- "openai/o4-mini": {
17410
- id: "openai/o4-mini",
17411
- name: "OpenAI: o4 Mini",
17412
- api: "openai-completions",
17413
- provider: "openrouter",
17414
- baseUrl: "https://openrouter.ai/api/v1",
17415
- reasoning: true,
17416
- input: ["text", "image"],
17417
- cost: {
17418
- input: 1.1,
17419
- output: 4.4,
17420
- cacheRead: 0.275,
17421
- cacheWrite: 0,
17422
- },
17423
- contextWindow: 200000,
17424
- maxTokens: 100000,
17425
- },
17426
- "openai/o4-mini-high": {
17427
- id: "openai/o4-mini-high",
17428
- name: "OpenAI: o4 Mini High",
17429
- api: "openai-completions",
17430
- provider: "openrouter",
17431
- baseUrl: "https://openrouter.ai/api/v1",
17432
- reasoning: true,
17433
- input: ["text", "image"],
17434
- cost: {
17435
- input: 1.1,
17436
- output: 4.4,
17437
- cacheRead: 0.275,
17438
- cacheWrite: 0,
17439
- },
17440
- contextWindow: 200000,
17441
- maxTokens: 100000,
17442
- },
17443
17309
  "openai/o4-mini:batch": {
17444
17310
  id: "openai/o4-mini:batch",
17445
17311
  name: "OpenAI: o4 Mini (batch)",
@@ -17489,7 +17355,7 @@ export const MODELS = {
17489
17355
  cacheWrite: 0,
17490
17356
  },
17491
17357
  contextWindow: 2000000,
17492
- maxTokens: 4096,
17358
+ maxTokens: 65536,
17493
17359
  },
17494
17360
  "openrouter/free": {
17495
17361
  id: "openrouter/free",
@@ -17525,107 +17391,73 @@ export const MODELS = {
17525
17391
  contextWindow: 2000000,
17526
17392
  maxTokens: 4096,
17527
17393
  },
17528
- "perceptron/perceptron-mk1.5": {
17529
- id: "perceptron/perceptron-mk1.5",
17530
- name: "Perceptron: Perceptron Mk1.5",
17394
+ "particle-ai/particle-1": {
17395
+ id: "particle-ai/particle-1",
17396
+ name: "Particle AI: Particle-1",
17531
17397
  api: "openai-completions",
17532
17398
  provider: "openrouter",
17533
17399
  baseUrl: "https://openrouter.ai/api/v1",
17534
17400
  reasoning: true,
17535
17401
  input: ["text", "image"],
17536
17402
  cost: {
17537
- input: 0.15,
17538
- output: 1.5,
17539
- cacheRead: 0,
17540
- cacheWrite: 0,
17541
- },
17542
- contextWindow: 36864,
17543
- maxTokens: 8192,
17544
- },
17545
- "poolside/laguna-s-2.1": {
17546
- id: "poolside/laguna-s-2.1",
17547
- name: "Poolside: Laguna S 2.1",
17548
- api: "openai-completions",
17549
- provider: "openrouter",
17550
- baseUrl: "https://openrouter.ai/api/v1",
17551
- reasoning: true,
17552
- input: ["text"],
17553
- cost: {
17554
- input: 0.09,
17555
- output: 0.18,
17556
- cacheRead: 0.009,
17403
+ input: 0.049999999999999996,
17404
+ output: 0.5,
17405
+ cacheRead: 0.003,
17557
17406
  cacheWrite: 0,
17558
17407
  },
17559
17408
  contextWindow: 1048576,
17560
17409
  maxTokens: 131072,
17561
17410
  },
17562
- "poolside/laguna-s-2.1:free": {
17563
- id: "poolside/laguna-s-2.1:free",
17564
- name: "Poolside: Laguna S 2.1 (free)",
17411
+ "perceptron/perceptron-mk1.5": {
17412
+ id: "perceptron/perceptron-mk1.5",
17413
+ name: "Perceptron: Perceptron Mk1.5",
17565
17414
  api: "openai-completions",
17566
17415
  provider: "openrouter",
17567
17416
  baseUrl: "https://openrouter.ai/api/v1",
17568
17417
  reasoning: true,
17569
- input: ["text"],
17418
+ input: ["text", "image"],
17570
17419
  cost: {
17571
- input: 0,
17572
- output: 0,
17420
+ input: 0.15,
17421
+ output: 1.5,
17573
17422
  cacheRead: 0,
17574
17423
  cacheWrite: 0,
17575
17424
  },
17576
- contextWindow: 262144,
17577
- maxTokens: 32768,
17578
- },
17579
- "poolside/laguna-xs-2.1": {
17580
- id: "poolside/laguna-xs-2.1",
17581
- name: "Poolside: Laguna XS 2.1",
17582
- api: "openai-completions",
17583
- provider: "openrouter",
17584
- baseUrl: "https://openrouter.ai/api/v1",
17585
- reasoning: true,
17586
- input: ["text"],
17587
- cost: {
17588
- input: 0.06,
17589
- output: 0.12,
17590
- cacheRead: 0.03,
17591
- cacheWrite: 0,
17592
- },
17593
- contextWindow: 262144,
17594
- maxTokens: 32768,
17425
+ contextWindow: 36864,
17426
+ maxTokens: 8192,
17595
17427
  },
17596
- "poolside/laguna-xs-2.1:free": {
17597
- id: "poolside/laguna-xs-2.1:free",
17598
- name: "Poolside: Laguna XS 2.1 (free)",
17428
+ "prism-ml/ternary-bonsai-2-27b": {
17429
+ id: "prism-ml/ternary-bonsai-2-27b",
17430
+ name: "PrismML: Ternary Bonsai 2 27B",
17599
17431
  api: "openai-completions",
17600
17432
  provider: "openrouter",
17601
17433
  baseUrl: "https://openrouter.ai/api/v1",
17602
17434
  reasoning: true,
17603
- input: ["text"],
17435
+ input: ["text", "image"],
17604
17436
  cost: {
17605
- input: 0,
17606
- output: 0,
17607
- cacheRead: 0,
17437
+ input: 0.075,
17438
+ output: 0.5,
17439
+ cacheRead: 0.0375,
17608
17440
  cacheWrite: 0,
17609
17441
  },
17610
17442
  contextWindow: 262144,
17611
17443
  maxTokens: 32768,
17612
17444
  },
17613
- "prism-ml/ternary-bonsai-2-27b": {
17614
- id: "prism-ml/ternary-bonsai-2-27b",
17615
- name: "PrismML: Ternary Bonsai 2 27B",
17445
+ "prism-ml/ternary-bonsai-2-9b": {
17446
+ id: "prism-ml/ternary-bonsai-2-9b",
17447
+ name: "PrismML: Ternary Bonsai 2 9B",
17616
17448
  api: "openai-completions",
17617
17449
  provider: "openrouter",
17618
17450
  baseUrl: "https://openrouter.ai/api/v1",
17619
17451
  reasoning: true,
17620
17452
  input: ["text", "image"],
17621
17453
  cost: {
17622
- input: 0.075,
17623
- output: 0.5,
17624
- cacheRead: 0.0375,
17454
+ input: 0.08,
17455
+ output: 0.13,
17456
+ cacheRead: 0.04,
17625
17457
  cacheWrite: 0,
17626
17458
  },
17627
17459
  contextWindow: 262144,
17628
- maxTokens: 32768,
17460
+ maxTokens: 65536,
17629
17461
  },
17630
17462
  "qwen/qwen-2.5-72b-instruct": {
17631
17463
  id: "qwen/qwen-2.5-72b-instruct",
@@ -17755,9 +17587,9 @@ export const MODELS = {
17755
17587
  reasoning: false,
17756
17588
  input: ["text"],
17757
17589
  cost: {
17758
- input: 0.09,
17590
+ input: 0.09999999999999999,
17759
17591
  output: 0.3,
17760
- cacheRead: 0,
17592
+ cacheRead: 0.09999999999999999,
17761
17593
  cacheWrite: 0,
17762
17594
  },
17763
17595
  contextWindow: 262144,
@@ -17865,23 +17697,6 @@ export const MODELS = {
17865
17697
  contextWindow: 262144,
17866
17698
  maxTokens: 16384,
17867
17699
  },
17868
- "qwen/qwen3-next-80b-a3b-thinking": {
17869
- id: "qwen/qwen3-next-80b-a3b-thinking",
17870
- name: "Qwen: Qwen3 Next 80B A3B Thinking",
17871
- api: "openai-completions",
17872
- provider: "openrouter",
17873
- baseUrl: "https://openrouter.ai/api/v1",
17874
- reasoning: true,
17875
- input: ["text"],
17876
- cost: {
17877
- input: 0.15,
17878
- output: 1.2,
17879
- cacheRead: 0,
17880
- cacheWrite: 0,
17881
- },
17882
- contextWindow: 262144,
17883
- maxTokens: 235929,
17884
- },
17885
17700
  "qwen/qwen3-vl-235b-a22b-instruct": {
17886
17701
  id: "qwen/qwen3-vl-235b-a22b-instruct",
17887
17702
  name: "Qwen: Qwen3 VL 235B A22B Instruct",
@@ -17976,13 +17791,13 @@ export const MODELS = {
17976
17791
  reasoning: true,
17977
17792
  input: ["text", "image"],
17978
17793
  cost: {
17979
- input: 0.27,
17980
- output: 2.16,
17981
- cacheRead: 0.27,
17794
+ input: 0.26,
17795
+ output: 2.6,
17796
+ cacheRead: 0,
17982
17797
  cacheWrite: 0,
17983
17798
  },
17984
17799
  contextWindow: 262144,
17985
- maxTokens: 65536,
17800
+ maxTokens: 81920,
17986
17801
  },
17987
17802
  "qwen/qwen3.5-35b-a3b": {
17988
17803
  id: "qwen/qwen3.5-35b-a3b",
@@ -18010,13 +17825,13 @@ export const MODELS = {
18010
17825
  reasoning: true,
18011
17826
  input: ["text", "image"],
18012
17827
  cost: {
18013
- input: 0.39,
18014
- output: 2.34,
18015
- cacheRead: 0,
17828
+ input: 0.5,
17829
+ output: 3.5999999999999996,
17830
+ cacheRead: 0.3,
18016
17831
  cacheWrite: 0,
18017
17832
  },
18018
17833
  contextWindow: 262144,
18019
- maxTokens: 65536,
17834
+ maxTokens: 235929,
18020
17835
  },
18021
17836
  "qwen/qwen3.5-9b": {
18022
17837
  id: "qwen/qwen3.5-9b",
@@ -18027,13 +17842,13 @@ export const MODELS = {
18027
17842
  reasoning: true,
18028
17843
  input: ["text", "image"],
18029
17844
  cost: {
18030
- input: 0.08,
18031
- output: 0.13,
18032
- cacheRead: 0.04,
17845
+ input: 0.16999999999999998,
17846
+ output: 0.25,
17847
+ cacheRead: 0,
18033
17848
  cacheWrite: 0,
18034
17849
  },
18035
17850
  contextWindow: 262144,
18036
- maxTokens: 65536,
17851
+ maxTokens: 235929,
18037
17852
  },
18038
17853
  "qwen/qwen3.5-flash-02-23": {
18039
17854
  id: "qwen/qwen3.5-flash-02-23",
@@ -18095,9 +17910,9 @@ export const MODELS = {
18095
17910
  reasoning: true,
18096
17911
  input: ["text", "image"],
18097
17912
  cost: {
18098
- input: 0.25,
18099
- output: 2,
18100
- cacheRead: 0.024999999999999998,
17913
+ input: 0.44999999999999996,
17914
+ output: 2.7,
17915
+ cacheRead: 0,
18101
17916
  cacheWrite: 0,
18102
17917
  },
18103
17918
  contextWindow: 262144,
@@ -18113,8 +17928,8 @@ export const MODELS = {
18113
17928
  input: ["text", "image"],
18114
17929
  cost: {
18115
17930
  input: 0.09999999999999999,
18116
- output: 0.95,
18117
- cacheRead: 0.049999999999999996,
17931
+ output: 0.8999999999999999,
17932
+ cacheRead: 0.024999999999999998,
18118
17933
  cacheWrite: 0,
18119
17934
  },
18120
17935
  contextWindow: 262144,
@@ -18237,7 +18052,7 @@ export const MODELS = {
18237
18052
  cacheWrite: 0,
18238
18053
  },
18239
18054
  contextWindow: 1048576,
18240
- maxTokens: 909000,
18055
+ maxTokens: 131072,
18241
18056
  },
18242
18057
  "qwen/qwen3.8-27b": {
18243
18058
  id: "qwen/qwen3.8-27b",
@@ -18248,13 +18063,13 @@ export const MODELS = {
18248
18063
  reasoning: true,
18249
18064
  input: ["text", "image"],
18250
18065
  cost: {
18251
- input: 0.04,
18252
- output: 1.35,
18253
- cacheRead: 0.018,
18066
+ input: 0.15,
18067
+ output: 1.875,
18068
+ cacheRead: 0.0375,
18254
18069
  cacheWrite: 0,
18255
18070
  },
18256
18071
  contextWindow: 1000000,
18257
- maxTokens: 65536,
18072
+ maxTokens: 235929,
18258
18073
  },
18259
18074
  "qwen/qwen3.8-flash": {
18260
18075
  id: "qwen/qwen3.8-flash",
@@ -18324,6 +18139,23 @@ export const MODELS = {
18324
18139
  contextWindow: 1000000,
18325
18140
  maxTokens: 131072,
18326
18141
  },
18142
+ "recursive/flint-v1.0:free": {
18143
+ id: "recursive/flint-v1.0:free",
18144
+ name: "Recursive: Flint (free)",
18145
+ api: "openai-completions",
18146
+ provider: "openrouter",
18147
+ baseUrl: "https://openrouter.ai/api/v1",
18148
+ reasoning: true,
18149
+ input: ["text"],
18150
+ cost: {
18151
+ input: 0,
18152
+ output: 0,
18153
+ cacheRead: 0,
18154
+ cacheWrite: 0,
18155
+ },
18156
+ contextWindow: 262144,
18157
+ maxTokens: 235929,
18158
+ },
18327
18159
  "reflection/beam-1.0-501b-a23b": {
18328
18160
  id: "reflection/beam-1.0-501b-a23b",
18329
18161
  name: "Reflection: Beam 1.0 501B A23B",
@@ -18333,13 +18165,13 @@ export const MODELS = {
18333
18165
  reasoning: true,
18334
18166
  input: ["text"],
18335
18167
  cost: {
18336
- input: 0.3,
18168
+ input: 0.25,
18337
18169
  output: 1,
18338
- cacheRead: 0.04,
18170
+ cacheRead: 0.049999999999999996,
18339
18171
  cacheWrite: 0,
18340
18172
  },
18341
18173
  contextWindow: 1048576,
18342
- maxTokens: 943718,
18174
+ maxTokens: 131072,
18343
18175
  },
18344
18176
  "rekaai/reka-edge": {
18345
18177
  id: "rekaai/reka-edge",
@@ -18503,9 +18335,9 @@ export const MODELS = {
18503
18335
  reasoning: true,
18504
18336
  input: ["text"],
18505
18337
  cost: {
18506
- input: 0.13199999999999998,
18507
- output: 0.5279999999999999,
18508
- cacheRead: 0.032999999999999995,
18338
+ input: 0.0825,
18339
+ output: 0.33,
18340
+ cacheRead: 0.020625,
18509
18341
  cacheWrite: 0,
18510
18342
  },
18511
18343
  contextWindow: 262144,
@@ -18520,9 +18352,9 @@ export const MODELS = {
18520
18352
  reasoning: true,
18521
18353
  input: ["text"],
18522
18354
  cost: {
18523
- input: 0.834,
18524
- output: 2.501,
18525
- cacheRead: 0.041999999999999996,
18355
+ input: 0.7505999999999999,
18356
+ output: 2.2509,
18357
+ cacheRead: 0.0378,
18526
18358
  cacheWrite: 0,
18527
18359
  },
18528
18360
  contextWindow: 1048576,
@@ -18611,7 +18443,7 @@ export const MODELS = {
18611
18443
  cacheWrite: 0,
18612
18444
  },
18613
18445
  contextWindow: 1000000,
18614
- maxTokens: 4096,
18446
+ maxTokens: 65536,
18615
18447
  },
18616
18448
  "unbiased/pareto-26.10": {
18617
18449
  id: "unbiased/pareto-26.10",
@@ -18664,23 +18496,6 @@ export const MODELS = {
18664
18496
  contextWindow: 524288,
18665
18497
  maxTokens: 131072,
18666
18498
  },
18667
- "upstage/solar-pro-3": {
18668
- id: "upstage/solar-pro-3",
18669
- name: "Upstage: Solar Pro 3",
18670
- api: "openai-completions",
18671
- provider: "openrouter",
18672
- baseUrl: "https://openrouter.ai/api/v1",
18673
- reasoning: true,
18674
- input: ["text"],
18675
- cost: {
18676
- input: 0.15,
18677
- output: 0.6,
18678
- cacheRead: 0.015,
18679
- cacheWrite: 0,
18680
- },
18681
- contextWindow: 131072,
18682
- maxTokens: 117964,
18683
- },
18684
18499
  "upstage/solar-pro4": {
18685
18500
  id: "upstage/solar-pro4",
18686
18501
  name: "Upstage: Solar Pro 4",
@@ -18826,13 +18641,13 @@ export const MODELS = {
18826
18641
  reasoning: true,
18827
18642
  input: ["text", "image"],
18828
18643
  cost: {
18829
- input: 0.119,
18830
- output: 0.238,
18831
- cacheRead: 0.00255,
18644
+ input: 0.39999999999999997,
18645
+ output: 2,
18646
+ cacheRead: 0.08,
18832
18647
  cacheWrite: 0,
18833
18648
  },
18834
18649
  contextWindow: 1050000,
18835
- maxTokens: 945000,
18650
+ maxTokens: 65536,
18836
18651
  },
18837
18652
  "xiaomi/mimo-v2.5-pro": {
18838
18653
  id: "xiaomi/mimo-v2.5-pro",
@@ -18843,13 +18658,13 @@ export const MODELS = {
18843
18658
  reasoning: true,
18844
18659
  input: ["text"],
18845
18660
  cost: {
18846
- input: 0.3045,
18847
- output: 0.609,
18848
- cacheRead: 0.0028,
18661
+ input: 0.48,
18662
+ output: 1.7999999999999998,
18663
+ cacheRead: 0.096,
18849
18664
  cacheWrite: 0,
18850
18665
  },
18851
18666
  contextWindow: 1050000,
18852
- maxTokens: 945000,
18667
+ maxTokens: 235929,
18853
18668
  },
18854
18669
  "xiaomi/mimo-v2.6-flash": {
18855
18670
  id: "xiaomi/mimo-v2.6-flash",
@@ -18979,9 +18794,9 @@ export const MODELS = {
18979
18794
  reasoning: true,
18980
18795
  input: ["text"],
18981
18796
  cost: {
18982
- input: 0.55,
18983
- output: 2.2,
18984
- cacheRead: 0.11,
18797
+ input: 0.5,
18798
+ output: 2,
18799
+ cacheRead: 0.09999999999999999,
18985
18800
  cacheWrite: 0,
18986
18801
  },
18987
18802
  contextWindow: 204800,
@@ -19013,9 +18828,9 @@ export const MODELS = {
19013
18828
  reasoning: true,
19014
18829
  input: ["text"],
19015
18830
  cost: {
19016
- input: 0.54,
19017
- output: 1.9800000000000002,
19018
- cacheRead: 0.099,
18831
+ input: 0.6,
18832
+ output: 2.2,
18833
+ cacheRead: 0.11,
19019
18834
  cacheWrite: 0,
19020
18835
  },
19021
18836
  contextWindow: 204800,
@@ -19098,9 +18913,9 @@ export const MODELS = {
19098
18913
  reasoning: true,
19099
18914
  input: ["text"],
19100
18915
  cost: {
19101
- input: 0.0341,
19102
- output: 7,
19103
- cacheRead: 0.032999999999999995,
18916
+ input: 0.006,
18917
+ output: 6.8,
18918
+ cacheRead: 0.005,
19104
18919
  cacheWrite: 0,
19105
18920
  },
19106
18921
  contextWindow: 1048576,
@@ -19115,9 +18930,9 @@ export const MODELS = {
19115
18930
  reasoning: true,
19116
18931
  input: ["text"],
19117
18932
  cost: {
19118
- input: 0.079,
19119
- output: 1.4,
19120
- cacheRead: 0.078,
18933
+ input: 0.08,
18934
+ output: 3.5999999999999996,
18935
+ cacheRead: 0.07600000000000001,
19121
18936
  cacheWrite: 0,
19122
18937
  },
19123
18938
  contextWindow: 1048576,
@@ -19132,13 +18947,13 @@ export const MODELS = {
19132
18947
  reasoning: true,
19133
18948
  input: ["text", "image"],
19134
18949
  cost: {
19135
- input: 0.15,
19136
- output: 0.5,
19137
- cacheRead: 0.03,
18950
+ input: 0.0285,
18951
+ output: 0.0923,
18952
+ cacheRead: 0.0285,
19138
18953
  cacheWrite: 0,
19139
18954
  },
19140
18955
  contextWindow: 1048576,
19141
- maxTokens: 943717,
18956
+ maxTokens: 131072,
19142
18957
  },
19143
18958
  "z-ai/glm-5.3-flash:batch": {
19144
18959
  id: "z-ai/glm-5.3-flash:batch",
@@ -19303,9 +19118,9 @@ export const MODELS = {
19303
19118
  reasoning: true,
19304
19119
  input: ["text", "image"],
19305
19120
  cost: {
19306
- input: 0.07,
19121
+ input: 0.035,
19307
19122
  output: 0.5,
19308
- cacheRead: 0.008,
19123
+ cacheRead: 0.005,
19309
19124
  cacheWrite: 0,
19310
19125
  },
19311
19126
  contextWindow: 1048576,
@@ -19320,9 +19135,9 @@ export const MODELS = {
19320
19135
  reasoning: true,
19321
19136
  input: ["text"],
19322
19137
  cost: {
19323
- input: 0.22499999999999998,
19138
+ input: 0.1035,
19324
19139
  output: 8,
19325
- cacheRead: 0.22999999999999998,
19140
+ cacheRead: 0.09999999999999999,
19326
19141
  cacheWrite: 0,
19327
19142
  },
19328
19143
  contextWindow: 1048576,
@@ -19339,13 +19154,13 @@ export const MODELS = {
19339
19154
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
19340
19155
  input: ["text"],
19341
19156
  cost: {
19342
- input: 0.020999999999999998,
19343
- output: 0.5279999999999999,
19344
- cacheRead: 0.0056,
19157
+ input: 0.059,
19158
+ output: 0.3,
19159
+ cacheRead: 0.035,
19345
19160
  cacheWrite: 0,
19346
19161
  },
19347
19162
  contextWindow: 1048576,
19348
- maxTokens: 131072,
19163
+ maxTokens: 943718,
19349
19164
  },
19350
19165
  "~google/gemini-flash-latest": {
19351
19166
  id: "~google/gemini-flash-latest",
@@ -19390,9 +19205,9 @@ export const MODELS = {
19390
19205
  reasoning: true,
19391
19206
  input: ["text", "image"],
19392
19207
  cost: {
19393
- input: 0.238,
19394
- output: 16,
19395
- cacheRead: 0.228,
19208
+ input: 0.14950000000000002,
19209
+ output: 7.15,
19210
+ cacheRead: 0.07475000000000001,
19396
19211
  cacheWrite: 0,
19397
19212
  },
19398
19213
  contextWindow: 1048576,
@@ -19475,10 +19290,10 @@ export const MODELS = {
19475
19290
  reasoning: true,
19476
19291
  input: ["text", "image"],
19477
19292
  cost: {
19478
- input: 2,
19479
- output: 12,
19480
- cacheRead: 0.19999999999999998,
19481
- cacheWrite: 2.5,
19293
+ input: 1,
19294
+ output: 5,
19295
+ cacheRead: 0.049999999999999996,
19296
+ cacheWrite: 1.25,
19482
19297
  },
19483
19298
  contextWindow: 1050000,
19484
19299
  maxTokens: 128000,
@@ -19526,13 +19341,13 @@ export const MODELS = {
19526
19341
  reasoning: true,
19527
19342
  input: ["text", "image"],
19528
19343
  cost: {
19529
- input: 0.051691,
19530
- output: 0.5249999999999999,
19531
- cacheRead: 0.00375,
19344
+ input: 0.0285,
19345
+ output: 0.0923,
19346
+ cacheRead: 0.0285,
19532
19347
  cacheWrite: 0,
19533
19348
  },
19534
19349
  contextWindow: 1048576,
19535
- maxTokens: 943718,
19350
+ maxTokens: 131072,
19536
19351
  },
19537
19352
  "~z-ai/glm-latest": {
19538
19353
  id: "~z-ai/glm-latest",
@@ -19543,9 +19358,9 @@ export const MODELS = {
19543
19358
  reasoning: true,
19544
19359
  input: ["text"],
19545
19360
  cost: {
19546
- input: 0.079,
19361
+ input: 0.0699,
19547
19362
  output: 1.4,
19548
- cacheRead: 0.078,
19363
+ cacheRead: 0.0689,
19549
19364
  cacheWrite: 0,
19550
19365
  },
19551
19366
  contextWindow: 1048576,
@@ -19553,25 +19368,6 @@ export const MODELS = {
19553
19368
  },
19554
19369
  },
19555
19370
  "together": {
19556
- "MiniMaxAI/MiniMax-M2.7": {
19557
- id: "MiniMaxAI/MiniMax-M2.7",
19558
- name: "MiniMax-M2.7",
19559
- api: "openai-completions",
19560
- provider: "together",
19561
- baseUrl: "https://api.together.ai/v1",
19562
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
19563
- reasoning: true,
19564
- thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
19565
- input: ["text"],
19566
- cost: {
19567
- input: 0.3,
19568
- output: 1.2,
19569
- cacheRead: 0.06,
19570
- cacheWrite: 0,
19571
- },
19572
- contextWindow: 196608,
19573
- maxTokens: 131072,
19574
- },
19575
19371
  "MiniMaxAI/MiniMax-M3": {
19576
19372
  id: "MiniMaxAI/MiniMax-M3",
19577
19373
  name: "MiniMax-M3",
@@ -19589,25 +19385,7 @@ export const MODELS = {
19589
19385
  cacheWrite: 0,
19590
19386
  },
19591
19387
  contextWindow: 524288,
19592
- maxTokens: 250000,
19593
- },
19594
- "Qwen/Qwen2.5-7B-Instruct-Turbo": {
19595
- id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
19596
- name: "Qwen 2.5 7B Instruct Turbo",
19597
- api: "openai-completions",
19598
- provider: "together",
19599
- baseUrl: "https://api.together.ai/v1",
19600
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
19601
- reasoning: false,
19602
- input: ["text"],
19603
- cost: {
19604
- input: 0.3,
19605
- output: 0.3,
19606
- cacheRead: 0,
19607
- cacheWrite: 0,
19608
- },
19609
- contextWindow: 32768,
19610
- maxTokens: 32768,
19388
+ maxTokens: 524288,
19611
19389
  },
19612
19390
  "Qwen/Qwen3.5-9B": {
19613
19391
  id: "Qwen/Qwen3.5-9B",
@@ -19653,36 +19431,18 @@ export const MODELS = {
19653
19431
  api: "openai-completions",
19654
19432
  provider: "together",
19655
19433
  baseUrl: "https://api.together.ai/v1",
19656
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
19657
- reasoning: false,
19658
- input: ["text"],
19659
- cost: {
19660
- input: 1.25,
19661
- output: 3.75,
19662
- cacheRead: 0.125,
19663
- cacheWrite: 0,
19664
- },
19665
- contextWindow: 1000000,
19666
- maxTokens: 131072,
19667
- },
19668
- "deepseek-ai/DeepSeek-V4-Flash-0731": {
19669
- id: "deepseek-ai/DeepSeek-V4-Flash-0731",
19670
- name: "DeepSeek V4 Flash 0731",
19671
- api: "openai-completions",
19672
- provider: "together",
19673
- baseUrl: "https://api.together.ai/v1",
19674
19434
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19675
19435
  reasoning: true,
19676
19436
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19677
19437
  input: ["text"],
19678
19438
  cost: {
19679
- input: 0.14,
19680
- output: 0.28,
19681
- cacheRead: 0.03,
19439
+ input: 2.5,
19440
+ output: 7.5,
19441
+ cacheRead: 0.5,
19682
19442
  cacheWrite: 0,
19683
19443
  },
19684
- contextWindow: 1048576,
19685
- maxTokens: 384000,
19444
+ contextWindow: 1000000,
19445
+ maxTokens: 131072,
19686
19446
  },
19687
19447
  "deepseek-ai/DeepSeek-V4-Pro-0813": {
19688
19448
  id: "deepseek-ai/DeepSeek-V4-Pro-0813",
@@ -19716,29 +19476,11 @@ export const MODELS = {
19716
19476
  cost: {
19717
19477
  input: 0.3,
19718
19478
  output: 1.2,
19719
- cacheRead: 0.006,
19720
- cacheWrite: 0,
19721
- },
19722
- contextWindow: 1048576,
19723
- maxTokens: 384000,
19724
- },
19725
- "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
19726
- id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
19727
- name: "Llama 3.3 70B",
19728
- api: "openai-completions",
19729
- provider: "together",
19730
- baseUrl: "https://api.together.ai/v1",
19731
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
19732
- reasoning: false,
19733
- input: ["text"],
19734
- cost: {
19735
- input: 1.04,
19736
- output: 1.04,
19737
- cacheRead: 0,
19479
+ cacheRead: 0.006,
19738
19480
  cacheWrite: 0,
19739
19481
  },
19740
- contextWindow: 131072,
19741
- maxTokens: 131072,
19482
+ contextWindow: 1048576,
19483
+ maxTokens: 384000,
19742
19484
  },
19743
19485
  "meta-models/Muse-Spark-Open-816B-A42B": {
19744
19486
  id: "meta-models/Muse-Spark-Open-816B-A42B",
@@ -19797,25 +19539,6 @@ export const MODELS = {
19797
19539
  contextWindow: 262144,
19798
19540
  maxTokens: 262144,
19799
19541
  },
19800
- "nvidia/nemotron-3-ultra-550b-a55b": {
19801
- id: "nvidia/nemotron-3-ultra-550b-a55b",
19802
- name: "Nemotron 3 Ultra 550B A55B",
19803
- api: "openai-completions",
19804
- provider: "together",
19805
- baseUrl: "https://api.together.ai/v1",
19806
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
19807
- reasoning: true,
19808
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
19809
- input: ["text"],
19810
- cost: {
19811
- input: 0.6,
19812
- output: 3.6,
19813
- cacheRead: 0.2,
19814
- cacheWrite: 0,
19815
- },
19816
- contextWindow: 512300,
19817
- maxTokens: 512300,
19818
- },
19819
19542
  "openai/gpt-oss-120b": {
19820
19543
  id: "openai/gpt-oss-120b",
19821
19544
  name: "GPT OSS 120B",
@@ -19908,7 +19631,7 @@ export const MODELS = {
19908
19631
  cacheRead: 0.26,
19909
19632
  cacheWrite: 0,
19910
19633
  },
19911
- contextWindow: 1048576,
19634
+ contextWindow: 1048575,
19912
19635
  maxTokens: 262144,
19913
19636
  },
19914
19637
  "zai-org/GLM-5.3-Flash": {
@@ -20366,9 +20089,9 @@ export const MODELS = {
20366
20089
  reasoning: true,
20367
20090
  input: ["text", "image"],
20368
20091
  cost: {
20369
- input: 0.3,
20370
- output: 2.5,
20371
- cacheRead: 0.075,
20092
+ input: 0.33,
20093
+ output: 2.75,
20094
+ cacheRead: 0.0825,
20372
20095
  cacheWrite: 0,
20373
20096
  },
20374
20097
  contextWindow: 1000000,
@@ -20385,7 +20108,7 @@ export const MODELS = {
20385
20108
  cost: {
20386
20109
  input: 0.06,
20387
20110
  output: 0.24,
20388
- cacheRead: 0,
20111
+ cacheRead: 0.015,
20389
20112
  cacheWrite: 0,
20390
20113
  },
20391
20114
  contextWindow: 300000,
@@ -20402,7 +20125,7 @@ export const MODELS = {
20402
20125
  cost: {
20403
20126
  input: 0.035,
20404
20127
  output: 0.14,
20405
- cacheRead: 0,
20128
+ cacheRead: 0.0087,
20406
20129
  cacheWrite: 0,
20407
20130
  },
20408
20131
  contextWindow: 128000,
@@ -20419,7 +20142,7 @@ export const MODELS = {
20419
20142
  cost: {
20420
20143
  input: 0.7999999999999999,
20421
20144
  output: 3.1999999999999997,
20422
- cacheRead: 0,
20145
+ cacheRead: 0.19999999999999998,
20423
20146
  cacheWrite: 0,
20424
20147
  },
20425
20148
  contextWindow: 300000,
@@ -20963,23 +20686,6 @@ export const MODELS = {
20963
20686
  contextWindow: 1000000,
20964
20687
  maxTokens: 128000,
20965
20688
  },
20966
- "arcee-ai/trinity-large-thinking": {
20967
- id: "arcee-ai/trinity-large-thinking",
20968
- name: "Trinity Large Thinking",
20969
- api: "anthropic-messages",
20970
- provider: "vercel-ai-gateway",
20971
- baseUrl: "https://ai-gateway.vercel.sh",
20972
- reasoning: true,
20973
- input: ["text"],
20974
- cost: {
20975
- input: 0.25,
20976
- output: 0.7999999999999999,
20977
- cacheRead: 0,
20978
- cacheWrite: 0,
20979
- },
20980
- contextWindow: 262100,
20981
- maxTokens: 80000,
20982
- },
20983
20689
  "bytedance/seed-1.6": {
20984
20690
  id: "bytedance/seed-1.6",
20985
20691
  name: "Seed 1.6",
@@ -21227,9 +20933,9 @@ export const MODELS = {
21227
20933
  reasoning: true,
21228
20934
  input: ["text", "image"],
21229
20935
  cost: {
21230
- input: 0.075,
21231
- output: 0.3,
21232
- cacheRead: 0.0015,
20936
+ input: 0.3,
20937
+ output: 1.2,
20938
+ cacheRead: 0.007,
21233
20939
  cacheWrite: 0,
21234
20940
  },
21235
20941
  contextWindow: 1048576,
@@ -21244,13 +20950,13 @@ export const MODELS = {
21244
20950
  reasoning: true,
21245
20951
  input: ["text", "image"],
21246
20952
  cost: {
21247
- input: 0.075,
21248
- output: 0.3,
21249
- cacheRead: 0.0015,
20953
+ input: 0.3,
20954
+ output: 1.2,
20955
+ cacheRead: 0.007,
21250
20956
  cacheWrite: 0,
21251
20957
  },
21252
20958
  contextWindow: 1048576,
21253
- maxTokens: 1048576,
20959
+ maxTokens: 262144,
21254
20960
  },
21255
20961
  "deepseek/deepseek-v4.1-flash-1017-fast": {
21256
20962
  id: "deepseek/deepseek-v4.1-flash-1017-fast",
@@ -21864,6 +21570,23 @@ export const MODELS = {
21864
21570
  contextWindow: 262144,
21865
21571
  maxTokens: 32768,
21866
21572
  },
21573
+ "inclusionai/ling-3.1-flash-1019": {
21574
+ id: "inclusionai/ling-3.1-flash-1019",
21575
+ name: "Ling 3.1 Flash 1019",
21576
+ api: "anthropic-messages",
21577
+ provider: "vercel-ai-gateway",
21578
+ baseUrl: "https://ai-gateway.vercel.sh",
21579
+ reasoning: true,
21580
+ input: ["text"],
21581
+ cost: {
21582
+ input: 0,
21583
+ output: 0,
21584
+ cacheRead: 0,
21585
+ cacheWrite: 0,
21586
+ },
21587
+ contextWindow: 1000000,
21588
+ maxTokens: 262144,
21589
+ },
21867
21590
  "interfaze/interfaze-beta": {
21868
21591
  id: "interfaze/interfaze-beta",
21869
21592
  name: "Interfaze Beta",
@@ -22281,13 +22004,13 @@ export const MODELS = {
22281
22004
  reasoning: true,
22282
22005
  input: ["text", "image"],
22283
22006
  cost: {
22284
- input: 0,
22285
- output: 0,
22286
- cacheRead: 0,
22007
+ input: 0.15,
22008
+ output: 0.6,
22009
+ cacheRead: 0.015,
22287
22010
  cacheWrite: 0,
22288
22011
  },
22289
- contextWindow: 1000000,
22290
- maxTokens: 524288,
22012
+ contextWindow: 1048576,
22013
+ maxTokens: 1048576,
22291
22014
  },
22292
22015
  "mistral/codestral": {
22293
22016
  id: "mistral/codestral",
@@ -22383,12 +22106,12 @@ export const MODELS = {
22383
22106
  reasoning: true,
22384
22107
  input: ["text", "image"],
22385
22108
  cost: {
22386
- input: 1.3599999999999999,
22387
- output: 4.18,
22388
- cacheRead: 0.14,
22109
+ input: 0.7,
22110
+ output: 2.0999999999999996,
22111
+ cacheRead: 0.07,
22389
22112
  cacheWrite: 0,
22390
22113
  },
22391
- contextWindow: 524288,
22114
+ contextWindow: 1048576,
22392
22115
  maxTokens: 262144,
22393
22116
  },
22394
22117
  "mistral/mistral-medium-3.5": {
@@ -22578,6 +22301,40 @@ export const MODELS = {
22578
22301
  contextWindow: 1000000,
22579
22302
  maxTokens: 131072,
22580
22303
  },
22304
+ "moonshotai/kimi-k3.1-pro": {
22305
+ id: "moonshotai/kimi-k3.1-pro",
22306
+ name: "Kimi K3.1 Pro",
22307
+ api: "anthropic-messages",
22308
+ provider: "vercel-ai-gateway",
22309
+ baseUrl: "https://ai-gateway.vercel.sh",
22310
+ reasoning: true,
22311
+ input: ["text", "image"],
22312
+ cost: {
22313
+ input: 2,
22314
+ output: 10,
22315
+ cacheRead: 0.19999999999999998,
22316
+ cacheWrite: 2,
22317
+ },
22318
+ contextWindow: 1048576,
22319
+ maxTokens: 1048576,
22320
+ },
22321
+ "moonshotai/kimi-k3.1-pro-highspeed": {
22322
+ id: "moonshotai/kimi-k3.1-pro-highspeed",
22323
+ name: "Kimi K3.1 Pro Highspeed",
22324
+ api: "anthropic-messages",
22325
+ provider: "vercel-ai-gateway",
22326
+ baseUrl: "https://ai-gateway.vercel.sh",
22327
+ reasoning: true,
22328
+ input: ["text", "image"],
22329
+ cost: {
22330
+ input: 4,
22331
+ output: 20,
22332
+ cacheRead: 0.19999999999999998,
22333
+ cacheWrite: 4,
22334
+ },
22335
+ contextWindow: 1048576,
22336
+ maxTokens: 1048576,
22337
+ },
22581
22338
  "nvidia/nemotron-3-nano-30b-a3b": {
22582
22339
  id: "nvidia/nemotron-3-nano-30b-a3b",
22583
22340
  name: "Nemotron 3 Nano 30B A3B",
@@ -22714,23 +22471,6 @@ export const MODELS = {
22714
22471
  contextWindow: 131072,
22715
22472
  maxTokens: 131072,
22716
22473
  },
22717
- "openai/gpt-3.5-turbo": {
22718
- id: "openai/gpt-3.5-turbo",
22719
- name: "GPT-3.5 Turbo",
22720
- api: "anthropic-messages",
22721
- provider: "vercel-ai-gateway",
22722
- baseUrl: "https://ai-gateway.vercel.sh",
22723
- reasoning: false,
22724
- input: ["text"],
22725
- cost: {
22726
- input: 0.5,
22727
- output: 1.5,
22728
- cacheRead: 0,
22729
- cacheWrite: 0,
22730
- },
22731
- contextWindow: 16385,
22732
- maxTokens: 4096,
22733
- },
22734
22474
  "openai/gpt-4.1": {
22735
22475
  id: "openai/gpt-4.1",
22736
22476
  name: "GPT-4.1",
@@ -22844,41 +22584,7 @@ export const MODELS = {
22844
22584
  cost: {
22845
22585
  input: 0.09999999999999999,
22846
22586
  output: 0.39999999999999997,
22847
- cacheRead: 0.024999999999999998,
22848
- cacheWrite: 0,
22849
- },
22850
- contextWindow: 1047576,
22851
- maxTokens: 32768,
22852
- },
22853
- "openai/gpt-4.1-nano-batch": {
22854
- id: "openai/gpt-4.1-nano-batch",
22855
- name: "GPT-4.1 nano (Batch)",
22856
- api: "anthropic-messages",
22857
- provider: "vercel-ai-gateway",
22858
- baseUrl: "https://ai-gateway.vercel.sh",
22859
- reasoning: false,
22860
- input: ["text", "image"],
22861
- cost: {
22862
- input: 0.049999999999999996,
22863
- output: 0.19999999999999998,
22864
- cacheRead: 0.012499999999999999,
22865
- cacheWrite: 0,
22866
- },
22867
- contextWindow: 1047576,
22868
- maxTokens: 32768,
22869
- },
22870
- "openai/gpt-4.1-nano-fast": {
22871
- id: "openai/gpt-4.1-nano-fast",
22872
- name: "GPT-4.1 nano (Fast)",
22873
- api: "anthropic-messages",
22874
- provider: "vercel-ai-gateway",
22875
- baseUrl: "https://ai-gateway.vercel.sh",
22876
- reasoning: false,
22877
- input: ["text", "image"],
22878
- cost: {
22879
- input: 0.19999999999999998,
22880
- output: 0.7999999999999999,
22881
- cacheRead: 0.049999999999999996,
22587
+ cacheRead: 0.03,
22882
22588
  cacheWrite: 0,
22883
22589
  },
22884
22590
  contextWindow: 1047576,
@@ -23993,6 +23699,40 @@ export const MODELS = {
23993
23699
  contextWindow: 1050000,
23994
23700
  maxTokens: 128000,
23995
23701
  },
23702
+ "openai/gpt-6.1-terra": {
23703
+ id: "openai/gpt-6.1-terra",
23704
+ name: "GPT-6.1 Terra",
23705
+ api: "anthropic-messages",
23706
+ provider: "vercel-ai-gateway",
23707
+ baseUrl: "https://ai-gateway.vercel.sh",
23708
+ reasoning: true,
23709
+ input: ["text", "image"],
23710
+ cost: {
23711
+ input: 1,
23712
+ output: 5,
23713
+ cacheRead: 0.049999999999999996,
23714
+ cacheWrite: 1.25,
23715
+ },
23716
+ contextWindow: 1050000,
23717
+ maxTokens: 128000,
23718
+ },
23719
+ "openai/gpt-6.1-terra-fast": {
23720
+ id: "openai/gpt-6.1-terra-fast",
23721
+ name: "GPT-6.1 Terra (Fast)",
23722
+ api: "anthropic-messages",
23723
+ provider: "vercel-ai-gateway",
23724
+ baseUrl: "https://ai-gateway.vercel.sh",
23725
+ reasoning: true,
23726
+ input: ["text", "image"],
23727
+ cost: {
23728
+ input: 2,
23729
+ output: 10,
23730
+ cacheRead: 0.09999999999999999,
23731
+ cacheWrite: 2.5,
23732
+ },
23733
+ contextWindow: 1050000,
23734
+ maxTokens: 128000,
23735
+ },
23996
23736
  "openai/gpt-oss-120b": {
23997
23737
  id: "openai/gpt-oss-120b",
23998
23738
  name: "GPT OSS 120B",
@@ -24163,22 +23903,22 @@ export const MODELS = {
24163
23903
  contextWindow: 200000,
24164
23904
  maxTokens: 100000,
24165
23905
  },
24166
- "openai/o4-mini-fast": {
24167
- id: "openai/o4-mini-fast",
24168
- name: "o4-mini (Fast)",
23906
+ "particle/particle-1": {
23907
+ id: "particle/particle-1",
23908
+ name: "Particle-1",
24169
23909
  api: "anthropic-messages",
24170
23910
  provider: "vercel-ai-gateway",
24171
23911
  baseUrl: "https://ai-gateway.vercel.sh",
24172
23912
  reasoning: true,
24173
23913
  input: ["text", "image"],
24174
23914
  cost: {
24175
- input: 2,
24176
- output: 8,
24177
- cacheRead: 0.5,
23915
+ input: 0.125,
23916
+ output: 0.5,
23917
+ cacheRead: 0.015,
24178
23918
  cacheWrite: 0,
24179
23919
  },
24180
- contextWindow: 200000,
24181
- maxTokens: 100000,
23920
+ contextWindow: 1048576,
23921
+ maxTokens: 131072,
24182
23922
  },
24183
23923
  "poolside/laguna-s-2.1": {
24184
23924
  id: "poolside/laguna-s-2.1",
@@ -24197,23 +23937,6 @@ export const MODELS = {
24197
23937
  contextWindow: 1000000,
24198
23938
  maxTokens: 131072,
24199
23939
  },
24200
- "poolside/laguna-s-2.1-free": {
24201
- id: "poolside/laguna-s-2.1-free",
24202
- name: "Laguna S 2.1 Free",
24203
- api: "anthropic-messages",
24204
- provider: "vercel-ai-gateway",
24205
- baseUrl: "https://ai-gateway.vercel.sh",
24206
- reasoning: true,
24207
- input: ["text"],
24208
- cost: {
24209
- input: 0,
24210
- output: 0,
24211
- cacheRead: 0,
24212
- cacheWrite: 0,
24213
- },
24214
- contextWindow: 256000,
24215
- maxTokens: 32768,
24216
- },
24217
23940
  "quiverai/arrow-2": {
24218
23941
  id: "quiverai/arrow-2",
24219
23942
  name: "Arrow 2",
@@ -24350,40 +24073,6 @@ export const MODELS = {
24350
24073
  contextWindow: 256000,
24351
24074
  maxTokens: 256000,
24352
24075
  },
24353
- "spacexai/grok-4.1-fast-non-reasoning": {
24354
- id: "spacexai/grok-4.1-fast-non-reasoning",
24355
- name: "Grok 4.1 Fast Non-Reasoning",
24356
- api: "anthropic-messages",
24357
- provider: "vercel-ai-gateway",
24358
- baseUrl: "https://ai-gateway.vercel.sh",
24359
- reasoning: false,
24360
- input: ["text", "image"],
24361
- cost: {
24362
- input: 0.19999999999999998,
24363
- output: 0.5,
24364
- cacheRead: 0.049999999999999996,
24365
- cacheWrite: 0,
24366
- },
24367
- contextWindow: 1000000,
24368
- maxTokens: 1000000,
24369
- },
24370
- "spacexai/grok-4.1-fast-reasoning": {
24371
- id: "spacexai/grok-4.1-fast-reasoning",
24372
- name: "Grok 4.1 Fast Reasoning",
24373
- api: "anthropic-messages",
24374
- provider: "vercel-ai-gateway",
24375
- baseUrl: "https://ai-gateway.vercel.sh",
24376
- reasoning: true,
24377
- input: ["text", "image"],
24378
- cost: {
24379
- input: 0.19999999999999998,
24380
- output: 0.5,
24381
- cacheRead: 0.049999999999999996,
24382
- cacheWrite: 0,
24383
- },
24384
- contextWindow: 1000000,
24385
- maxTokens: 1000000,
24386
- },
24387
24076
  "spacexai/grok-4.20-multi-agent": {
24388
24077
  id: "spacexai/grok-4.20-multi-agent",
24389
24078
  name: "Grok 4.20 Multi-Agent",
@@ -24639,6 +24328,23 @@ export const MODELS = {
24639
24328
  contextWindow: 256000,
24640
24329
  maxTokens: 256000,
24641
24330
  },
24331
+ "spacexai/grok-voice-3.0": {
24332
+ id: "spacexai/grok-voice-3.0",
24333
+ name: "Grok Voice 3.0",
24334
+ api: "anthropic-messages",
24335
+ provider: "vercel-ai-gateway",
24336
+ baseUrl: "https://ai-gateway.vercel.sh",
24337
+ reasoning: true,
24338
+ input: ["text"],
24339
+ cost: {
24340
+ input: 0,
24341
+ output: 0,
24342
+ cacheRead: 0,
24343
+ cacheWrite: 0,
24344
+ },
24345
+ contextWindow: 4096,
24346
+ maxTokens: 4096,
24347
+ },
24642
24348
  "stealth/glyph-cluster": {
24643
24349
  id: "stealth/glyph-cluster",
24644
24350
  name: "Glyph Cluster",
@@ -24767,9 +24473,9 @@ export const MODELS = {
24767
24473
  reasoning: true,
24768
24474
  input: ["text", "image"],
24769
24475
  cost: {
24770
- input: 0.14,
24771
- output: 0.28,
24772
- cacheRead: 0.0028,
24476
+ input: 0.119,
24477
+ output: 0.238,
24478
+ cacheRead: 0.0025,
24773
24479
  cacheWrite: 0,
24774
24480
  },
24775
24481
  contextWindow: 1050000,