@dreb/ai 2.55.0 → 2.55.2

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.
@@ -1359,7 +1359,7 @@ export const MODELS = {
1359
1359
  cacheRead: 0.022,
1360
1360
  cacheWrite: 0.275,
1361
1361
  },
1362
- contextWindow: 272000,
1362
+ contextWindow: 1050000,
1363
1363
  maxTokens: 128000,
1364
1364
  },
1365
1365
  "openai.gpt-5.6-sol": {
@@ -1374,9 +1374,9 @@ export const MODELS = {
1374
1374
  input: 5.5,
1375
1375
  output: 33,
1376
1376
  cacheRead: 0.55,
1377
- cacheWrite: 6.88,
1377
+ cacheWrite: 6.875,
1378
1378
  },
1379
- contextWindow: 272000,
1379
+ contextWindow: 1050000,
1380
1380
  maxTokens: 128000,
1381
1381
  },
1382
1382
  "openai.gpt-5.6-terra": {
@@ -1393,7 +1393,7 @@ export const MODELS = {
1393
1393
  cacheRead: 0.22,
1394
1394
  cacheWrite: 2.75,
1395
1395
  },
1396
- contextWindow: 272000,
1396
+ contextWindow: 1050000,
1397
1397
  maxTokens: 128000,
1398
1398
  },
1399
1399
  "openai.gpt-oss-120b": {
@@ -3504,40 +3504,6 @@ export const MODELS = {
3504
3504
  contextWindow: 131072,
3505
3505
  maxTokens: 65536,
3506
3506
  },
3507
- "gemini-2.0-flash": {
3508
- id: "gemini-2.0-flash",
3509
- name: "Gemini 2.0 Flash",
3510
- api: "google-generative-ai",
3511
- provider: "google",
3512
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3513
- reasoning: false,
3514
- input: ["text", "image"],
3515
- cost: {
3516
- input: 0.1,
3517
- output: 0.4,
3518
- cacheRead: 0.025,
3519
- cacheWrite: 0,
3520
- },
3521
- contextWindow: 1048576,
3522
- maxTokens: 8192,
3523
- },
3524
- "gemini-2.0-flash-lite": {
3525
- id: "gemini-2.0-flash-lite",
3526
- name: "Gemini 2.0 Flash-Lite",
3527
- api: "google-generative-ai",
3528
- provider: "google",
3529
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3530
- reasoning: false,
3531
- input: ["text", "image"],
3532
- cost: {
3533
- input: 0.075,
3534
- output: 0.3,
3535
- cacheRead: 0,
3536
- cacheWrite: 0,
3537
- },
3538
- contextWindow: 1048576,
3539
- maxTokens: 8192,
3540
- },
3541
3507
  "gemini-2.5-computer-use-preview-10-2025": {
3542
3508
  id: "gemini-2.5-computer-use-preview-10-2025",
3543
3509
  name: "Gemini 2.5 Computer Use Preview 10-2025",
@@ -3623,23 +3589,6 @@ export const MODELS = {
3623
3589
  contextWindow: 1048576,
3624
3590
  maxTokens: 65536,
3625
3591
  },
3626
- "gemini-3-pro-preview": {
3627
- id: "gemini-3-pro-preview",
3628
- name: "Gemini 3 Pro Preview",
3629
- api: "google-generative-ai",
3630
- provider: "google",
3631
- baseUrl: "https://generativelanguage.googleapis.com/v1beta",
3632
- reasoning: true,
3633
- input: ["text", "image"],
3634
- cost: {
3635
- input: 2,
3636
- output: 12,
3637
- cacheRead: 0.2,
3638
- cacheWrite: 0,
3639
- },
3640
- contextWindow: 1048576,
3641
- maxTokens: 65536,
3642
- },
3643
3592
  "gemini-3.1-flash-lite": {
3644
3593
  id: "gemini-3.1-flash-lite",
3645
3594
  name: "Gemini 3.1 Flash Lite",
@@ -8079,23 +8028,6 @@ export const MODELS = {
8079
8028
  contextWindow: 1000000,
8080
8029
  maxTokens: 128000,
8081
8030
  },
8082
- "north-mini-code-free": {
8083
- id: "north-mini-code-free",
8084
- name: "North Mini Code Free",
8085
- api: "openai-completions",
8086
- provider: "opencode",
8087
- baseUrl: "https://opencode.ai/zen/v1",
8088
- reasoning: true,
8089
- input: ["text"],
8090
- cost: {
8091
- input: 0,
8092
- output: 0,
8093
- cacheRead: 0,
8094
- cacheWrite: 0,
8095
- },
8096
- contextWindow: 256000,
8097
- maxTokens: 64000,
8098
- },
8099
8031
  "qwen3.5-plus": {
8100
8032
  id: "qwen3.5-plus",
8101
8033
  name: "Qwen3.5 Plus",
@@ -9401,13 +9333,13 @@ export const MODELS = {
9401
9333
  reasoning: true,
9402
9334
  input: ["text"],
9403
9335
  cost: {
9404
- input: 0.09,
9336
+ input: 0.08,
9405
9337
  output: 0.18,
9406
- cacheRead: 0.018,
9338
+ cacheRead: 0.016,
9407
9339
  cacheWrite: 0,
9408
9340
  },
9409
9341
  contextWindow: 1048576,
9410
- maxTokens: 65536,
9342
+ maxTokens: 384000,
9411
9343
  },
9412
9344
  "deepseek/deepseek-v4-pro": {
9413
9345
  id: "deepseek/deepseek-v4-pro",
@@ -9418,13 +9350,13 @@ export const MODELS = {
9418
9350
  reasoning: true,
9419
9351
  input: ["text"],
9420
9352
  cost: {
9421
- input: 0.435,
9422
- output: 0.87,
9423
- cacheRead: 0.003625,
9353
+ input: 0.63168,
9354
+ output: 1.26336,
9355
+ cacheRead: 0.053298,
9424
9356
  cacheWrite: 0,
9425
9357
  },
9426
9358
  contextWindow: 1048576,
9427
- maxTokens: 384000,
9359
+ maxTokens: 393216,
9428
9360
  },
9429
9361
  "google/gemini-2.5-flash": {
9430
9362
  id: "google/gemini-2.5-flash",
@@ -9860,13 +9792,13 @@ export const MODELS = {
9860
9792
  reasoning: true,
9861
9793
  input: ["text", "image"],
9862
9794
  cost: {
9863
- input: 0.07,
9864
- output: 0.33999999999999997,
9865
- cacheRead: 0,
9795
+ input: 0.12,
9796
+ output: 0.39999999999999997,
9797
+ cacheRead: 0.049999999999999996,
9866
9798
  cacheWrite: 0,
9867
9799
  },
9868
9800
  contextWindow: 262144,
9869
- maxTokens: 16384,
9801
+ maxTokens: 262144,
9870
9802
  },
9871
9803
  "google/gemma-4-26b-a4b-it:free": {
9872
9804
  id: "google/gemma-4-26b-a4b-it:free",
@@ -10167,12 +10099,12 @@ export const MODELS = {
10167
10099
  input: ["text", "image"],
10168
10100
  cost: {
10169
10101
  input: 0.19999999999999998,
10170
- output: 0.7999999999999999,
10102
+ output: 0.696,
10171
10103
  cacheRead: 0,
10172
10104
  cacheWrite: 0,
10173
10105
  },
10174
10106
  contextWindow: 1048576,
10175
- maxTokens: 16384,
10107
+ maxTokens: 4096,
10176
10108
  },
10177
10109
  "meta-llama/llama-4-scout": {
10178
10110
  id: "meta-llama/llama-4-scout",
@@ -10191,6 +10123,23 @@ export const MODELS = {
10191
10123
  contextWindow: 1310720,
10192
10124
  maxTokens: 16384,
10193
10125
  },
10126
+ "meta/muse-glimmer-30b": {
10127
+ id: "meta/muse-glimmer-30b",
10128
+ name: "Meta: Muse Glimmer 30B",
10129
+ api: "openai-completions",
10130
+ provider: "openrouter",
10131
+ baseUrl: "https://openrouter.ai/api/v1",
10132
+ reasoning: true,
10133
+ input: ["text", "image"],
10134
+ cost: {
10135
+ input: 0.35,
10136
+ output: 1.5,
10137
+ cacheRead: 0.04,
10138
+ cacheWrite: 0,
10139
+ },
10140
+ contextWindow: 131072,
10141
+ maxTokens: 4096,
10142
+ },
10194
10143
  "meta/muse-spark-1.1": {
10195
10144
  id: "meta/muse-spark-1.1",
10196
10145
  name: "Meta: Muse Spark 1.1",
@@ -10302,9 +10251,9 @@ export const MODELS = {
10302
10251
  reasoning: true,
10303
10252
  input: ["text"],
10304
10253
  cost: {
10305
- input: 0.27,
10306
- output: 1.08,
10307
- cacheRead: 0.054,
10254
+ input: 0.3,
10255
+ output: 1.2,
10256
+ cacheRead: 0.06,
10308
10257
  cacheWrite: 0,
10309
10258
  },
10310
10259
  contextWindow: 204800,
@@ -10797,11 +10746,11 @@ export const MODELS = {
10797
10746
  cost: {
10798
10747
  input: 0.049999999999999996,
10799
10748
  output: 0.19999999999999998,
10800
- cacheRead: 0.03,
10749
+ cacheRead: 0.024999999999999998,
10801
10750
  cacheWrite: 0,
10802
10751
  },
10803
10752
  contextWindow: 262144,
10804
- maxTokens: 262144,
10753
+ maxTokens: 228000,
10805
10754
  },
10806
10755
  "nvidia/nemotron-3-nano-30b-a3b:free": {
10807
10756
  id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -10922,6 +10871,23 @@ export const MODELS = {
10922
10871
  contextWindow: 1000000,
10923
10872
  maxTokens: 65536,
10924
10873
  },
10874
+ "nvidia/nemotron-3.5-lightning:free": {
10875
+ id: "nvidia/nemotron-3.5-lightning:free",
10876
+ name: "NVIDIA: Nemotron 3.5 Lightning (free)",
10877
+ api: "openai-completions",
10878
+ provider: "openrouter",
10879
+ baseUrl: "https://openrouter.ai/api/v1",
10880
+ reasoning: true,
10881
+ input: ["text"],
10882
+ cost: {
10883
+ input: 0,
10884
+ output: 0,
10885
+ cacheRead: 0,
10886
+ cacheWrite: 0,
10887
+ },
10888
+ contextWindow: 1000000,
10889
+ maxTokens: 65536,
10890
+ },
10925
10891
  "nvidia/nemotron-nano-12b-v2-vl:free": {
10926
10892
  id: "nvidia/nemotron-nano-12b-v2-vl:free",
10927
10893
  name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
@@ -11583,7 +11549,7 @@ export const MODELS = {
11583
11549
  cacheWrite: 0,
11584
11550
  },
11585
11551
  contextWindow: 128000,
11586
- maxTokens: 16384,
11552
+ maxTokens: 32000,
11587
11553
  },
11588
11554
  "openai/gpt-5.2-codex": {
11589
11555
  id: "openai/gpt-5.2-codex",
@@ -11653,23 +11619,6 @@ export const MODELS = {
11653
11619
  contextWindow: 400000,
11654
11620
  maxTokens: 128000,
11655
11621
  },
11656
- "openai/gpt-5.3-chat": {
11657
- id: "openai/gpt-5.3-chat",
11658
- name: "OpenAI: GPT-5.3 Chat",
11659
- api: "openai-completions",
11660
- provider: "openrouter",
11661
- baseUrl: "https://openrouter.ai/api/v1",
11662
- reasoning: false,
11663
- input: ["text", "image"],
11664
- cost: {
11665
- input: 1.75,
11666
- output: 14,
11667
- cacheRead: 0.175,
11668
- cacheWrite: 0,
11669
- },
11670
- contextWindow: 128000,
11671
- maxTokens: 16384,
11672
- },
11673
11622
  "openai/gpt-5.3-codex": {
11674
11623
  id: "openai/gpt-5.3-codex",
11675
11624
  name: "OpenAI: GPT-5.3-Codex",
@@ -12682,13 +12631,13 @@ export const MODELS = {
12682
12631
  reasoning: true,
12683
12632
  input: ["text"],
12684
12633
  cost: {
12685
- input: 0.22749999999999998,
12686
- output: 0.9099999999999999,
12634
+ input: 0.12,
12635
+ output: 0.24,
12687
12636
  cacheRead: 0,
12688
12637
  cacheWrite: 0,
12689
12638
  },
12690
12639
  contextWindow: 131072,
12691
- maxTokens: 8192,
12640
+ maxTokens: 16384,
12692
12641
  },
12693
12642
  "qwen/qwen3-235b-a22b": {
12694
12643
  id: "qwen/qwen3-235b-a22b",
@@ -12853,12 +12802,12 @@ export const MODELS = {
12853
12802
  input: ["text"],
12854
12803
  cost: {
12855
12804
  input: 0.07,
12856
- output: 0.27,
12805
+ output: 0.28,
12857
12806
  cacheRead: 0,
12858
12807
  cacheWrite: 0,
12859
12808
  },
12860
12809
  contextWindow: 262144,
12861
- maxTokens: 32768,
12810
+ maxTokens: 262144,
12862
12811
  },
12863
12812
  "qwen/qwen3-coder-flash": {
12864
12813
  id: "qwen/qwen3-coder-flash",
@@ -13158,13 +13107,13 @@ export const MODELS = {
13158
13107
  reasoning: true,
13159
13108
  input: ["text", "image"],
13160
13109
  cost: {
13161
- input: 0.39,
13162
- output: 2.34,
13163
- cacheRead: 0,
13110
+ input: 0.5,
13111
+ output: 3.5999999999999996,
13112
+ cacheRead: 0.3,
13164
13113
  cacheWrite: 0,
13165
13114
  },
13166
13115
  contextWindow: 262144,
13167
- maxTokens: 65536,
13116
+ maxTokens: 262144,
13168
13117
  },
13169
13118
  "qwen/qwen3.5-9b": {
13170
13119
  id: "qwen/qwen3.5-9b",
@@ -13260,7 +13209,7 @@ export const MODELS = {
13260
13209
  reasoning: true,
13261
13210
  input: ["text", "image"],
13262
13211
  cost: {
13263
- input: 0.14,
13212
+ input: 0.15,
13264
13213
  output: 1,
13265
13214
  cacheRead: 0.049999999999999996,
13266
13215
  cacheWrite: 0,
@@ -13438,6 +13387,23 @@ export const MODELS = {
13438
13387
  contextWindow: 1000000,
13439
13388
  maxTokens: 128000,
13440
13389
  },
13390
+ "sakana/sakana-namazu": {
13391
+ id: "sakana/sakana-namazu",
13392
+ name: "Sakana: Sakana Namazu",
13393
+ api: "openai-completions",
13394
+ provider: "openrouter",
13395
+ baseUrl: "https://openrouter.ai/api/v1",
13396
+ reasoning: true,
13397
+ input: ["text", "image"],
13398
+ cost: {
13399
+ input: 0.95,
13400
+ output: 4,
13401
+ cacheRead: 0.15,
13402
+ cacheWrite: 0,
13403
+ },
13404
+ contextWindow: 262144,
13405
+ maxTokens: 65536,
13406
+ },
13441
13407
  "sao10k/l3.1-euryale-70b": {
13442
13408
  id: "sao10k/l3.1-euryale-70b",
13443
13409
  name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -13549,13 +13515,13 @@ export const MODELS = {
13549
13515
  reasoning: true,
13550
13516
  input: ["text", "image"],
13551
13517
  cost: {
13552
- input: 1,
13518
+ input: 0.95,
13553
13519
  output: 4.05,
13554
- cacheRead: 0.16999999999999998,
13520
+ cacheRead: 0.16,
13555
13521
  cacheWrite: 0,
13556
13522
  },
13557
13523
  contextWindow: 1048576,
13558
- maxTokens: 4096,
13524
+ maxTokens: 262144,
13559
13525
  },
13560
13526
  "thinkingmachines/inkling-small": {
13561
13527
  id: "thinkingmachines/inkling-small",
@@ -13608,6 +13574,23 @@ export const MODELS = {
13608
13574
  contextWindow: 131072,
13609
13575
  maxTokens: 131072,
13610
13576
  },
13577
+ "upstage/solar-pro4": {
13578
+ id: "upstage/solar-pro4",
13579
+ name: "Upstage: Solar Pro 4",
13580
+ api: "openai-completions",
13581
+ provider: "openrouter",
13582
+ baseUrl: "https://openrouter.ai/api/v1",
13583
+ reasoning: true,
13584
+ input: ["text"],
13585
+ cost: {
13586
+ input: 0.03,
13587
+ output: 0.12,
13588
+ cacheRead: 0.006,
13589
+ cacheWrite: 0,
13590
+ },
13591
+ contextWindow: 524288,
13592
+ maxTokens: 131072,
13593
+ },
13611
13594
  "x-ai/grok-4.20": {
13612
13595
  id: "x-ai/grok-4.20",
13613
13596
  name: "SpaceXAI: Grok 4.20",
@@ -13889,13 +13872,13 @@ export const MODELS = {
13889
13872
  reasoning: true,
13890
13873
  input: ["text"],
13891
13874
  cost: {
13892
- input: 0.5166,
13893
- output: 1.6236,
13894
- cacheRead: 0.09594,
13875
+ input: 0.76,
13876
+ output: 2.42,
13877
+ cacheRead: 0.14,
13895
13878
  cacheWrite: 0,
13896
13879
  },
13897
13880
  contextWindow: 1048576,
13898
- maxTokens: 131072,
13881
+ maxTokens: 262144,
13899
13882
  },
13900
13883
  "z-ai/glm-5.2:batch": {
13901
13884
  id: "z-ai/glm-5.2:batch",
@@ -14008,13 +13991,13 @@ export const MODELS = {
14008
13991
  reasoning: true,
14009
13992
  input: ["text"],
14010
13993
  cost: {
14011
- input: 0.09,
14012
- output: 0.18,
14013
- cacheRead: 0.018,
13994
+ input: 0.0798,
13995
+ output: 0.1596,
13996
+ cacheRead: 0.01596,
14014
13997
  cacheWrite: 0,
14015
13998
  },
14016
13999
  contextWindow: 1048576,
14017
- maxTokens: 65536,
14000
+ maxTokens: 131072,
14018
14001
  },
14019
14002
  "~google/gemini-flash-latest": {
14020
14003
  id: "~google/gemini-flash-latest",
@@ -14059,7 +14042,7 @@ export const MODELS = {
14059
14042
  reasoning: true,
14060
14043
  input: ["text", "image"],
14061
14044
  cost: {
14062
- input: 2.5,
14045
+ input: 2.8,
14063
14046
  output: 14,
14064
14047
  cacheRead: 0.29,
14065
14048
  cacheWrite: 0,
@@ -14800,6 +14783,23 @@ export const MODELS = {
14800
14783
  contextWindow: 1000000,
14801
14784
  maxTokens: 128000,
14802
14785
  },
14786
+ "anthropic/claude-opus-5-fast": {
14787
+ id: "anthropic/claude-opus-5-fast",
14788
+ name: "Claude Opus 5 (Fast)",
14789
+ api: "anthropic-messages",
14790
+ provider: "vercel-ai-gateway",
14791
+ baseUrl: "https://ai-gateway.vercel.sh",
14792
+ reasoning: true,
14793
+ input: ["text", "image"],
14794
+ cost: {
14795
+ input: 10,
14796
+ output: 50,
14797
+ cacheRead: 1,
14798
+ cacheWrite: 12.5,
14799
+ },
14800
+ contextWindow: 1000000,
14801
+ maxTokens: 128000,
14802
+ },
14803
14803
  "anthropic/claude-sonnet-4": {
14804
14804
  id: "anthropic/claude-sonnet-4",
14805
14805
  name: "Claude Sonnet 4",
@@ -15081,9 +15081,9 @@ export const MODELS = {
15081
15081
  reasoning: true,
15082
15082
  input: ["text"],
15083
15083
  cost: {
15084
- input: 0.13,
15085
- output: 0.26,
15086
- cacheRead: 0.028,
15084
+ input: 0.19999999999999998,
15085
+ output: 0.39999999999999997,
15086
+ cacheRead: 0.04,
15087
15087
  cacheWrite: 0,
15088
15088
  },
15089
15089
  contextWindow: 1000000,
@@ -15261,7 +15261,7 @@ export const MODELS = {
15261
15261
  },
15262
15262
  "google/gemma-4-26b-a4b-it": {
15263
15263
  id: "google/gemma-4-26b-a4b-it",
15264
- name: "Gemma 4 26B A4B IT",
15264
+ name: "Google Gemma 4 26B A4B",
15265
15265
  api: "anthropic-messages",
15266
15266
  provider: "vercel-ai-gateway",
15267
15267
  baseUrl: "https://ai-gateway.vercel.sh",
@@ -15531,6 +15531,23 @@ export const MODELS = {
15531
15531
  contextWindow: 128000,
15532
15532
  maxTokens: 8192,
15533
15533
  },
15534
+ "meta/muse-glimmer-30b": {
15535
+ id: "meta/muse-glimmer-30b",
15536
+ name: "Muse Glimmer 30B",
15537
+ api: "anthropic-messages",
15538
+ provider: "vercel-ai-gateway",
15539
+ baseUrl: "https://ai-gateway.vercel.sh",
15540
+ reasoning: true,
15541
+ input: ["text", "image"],
15542
+ cost: {
15543
+ input: 0.35,
15544
+ output: 1.5,
15545
+ cacheRead: 0.04,
15546
+ cacheWrite: 0,
15547
+ },
15548
+ contextWindow: 131072,
15549
+ maxTokens: 131072,
15550
+ },
15534
15551
  "meta/muse-spark-1.1": {
15535
15552
  id: "meta/muse-spark-1.1",
15536
15553
  name: "Muse Spark 1.1",
@@ -16432,23 +16449,6 @@ export const MODELS = {
16432
16449
  contextWindow: 400000,
16433
16450
  maxTokens: 128000,
16434
16451
  },
16435
- "openai/gpt-5.1-instant": {
16436
- id: "openai/gpt-5.1-instant",
16437
- name: "GPT-5.1 Instant",
16438
- api: "anthropic-messages",
16439
- provider: "vercel-ai-gateway",
16440
- baseUrl: "https://ai-gateway.vercel.sh",
16441
- reasoning: false,
16442
- input: ["text", "image"],
16443
- cost: {
16444
- input: 1.25,
16445
- output: 10,
16446
- cacheRead: 0.13,
16447
- cacheWrite: 0,
16448
- },
16449
- contextWindow: 128000,
16450
- maxTokens: 16384,
16451
- },
16452
16452
  "openai/gpt-5.1-thinking": {
16453
16453
  id: "openai/gpt-5.1-thinking",
16454
16454
  name: "GPT 5.1 Thinking",
@@ -16517,23 +16517,6 @@ export const MODELS = {
16517
16517
  contextWindow: 400000,
16518
16518
  maxTokens: 128000,
16519
16519
  },
16520
- "openai/gpt-5.3-chat": {
16521
- id: "openai/gpt-5.3-chat",
16522
- name: "GPT-5.3 Chat",
16523
- api: "anthropic-messages",
16524
- provider: "vercel-ai-gateway",
16525
- baseUrl: "https://ai-gateway.vercel.sh",
16526
- reasoning: false,
16527
- input: ["text", "image"],
16528
- cost: {
16529
- input: 1.75,
16530
- output: 14,
16531
- cacheRead: 0.175,
16532
- cacheWrite: 0,
16533
- },
16534
- contextWindow: 128000,
16535
- maxTokens: 16384,
16536
- },
16537
16520
  "openai/gpt-5.3-codex": {
16538
16521
  id: "openai/gpt-5.3-codex",
16539
16522
  name: "GPT 5.3 Codex",
@@ -16908,6 +16891,23 @@ export const MODELS = {
16908
16891
  contextWindow: 1000000,
16909
16892
  maxTokens: 1000000,
16910
16893
  },
16894
+ "sakana/namazu": {
16895
+ id: "sakana/namazu",
16896
+ name: "Sakana Namazu",
16897
+ api: "anthropic-messages",
16898
+ provider: "vercel-ai-gateway",
16899
+ baseUrl: "https://ai-gateway.vercel.sh",
16900
+ reasoning: true,
16901
+ input: ["text", "image"],
16902
+ cost: {
16903
+ input: 0.95,
16904
+ output: 4,
16905
+ cacheRead: 0.15,
16906
+ cacheWrite: 0,
16907
+ },
16908
+ contextWindow: 256000,
16909
+ maxTokens: 256000,
16910
+ },
16911
16911
  "stepfun/step-3.5-flash": {
16912
16912
  id: "stepfun/step-3.5-flash",
16913
16913
  name: "StepFun 3.5 Flash",