@avadisabelle/ava-pi-ai 0.63.2 → 0.64.0

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.
@@ -1551,23 +1551,6 @@ export const MODELS = {
1551
1551
  contextWindow: 200000,
1552
1552
  maxTokens: 64000,
1553
1553
  },
1554
- "claude-3-7-sonnet-latest": {
1555
- id: "claude-3-7-sonnet-latest",
1556
- name: "Claude Sonnet 3.7 (latest)",
1557
- api: "anthropic-messages",
1558
- provider: "anthropic",
1559
- baseUrl: "https://api.anthropic.com",
1560
- reasoning: true,
1561
- input: ["text", "image"],
1562
- cost: {
1563
- input: 3,
1564
- output: 15,
1565
- cacheRead: 0.3,
1566
- cacheWrite: 3.75,
1567
- },
1568
- contextWindow: 200000,
1569
- maxTokens: 64000,
1570
- },
1571
1554
  "claude-3-haiku-20240307": {
1572
1555
  id: "claude-3-haiku-20240307",
1573
1556
  name: "Claude Haiku 3",
@@ -3494,6 +3477,40 @@ export const MODELS = {
3494
3477
  contextWindow: 131072,
3495
3478
  maxTokens: 8192,
3496
3479
  },
3480
+ "gemma-4-26b": {
3481
+ id: "gemma-4-26b",
3482
+ name: "Gemma 4 26B",
3483
+ api: "google-generative-ai",
3484
+ provider: "google",
3485
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3486
+ reasoning: true,
3487
+ input: ["text", "image"],
3488
+ cost: {
3489
+ input: 0,
3490
+ output: 0,
3491
+ cacheRead: 0,
3492
+ cacheWrite: 0,
3493
+ },
3494
+ contextWindow: 256000,
3495
+ maxTokens: 8192,
3496
+ },
3497
+ "gemma-4-31b": {
3498
+ id: "gemma-4-31b",
3499
+ name: "Gemma 4 31B",
3500
+ api: "google-generative-ai",
3501
+ provider: "google",
3502
+ baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3503
+ reasoning: true,
3504
+ input: ["text", "image"],
3505
+ cost: {
3506
+ input: 0,
3507
+ output: 0,
3508
+ cacheRead: 0,
3509
+ cacheWrite: 0,
3510
+ },
3511
+ contextWindow: 256000,
3512
+ maxTokens: 8192,
3513
+ },
3497
3514
  },
3498
3515
  "google-antigravity": {
3499
3516
  "claude-opus-4-5-thinking": {
@@ -6630,40 +6647,6 @@ export const MODELS = {
6630
6647
  contextWindow: 262144,
6631
6648
  maxTokens: 65536,
6632
6649
  },
6633
- "mimo-v2-omni-free": {
6634
- id: "mimo-v2-omni-free",
6635
- name: "MiMo V2 Omni Free",
6636
- api: "openai-completions",
6637
- provider: "opencode",
6638
- baseUrl: "https://opencode.ai/zen/v1",
6639
- reasoning: true,
6640
- input: ["text", "image"],
6641
- cost: {
6642
- input: 0,
6643
- output: 0,
6644
- cacheRead: 0,
6645
- cacheWrite: 0,
6646
- },
6647
- contextWindow: 262144,
6648
- maxTokens: 64000,
6649
- },
6650
- "mimo-v2-pro-free": {
6651
- id: "mimo-v2-pro-free",
6652
- name: "MiMo V2 Pro Free",
6653
- api: "openai-completions",
6654
- provider: "opencode",
6655
- baseUrl: "https://opencode.ai/zen/v1",
6656
- reasoning: true,
6657
- input: ["text"],
6658
- cost: {
6659
- input: 0,
6660
- output: 0,
6661
- cacheRead: 0,
6662
- cacheWrite: 0,
6663
- },
6664
- contextWindow: 1048576,
6665
- maxTokens: 64000,
6666
- },
6667
6650
  "minimax-m2.5": {
6668
6651
  id: "minimax-m2.5",
6669
6652
  name: "MiniMax M2.5",
@@ -6712,7 +6695,7 @@ export const MODELS = {
6712
6695
  cacheRead: 0,
6713
6696
  cacheWrite: 0,
6714
6697
  },
6715
- contextWindow: 1000000,
6698
+ contextWindow: 204800,
6716
6699
  maxTokens: 128000,
6717
6700
  },
6718
6701
  "qwen3.6-plus-free": {
@@ -6768,12 +6751,46 @@ export const MODELS = {
6768
6751
  contextWindow: 262144,
6769
6752
  maxTokens: 65536,
6770
6753
  },
6754
+ "mimo-v2-omni": {
6755
+ id: "mimo-v2-omni",
6756
+ name: "MiMo V2 Omni",
6757
+ api: "openai-completions",
6758
+ provider: "opencode-go",
6759
+ baseUrl: "https://opencode.ai/zen/go/v1",
6760
+ reasoning: true,
6761
+ input: ["text", "image"],
6762
+ cost: {
6763
+ input: 0.4,
6764
+ output: 2,
6765
+ cacheRead: 0.08,
6766
+ cacheWrite: 0,
6767
+ },
6768
+ contextWindow: 262144,
6769
+ maxTokens: 64000,
6770
+ },
6771
+ "mimo-v2-pro": {
6772
+ id: "mimo-v2-pro",
6773
+ name: "MiMo V2 Pro",
6774
+ api: "openai-completions",
6775
+ provider: "opencode-go",
6776
+ baseUrl: "https://opencode.ai/zen/go/v1",
6777
+ reasoning: true,
6778
+ input: ["text"],
6779
+ cost: {
6780
+ input: 1,
6781
+ output: 3,
6782
+ cacheRead: 0.2,
6783
+ cacheWrite: 0,
6784
+ },
6785
+ contextWindow: 1048576,
6786
+ maxTokens: 64000,
6787
+ },
6771
6788
  "minimax-m2.5": {
6772
6789
  id: "minimax-m2.5",
6773
6790
  name: "MiniMax M2.5",
6774
- api: "anthropic-messages",
6791
+ api: "openai-completions",
6775
6792
  provider: "opencode-go",
6776
- baseUrl: "https://opencode.ai/zen/go",
6793
+ baseUrl: "https://opencode.ai/zen/go/v1",
6777
6794
  reasoning: true,
6778
6795
  input: ["text"],
6779
6796
  cost: {
@@ -6974,23 +6991,6 @@ export const MODELS = {
6974
6991
  contextWindow: 200000,
6975
6992
  maxTokens: 8192,
6976
6993
  },
6977
- "anthropic/claude-3.5-sonnet": {
6978
- id: "anthropic/claude-3.5-sonnet",
6979
- name: "Anthropic: Claude 3.5 Sonnet",
6980
- api: "openai-completions",
6981
- provider: "openrouter",
6982
- baseUrl: "https://openrouter.ai/api/v1",
6983
- reasoning: false,
6984
- input: ["text", "image"],
6985
- cost: {
6986
- input: 6,
6987
- output: 30,
6988
- cacheRead: 0.6,
6989
- cacheWrite: 7.5,
6990
- },
6991
- contextWindow: 200000,
6992
- maxTokens: 8192,
6993
- },
6994
6994
  "anthropic/claude-3.7-sonnet": {
6995
6995
  id: "anthropic/claude-3.7-sonnet",
6996
6996
  name: "Anthropic: Claude 3.7 Sonnet",
@@ -7178,6 +7178,23 @@ export const MODELS = {
7178
7178
  contextWindow: 131000,
7179
7179
  maxTokens: 4096,
7180
7180
  },
7181
+ "arcee-ai/trinity-large-thinking": {
7182
+ id: "arcee-ai/trinity-large-thinking",
7183
+ name: "Arcee AI: Trinity Large Thinking",
7184
+ api: "openai-completions",
7185
+ provider: "openrouter",
7186
+ baseUrl: "https://openrouter.ai/api/v1",
7187
+ reasoning: true,
7188
+ input: ["text"],
7189
+ cost: {
7190
+ input: 0.22,
7191
+ output: 0.85,
7192
+ cacheRead: 0,
7193
+ cacheWrite: 0,
7194
+ },
7195
+ contextWindow: 262144,
7196
+ maxTokens: 262144,
7197
+ },
7181
7198
  "arcee-ai/trinity-mini": {
7182
7199
  id: "arcee-ai/trinity-mini",
7183
7200
  name: "Arcee AI: Trinity Mini",
@@ -7618,7 +7635,7 @@ export const MODELS = {
7618
7635
  cacheWrite: 0.08333333333333334,
7619
7636
  },
7620
7637
  contextWindow: 1048576,
7621
- maxTokens: 65536,
7638
+ maxTokens: 65535,
7622
7639
  },
7623
7640
  "google/gemini-2.5-pro": {
7624
7641
  id: "google/gemini-2.5-pro",
@@ -7739,6 +7756,40 @@ export const MODELS = {
7739
7756
  contextWindow: 1048576,
7740
7757
  maxTokens: 65536,
7741
7758
  },
7759
+ "google/gemma-4-26b-a4b-it": {
7760
+ id: "google/gemma-4-26b-a4b-it",
7761
+ name: "Google: Gemma 4 26B A4B ",
7762
+ api: "openai-completions",
7763
+ provider: "openrouter",
7764
+ baseUrl: "https://openrouter.ai/api/v1",
7765
+ reasoning: true,
7766
+ input: ["text", "image"],
7767
+ cost: {
7768
+ input: 0.13,
7769
+ output: 0.39999999999999997,
7770
+ cacheRead: 0,
7771
+ cacheWrite: 0,
7772
+ },
7773
+ contextWindow: 262144,
7774
+ maxTokens: 262144,
7775
+ },
7776
+ "google/gemma-4-31b-it": {
7777
+ id: "google/gemma-4-31b-it",
7778
+ name: "Google: Gemma 4 31B",
7779
+ api: "openai-completions",
7780
+ provider: "openrouter",
7781
+ baseUrl: "https://openrouter.ai/api/v1",
7782
+ reasoning: true,
7783
+ input: ["text", "image"],
7784
+ cost: {
7785
+ input: 0.14,
7786
+ output: 0.39999999999999997,
7787
+ cacheRead: 0,
7788
+ cacheWrite: 0,
7789
+ },
7790
+ contextWindow: 262144,
7791
+ maxTokens: 131072,
7792
+ },
7742
7793
  "inception/mercury": {
7743
7794
  id: "inception/mercury",
7744
7795
  name: "Inception: Mercury",
@@ -8003,9 +8054,9 @@ export const MODELS = {
8003
8054
  reasoning: true,
8004
8055
  input: ["text"],
8005
8056
  cost: {
8006
- input: 0.16,
8007
- output: 1.1,
8008
- cacheRead: 0.08,
8057
+ input: 0.118,
8058
+ output: 0.9900000000000001,
8059
+ cacheRead: 0.059,
8009
8060
  cacheWrite: 0,
8010
8061
  },
8011
8062
  contextWindow: 196608,
@@ -8300,23 +8351,6 @@ export const MODELS = {
8300
8351
  contextWindow: 32768,
8301
8352
  maxTokens: 4096,
8302
8353
  },
8303
- "mistralai/mistral-small-24b-instruct-2501": {
8304
- id: "mistralai/mistral-small-24b-instruct-2501",
8305
- name: "Mistral: Mistral Small 3",
8306
- api: "openai-completions",
8307
- provider: "openrouter",
8308
- baseUrl: "https://openrouter.ai/api/v1",
8309
- reasoning: false,
8310
- input: ["text"],
8311
- cost: {
8312
- input: 0.049999999999999996,
8313
- output: 0.08,
8314
- cacheRead: 0,
8315
- cacheWrite: 0,
8316
- },
8317
- contextWindow: 32768,
8318
- maxTokens: 16384,
8319
- },
8320
8354
  "mistralai/mistral-small-2603": {
8321
8355
  id: "mistralai/mistral-small-2603",
8322
8356
  name: "Mistral: Mistral Small 4",
@@ -10372,7 +10406,7 @@ export const MODELS = {
10372
10406
  cacheWrite: 0,
10373
10407
  },
10374
10408
  contextWindow: 256000,
10375
- maxTokens: 65536,
10409
+ maxTokens: 32768,
10376
10410
  },
10377
10411
  "qwen/qwen3.5-flash-02-23": {
10378
10412
  id: "qwen/qwen3.5-flash-02-23",
@@ -10408,14 +10442,14 @@ export const MODELS = {
10408
10442
  contextWindow: 1000000,
10409
10443
  maxTokens: 65536,
10410
10444
  },
10411
- "qwen/qwen3.6-plus-preview:free": {
10412
- id: "qwen/qwen3.6-plus-preview:free",
10413
- name: "Qwen: Qwen3.6 Plus Preview (free)",
10445
+ "qwen/qwen3.6-plus:free": {
10446
+ id: "qwen/qwen3.6-plus:free",
10447
+ name: "Qwen: Qwen3.6 Plus (free)",
10414
10448
  api: "openai-completions",
10415
10449
  provider: "openrouter",
10416
10450
  baseUrl: "https://openrouter.ai/api/v1",
10417
10451
  reasoning: true,
10418
- input: ["text"],
10452
+ input: ["text", "image"],
10419
10453
  cost: {
10420
10454
  input: 0,
10421
10455
  output: 0,
@@ -10423,7 +10457,7 @@ export const MODELS = {
10423
10457
  cacheWrite: 0,
10424
10458
  },
10425
10459
  contextWindow: 1000000,
10426
- maxTokens: 32000,
10460
+ maxTokens: 65536,
10427
10461
  },
10428
10462
  "qwen/qwq-32b": {
10429
10463
  id: "qwen/qwq-32b",
@@ -10442,8 +10476,8 @@ export const MODELS = {
10442
10476
  contextWindow: 131072,
10443
10477
  maxTokens: 131072,
10444
10478
  },
10445
- "reka/reka-edge": {
10446
- id: "reka/reka-edge",
10479
+ "rekaai/reka-edge": {
10480
+ id: "rekaai/reka-edge",
10447
10481
  name: "Reka Edge",
10448
10482
  api: "openai-completions",
10449
10483
  provider: "openrouter",
@@ -11003,6 +11037,23 @@ export const MODELS = {
11003
11037
  contextWindow: 202752,
11004
11038
  maxTokens: 131072,
11005
11039
  },
11040
+ "z-ai/glm-5v-turbo": {
11041
+ id: "z-ai/glm-5v-turbo",
11042
+ name: "Z.ai: GLM 5V Turbo",
11043
+ api: "openai-completions",
11044
+ provider: "openrouter",
11045
+ baseUrl: "https://openrouter.ai/api/v1",
11046
+ reasoning: true,
11047
+ input: ["text", "image"],
11048
+ cost: {
11049
+ input: 1.2,
11050
+ output: 4,
11051
+ cacheRead: 0.24,
11052
+ cacheWrite: 0,
11053
+ },
11054
+ contextWindow: 202752,
11055
+ maxTokens: 131072,
11056
+ },
11006
11057
  },
11007
11058
  "vercel-ai-gateway": {
11008
11059
  "alibaba/qwen-3-14b": {
@@ -11024,7 +11075,7 @@ export const MODELS = {
11024
11075
  },
11025
11076
  "alibaba/qwen-3-235b": {
11026
11077
  id: "alibaba/qwen-3-235b",
11027
- name: "Qwen3-235B-A22B",
11078
+ name: "Qwen3 235B A22b Instruct 2507",
11028
11079
  api: "anthropic-messages",
11029
11080
  provider: "vercel-ai-gateway",
11030
11081
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -11218,13 +11269,13 @@ export const MODELS = {
11218
11269
  reasoning: true,
11219
11270
  input: ["text", "image"],
11220
11271
  cost: {
11221
- input: 0.22,
11222
- output: 0.88,
11272
+ input: 0.39999999999999997,
11273
+ output: 4,
11223
11274
  cacheRead: 0,
11224
11275
  cacheWrite: 0,
11225
11276
  },
11226
- contextWindow: 256000,
11227
- maxTokens: 256000,
11277
+ contextWindow: 131072,
11278
+ maxTokens: 32768,
11228
11279
  },
11229
11280
  "alibaba/qwen3.5-flash": {
11230
11281
  id: "alibaba/qwen3.5-flash",
@@ -11260,6 +11311,23 @@ export const MODELS = {
11260
11311
  contextWindow: 1000000,
11261
11312
  maxTokens: 64000,
11262
11313
  },
11314
+ "alibaba/qwen3.6-plus": {
11315
+ id: "alibaba/qwen3.6-plus",
11316
+ name: "Qwen 3.6 Plus",
11317
+ api: "anthropic-messages",
11318
+ provider: "vercel-ai-gateway",
11319
+ baseUrl: "https://ai-gateway.vercel.sh",
11320
+ reasoning: true,
11321
+ input: ["text", "image"],
11322
+ cost: {
11323
+ input: 0.5,
11324
+ output: 3,
11325
+ cacheRead: 0.09999999999999999,
11326
+ cacheWrite: 0.625,
11327
+ },
11328
+ contextWindow: 1000000,
11329
+ maxTokens: 64000,
11330
+ },
11263
11331
  "anthropic/claude-3-haiku": {
11264
11332
  id: "anthropic/claude-3-haiku",
11265
11333
  name: "Claude 3 Haiku",
@@ -11294,40 +11362,6 @@ export const MODELS = {
11294
11362
  contextWindow: 200000,
11295
11363
  maxTokens: 8192,
11296
11364
  },
11297
- "anthropic/claude-3.5-sonnet": {
11298
- id: "anthropic/claude-3.5-sonnet",
11299
- name: "Claude 3.5 Sonnet",
11300
- api: "anthropic-messages",
11301
- provider: "vercel-ai-gateway",
11302
- baseUrl: "https://ai-gateway.vercel.sh",
11303
- reasoning: false,
11304
- input: ["text", "image"],
11305
- cost: {
11306
- input: 3,
11307
- output: 15,
11308
- cacheRead: 0.3,
11309
- cacheWrite: 3.75,
11310
- },
11311
- contextWindow: 200000,
11312
- maxTokens: 8192,
11313
- },
11314
- "anthropic/claude-3.5-sonnet-20240620": {
11315
- id: "anthropic/claude-3.5-sonnet-20240620",
11316
- name: "Claude 3.5 Sonnet (2024-06-20)",
11317
- api: "anthropic-messages",
11318
- provider: "vercel-ai-gateway",
11319
- baseUrl: "https://ai-gateway.vercel.sh",
11320
- reasoning: false,
11321
- input: ["text", "image"],
11322
- cost: {
11323
- input: 3,
11324
- output: 15,
11325
- cacheRead: 0.3,
11326
- cacheWrite: 3.75,
11327
- },
11328
- contextWindow: 200000,
11329
- maxTokens: 8192,
11330
- },
11331
11365
  "anthropic/claude-3.7-sonnet": {
11332
11366
  id: "anthropic/claude-3.7-sonnet",
11333
11367
  name: "Claude 3.7 Sonnet",
@@ -11498,6 +11532,23 @@ export const MODELS = {
11498
11532
  contextWindow: 131000,
11499
11533
  maxTokens: 131000,
11500
11534
  },
11535
+ "arcee-ai/trinity-large-thinking": {
11536
+ id: "arcee-ai/trinity-large-thinking",
11537
+ name: "Trinity Large Thinking",
11538
+ api: "anthropic-messages",
11539
+ provider: "vercel-ai-gateway",
11540
+ baseUrl: "https://ai-gateway.vercel.sh",
11541
+ reasoning: true,
11542
+ input: ["text"],
11543
+ cost: {
11544
+ input: 0.25,
11545
+ output: 0.8999999999999999,
11546
+ cacheRead: 0,
11547
+ cacheWrite: 0,
11548
+ },
11549
+ contextWindow: 262100,
11550
+ maxTokens: 80000,
11551
+ },
11501
11552
  "bytedance/seed-1.6": {
11502
11553
  id: "bytedance/seed-1.6",
11503
11554
  name: "Seed 1.6",
@@ -11787,6 +11838,40 @@ export const MODELS = {
11787
11838
  contextWindow: 1000000,
11788
11839
  maxTokens: 64000,
11789
11840
  },
11841
+ "google/gemma-4-26b-a4b-it": {
11842
+ id: "google/gemma-4-26b-a4b-it",
11843
+ name: "Gemma 4 26B A4B IT",
11844
+ api: "anthropic-messages",
11845
+ provider: "vercel-ai-gateway",
11846
+ baseUrl: "https://ai-gateway.vercel.sh",
11847
+ reasoning: false,
11848
+ input: ["text", "image"],
11849
+ cost: {
11850
+ input: 0.13,
11851
+ output: 0.39999999999999997,
11852
+ cacheRead: 0,
11853
+ cacheWrite: 0,
11854
+ },
11855
+ contextWindow: 262144,
11856
+ maxTokens: 131072,
11857
+ },
11858
+ "google/gemma-4-31b-it": {
11859
+ id: "google/gemma-4-31b-it",
11860
+ name: "Gemma 4 31B IT",
11861
+ api: "anthropic-messages",
11862
+ provider: "vercel-ai-gateway",
11863
+ baseUrl: "https://ai-gateway.vercel.sh",
11864
+ reasoning: false,
11865
+ input: ["text", "image"],
11866
+ cost: {
11867
+ input: 0.14,
11868
+ output: 0.39999999999999997,
11869
+ cacheRead: 0,
11870
+ cacheWrite: 0,
11871
+ },
11872
+ contextWindow: 262144,
11873
+ maxTokens: 131072,
11874
+ },
11790
11875
  "inception/mercury-2": {
11791
11876
  id: "inception/mercury-2",
11792
11877
  name: "Mercury 2",
@@ -11855,23 +11940,6 @@ export const MODELS = {
11855
11940
  contextWindow: 128000,
11856
11941
  maxTokens: 8192,
11857
11942
  },
11858
- "meituan/longcat-flash-thinking": {
11859
- id: "meituan/longcat-flash-thinking",
11860
- name: "LongCat Flash Thinking",
11861
- api: "anthropic-messages",
11862
- provider: "vercel-ai-gateway",
11863
- baseUrl: "https://ai-gateway.vercel.sh",
11864
- reasoning: true,
11865
- input: ["text"],
11866
- cost: {
11867
- input: 0.15,
11868
- output: 1.5,
11869
- cacheRead: 0,
11870
- cacheWrite: 0,
11871
- },
11872
- contextWindow: 128000,
11873
- maxTokens: 8192,
11874
- },
11875
11943
  "meta/llama-3.1-70b": {
11876
11944
  id: "meta/llama-3.1-70b",
11877
11945
  name: "Llama 3.1 70B Instruct",
@@ -11966,12 +12034,12 @@ export const MODELS = {
11966
12034
  reasoning: false,
11967
12035
  input: ["text", "image"],
11968
12036
  cost: {
11969
- input: 0.35,
11970
- output: 1.15,
12037
+ input: 0.24,
12038
+ output: 0.9700000000000001,
11971
12039
  cacheRead: 0,
11972
12040
  cacheWrite: 0,
11973
12041
  },
11974
- contextWindow: 524288,
12042
+ contextWindow: 128000,
11975
12043
  maxTokens: 8192,
11976
12044
  },
11977
12045
  "meta/llama-4-scout": {
@@ -12282,20 +12350,20 @@ export const MODELS = {
12282
12350
  },
12283
12351
  "moonshotai/kimi-k2": {
12284
12352
  id: "moonshotai/kimi-k2",
12285
- name: "Kimi K2",
12353
+ name: "Kimi K2 Instruct",
12286
12354
  api: "anthropic-messages",
12287
12355
  provider: "vercel-ai-gateway",
12288
12356
  baseUrl: "https://ai-gateway.vercel.sh",
12289
12357
  reasoning: false,
12290
12358
  input: ["text"],
12291
12359
  cost: {
12292
- input: 0.6,
12293
- output: 2.5,
12294
- cacheRead: 0.15,
12360
+ input: 0.5700000000000001,
12361
+ output: 2.3,
12362
+ cacheRead: 0,
12295
12363
  cacheWrite: 0,
12296
12364
  },
12297
12365
  contextWindow: 131072,
12298
- maxTokens: 16384,
12366
+ maxTokens: 131072,
12299
12367
  },
12300
12368
  "moonshotai/kimi-k2-0905": {
12301
12369
  id: "moonshotai/kimi-k2-0905",
@@ -12308,11 +12376,11 @@ export const MODELS = {
12308
12376
  cost: {
12309
12377
  input: 0.6,
12310
12378
  output: 2.5,
12311
- cacheRead: 0.15,
12379
+ cacheRead: 0.3,
12312
12380
  cacheWrite: 0,
12313
12381
  },
12314
12382
  contextWindow: 256000,
12315
- maxTokens: 16384,
12383
+ maxTokens: 128000,
12316
12384
  },
12317
12385
  "moonshotai/kimi-k2-thinking": {
12318
12386
  id: "moonshotai/kimi-k2-thinking",
@@ -12901,12 +12969,12 @@ export const MODELS = {
12901
12969
  reasoning: true,
12902
12970
  input: ["text"],
12903
12971
  cost: {
12904
- input: 0.07,
12905
- output: 0.3,
12972
+ input: 0.049999999999999996,
12973
+ output: 0.19999999999999998,
12906
12974
  cacheRead: 0,
12907
12975
  cacheWrite: 0,
12908
12976
  },
12909
- contextWindow: 128000,
12977
+ contextWindow: 131072,
12910
12978
  maxTokens: 8192,
12911
12979
  },
12912
12980
  "openai/gpt-oss-safeguard-20b": {
@@ -13589,6 +13657,23 @@ export const MODELS = {
13589
13657
  contextWindow: 202800,
13590
13658
  maxTokens: 131100,
13591
13659
  },
13660
+ "zai/glm-5v-turbo": {
13661
+ id: "zai/glm-5v-turbo",
13662
+ name: "GLM 5V Turbo",
13663
+ api: "anthropic-messages",
13664
+ provider: "vercel-ai-gateway",
13665
+ baseUrl: "https://ai-gateway.vercel.sh",
13666
+ reasoning: true,
13667
+ input: ["text", "image"],
13668
+ cost: {
13669
+ input: 1.2,
13670
+ output: 4,
13671
+ cacheRead: 0.24,
13672
+ cacheWrite: 0,
13673
+ },
13674
+ contextWindow: 200000,
13675
+ maxTokens: 128000,
13676
+ },
13592
13677
  },
13593
13678
  "xai": {
13594
13679
  "grok-2": {
@@ -14199,6 +14284,24 @@ export const MODELS = {
14199
14284
  contextWindow: 200000,
14200
14285
  maxTokens: 131072,
14201
14286
  },
14287
+ "glm-5v-turbo": {
14288
+ id: "glm-5v-turbo",
14289
+ name: "glm-5v-turbo",
14290
+ api: "openai-completions",
14291
+ provider: "zai",
14292
+ baseUrl: "https://api.z.ai/api/coding/paas/v4",
14293
+ compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
14294
+ reasoning: true,
14295
+ input: ["text", "image"],
14296
+ cost: {
14297
+ input: 1.2,
14298
+ output: 4,
14299
+ cacheRead: 0.24,
14300
+ cacheWrite: 0,
14301
+ },
14302
+ contextWindow: 200000,
14303
+ maxTokens: 131072,
14304
+ },
14202
14305
  },
14203
14306
  };
14204
14307
  //# sourceMappingURL=models.generated.js.map