@caupulican/pi-ai 0.80.21 → 0.80.22

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.
@@ -2854,30 +2854,13 @@ export const MODELS = {
2854
2854
  reasoning: true,
2855
2855
  input: ["text"],
2856
2856
  cost: {
2857
- input: 0.25,
2858
- output: 0.69,
2857
+ input: 0.35,
2858
+ output: 0.75,
2859
2859
  cacheRead: 0,
2860
2860
  cacheWrite: 0,
2861
2861
  },
2862
2862
  contextWindow: 131072,
2863
- maxTokens: 32768,
2864
- },
2865
- "llama3.1-8b": {
2866
- id: "llama3.1-8b",
2867
- name: "Llama 3.1 8B",
2868
- api: "openai-completions",
2869
- provider: "cerebras",
2870
- baseUrl: "https://api.cerebras.ai/v1",
2871
- reasoning: false,
2872
- input: ["text"],
2873
- cost: {
2874
- input: 0.1,
2875
- output: 0.1,
2876
- cacheRead: 0,
2877
- cacheWrite: 0,
2878
- },
2879
- contextWindow: 32000,
2880
- maxTokens: 8000,
2863
+ maxTokens: 40960,
2881
2864
  },
2882
2865
  "zai-glm-4.7": {
2883
2866
  id: "zai-glm-4.7",
@@ -2885,7 +2868,7 @@ export const MODELS = {
2885
2868
  api: "openai-completions",
2886
2869
  provider: "cerebras",
2887
2870
  baseUrl: "https://api.cerebras.ai/v1",
2888
- reasoning: false,
2871
+ reasoning: true,
2889
2872
  input: ["text"],
2890
2873
  cost: {
2891
2874
  input: 2.25,
@@ -2894,7 +2877,7 @@ export const MODELS = {
2894
2877
  cacheWrite: 0,
2895
2878
  },
2896
2879
  contextWindow: 131072,
2897
- maxTokens: 40000,
2880
+ maxTokens: 40960,
2898
2881
  },
2899
2882
  },
2900
2883
  "cloudflare-ai-gateway": {
@@ -4023,6 +4006,25 @@ export const MODELS = {
4023
4006
  },
4024
4007
  },
4025
4008
  "github-copilot": {
4009
+ "claude-fable-5": {
4010
+ id: "claude-fable-5",
4011
+ name: "Claude Fable 5",
4012
+ api: "openai-completions",
4013
+ provider: "github-copilot",
4014
+ baseUrl: "https://api.individual.githubcopilot.com",
4015
+ 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" },
4016
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
4017
+ reasoning: true,
4018
+ input: ["text", "image"],
4019
+ cost: {
4020
+ input: 10,
4021
+ output: 50,
4022
+ cacheRead: 1,
4023
+ cacheWrite: 12.5,
4024
+ },
4025
+ contextWindow: 1000000,
4026
+ maxTokens: 128000,
4027
+ },
4026
4028
  "claude-haiku-4.5": {
4027
4029
  id: "claude-haiku-4.5",
4028
4030
  name: "Claude Haiku 4.5 (latest)",
@@ -8203,16 +8205,16 @@ export const MODELS = {
8203
8205
  },
8204
8206
  "minimax-m3": {
8205
8207
  id: "minimax-m3",
8206
- name: "MiniMax M3",
8208
+ name: "MiniMax M3 (3x usage)",
8207
8209
  api: "anthropic-messages",
8208
8210
  provider: "opencode-go",
8209
8211
  baseUrl: "https://opencode.ai/zen/go",
8210
8212
  reasoning: true,
8211
8213
  input: ["text", "image"],
8212
8214
  cost: {
8213
- input: 0.3,
8214
- output: 1.2,
8215
- cacheRead: 0.06,
8215
+ input: 0.1,
8216
+ output: 0.4,
8217
+ cacheRead: 0.02,
8216
8218
  cacheWrite: 0,
8217
8219
  },
8218
8220
  contextWindow: 512000,
@@ -8969,13 +8971,13 @@ export const MODELS = {
8969
8971
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
8970
8972
  input: ["text"],
8971
8973
  cost: {
8972
- input: 0.0983,
8973
- output: 0.1966,
8974
- cacheRead: 0.019700000000000002,
8974
+ input: 0.098,
8975
+ output: 0.196,
8976
+ cacheRead: 0.02,
8975
8977
  cacheWrite: 0,
8976
8978
  },
8977
8979
  contextWindow: 1048576,
8978
- maxTokens: 131072,
8980
+ maxTokens: 4096,
8979
8981
  },
8980
8982
  "deepseek/deepseek-v4-pro": {
8981
8983
  id: "deepseek/deepseek-v4-pro",
@@ -9295,12 +9297,12 @@ export const MODELS = {
9295
9297
  input: ["text", "image"],
9296
9298
  cost: {
9297
9299
  input: 0.12,
9298
- output: 0.36,
9300
+ output: 0.35,
9299
9301
  cacheRead: 0.09,
9300
9302
  cacheWrite: 0,
9301
9303
  },
9302
9304
  contextWindow: 262144,
9303
- maxTokens: 8192,
9305
+ maxTokens: 262144,
9304
9306
  },
9305
9307
  "google/gemma-4-31b-it:free": {
9306
9308
  id: "google/gemma-4-31b-it:free",
@@ -9601,9 +9603,9 @@ export const MODELS = {
9601
9603
  reasoning: true,
9602
9604
  input: ["text"],
9603
9605
  cost: {
9604
- input: 0.27,
9605
- output: 1.08,
9606
- cacheRead: 0.054,
9606
+ input: 0.25,
9607
+ output: 1,
9608
+ cacheRead: 0.049999999999999996,
9607
9609
  cacheWrite: 0,
9608
9610
  },
9609
9611
  contextWindow: 204800,
@@ -9993,13 +9995,30 @@ export const MODELS = {
9993
9995
  reasoning: true,
9994
9996
  input: ["text", "image"],
9995
9997
  cost: {
9996
- input: 0.6799999999999999,
9997
- output: 3.41,
9998
- cacheRead: 0.33999999999999997,
9998
+ input: 0.67,
9999
+ output: 3.39,
10000
+ cacheRead: 0.14,
10001
+ cacheWrite: 0,
10002
+ },
10003
+ contextWindow: 262144,
10004
+ maxTokens: 262144,
10005
+ },
10006
+ "moonshotai/kimi-k2.7-code": {
10007
+ id: "moonshotai/kimi-k2.7-code",
10008
+ name: "MoonshotAI: Kimi K2.7 Code",
10009
+ api: "openai-completions",
10010
+ provider: "openrouter",
10011
+ baseUrl: "https://openrouter.ai/api/v1",
10012
+ reasoning: true,
10013
+ input: ["text", "image"],
10014
+ cost: {
10015
+ input: 0.95,
10016
+ output: 4,
10017
+ cacheRead: 0.19,
9999
10018
  cacheWrite: 0,
10000
10019
  },
10001
10020
  contextWindow: 262144,
10002
- maxTokens: 262142,
10021
+ maxTokens: 4096,
10003
10022
  },
10004
10023
  "nex-agi/nex-n2-pro:free": {
10005
10024
  id: "nex-agi/nex-n2-pro:free",
@@ -10171,23 +10190,6 @@ export const MODELS = {
10171
10190
  contextWindow: 128000,
10172
10191
  maxTokens: 128000,
10173
10192
  },
10174
- "nvidia/nemotron-nano-9b-v2": {
10175
- id: "nvidia/nemotron-nano-9b-v2",
10176
- name: "NVIDIA: Nemotron Nano 9B V2",
10177
- api: "openai-completions",
10178
- provider: "openrouter",
10179
- baseUrl: "https://openrouter.ai/api/v1",
10180
- reasoning: true,
10181
- input: ["text"],
10182
- cost: {
10183
- input: 0.04,
10184
- output: 0.16,
10185
- cacheRead: 0,
10186
- cacheWrite: 0,
10187
- },
10188
- contextWindow: 131072,
10189
- maxTokens: 16384,
10190
- },
10191
10193
  "nvidia/nemotron-nano-9b-v2:free": {
10192
10194
  id: "nvidia/nemotron-nano-9b-v2:free",
10193
10195
  name: "NVIDIA: Nemotron Nano 9B V2 (free)",
@@ -11909,13 +11911,13 @@ export const MODELS = {
11909
11911
  reasoning: true,
11910
11912
  input: ["text", "image"],
11911
11913
  cost: {
11912
- input: 0.28900000000000003,
11913
- output: 2.4,
11914
+ input: 0.28700000000000003,
11915
+ output: 3.1,
11914
11916
  cacheRead: 0,
11915
11917
  cacheWrite: 0,
11916
11918
  },
11917
11919
  contextWindow: 262144,
11918
- maxTokens: 131072,
11920
+ maxTokens: 262140,
11919
11921
  },
11920
11922
  "qwen/qwen3.6-35b-a3b": {
11921
11923
  id: "qwen/qwen3.6-35b-a3b",
@@ -11926,13 +11928,13 @@ export const MODELS = {
11926
11928
  reasoning: true,
11927
11929
  input: ["text", "image"],
11928
11930
  cost: {
11929
- input: 0.14,
11931
+ input: 0.15,
11930
11932
  output: 1,
11931
- cacheRead: 0,
11933
+ cacheRead: 0.049999999999999996,
11932
11934
  cacheWrite: 0,
11933
11935
  },
11934
11936
  contextWindow: 262144,
11935
- maxTokens: 262140,
11937
+ maxTokens: 262144,
11936
11938
  },
11937
11939
  "qwen/qwen3.6-flash": {
11938
11940
  id: "qwen/qwen3.6-flash",
@@ -12011,10 +12013,10 @@ export const MODELS = {
12011
12013
  reasoning: true,
12012
12014
  input: ["text", "image"],
12013
12015
  cost: {
12014
- input: 0.39999999999999997,
12015
- output: 1.5999999999999999,
12016
- cacheRead: 0.08,
12017
- cacheWrite: 0.5,
12016
+ input: 0.32,
12017
+ output: 1.28,
12018
+ cacheRead: 0.064,
12019
+ cacheWrite: 0.39999999999999997,
12018
12020
  },
12019
12021
  contextWindow: 1000000,
12020
12022
  maxTokens: 65536,
@@ -12555,13 +12557,13 @@ export const MODELS = {
12555
12557
  reasoning: true,
12556
12558
  input: ["text", "image"],
12557
12559
  cost: {
12558
- input: 0.6799999999999999,
12559
- output: 3.41,
12560
- cacheRead: 0.33999999999999997,
12560
+ input: 0.67,
12561
+ output: 3.39,
12562
+ cacheRead: 0.14,
12561
12563
  cacheWrite: 0,
12562
12564
  },
12563
12565
  contextWindow: 262144,
12564
- maxTokens: 262142,
12566
+ maxTokens: 262144,
12565
12567
  },
12566
12568
  "~openai/gpt-latest": {
12567
12569
  id: "~openai/gpt-latest",
@@ -12599,25 +12601,6 @@ export const MODELS = {
12599
12601
  },
12600
12602
  },
12601
12603
  "together": {
12602
- "MiniMaxAI/MiniMax-M2.5": {
12603
- id: "MiniMaxAI/MiniMax-M2.5",
12604
- name: "MiniMax-M2.5",
12605
- api: "openai-completions",
12606
- provider: "together",
12607
- baseUrl: "https://api.together.ai/v1",
12608
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
12609
- reasoning: true,
12610
- thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
12611
- input: ["text"],
12612
- cost: {
12613
- input: 0.3,
12614
- output: 1.2,
12615
- cacheRead: 0.06,
12616
- cacheWrite: 0,
12617
- },
12618
- contextWindow: 204800,
12619
- maxTokens: 131072,
12620
- },
12621
12604
  "MiniMaxAI/MiniMax-M2.7": {
12622
12605
  id: "MiniMaxAI/MiniMax-M2.7",
12623
12606
  name: "MiniMax-M2.7",
@@ -12637,28 +12620,27 @@ export const MODELS = {
12637
12620
  contextWindow: 202752,
12638
12621
  maxTokens: 131072,
12639
12622
  },
12640
- "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
12641
- id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
12642
- name: "Qwen3 235B A22B Instruct 2507 FP8",
12623
+ "Qwen/Qwen2.5-7B-Instruct-Turbo": {
12624
+ id: "Qwen/Qwen2.5-7B-Instruct-Turbo",
12625
+ name: "Qwen 2.5 7B Instruct Turbo",
12643
12626
  api: "openai-completions",
12644
12627
  provider: "together",
12645
12628
  baseUrl: "https://api.together.ai/v1",
12646
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12647
- reasoning: true,
12648
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12629
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
12630
+ reasoning: false,
12649
12631
  input: ["text"],
12650
12632
  cost: {
12651
- input: 0.2,
12652
- output: 0.6,
12633
+ input: 0.3,
12634
+ output: 0.3,
12653
12635
  cacheRead: 0,
12654
12636
  cacheWrite: 0,
12655
12637
  },
12656
- contextWindow: 262144,
12657
- maxTokens: 262144,
12638
+ contextWindow: 32768,
12639
+ maxTokens: 32768,
12658
12640
  },
12659
- "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
12660
- id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
12661
- name: "Qwen3 Coder 480B A35B Instruct",
12641
+ "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
12642
+ id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
12643
+ name: "Qwen3 235B A22B Instruct 2507 FP8",
12662
12644
  api: "openai-completions",
12663
12645
  provider: "together",
12664
12646
  baseUrl: "https://api.together.ai/v1",
@@ -12666,36 +12648,36 @@ export const MODELS = {
12666
12648
  reasoning: false,
12667
12649
  input: ["text"],
12668
12650
  cost: {
12669
- input: 2,
12670
- output: 2,
12651
+ input: 0.2,
12652
+ output: 0.6,
12671
12653
  cacheRead: 0,
12672
12654
  cacheWrite: 0,
12673
12655
  },
12674
12656
  contextWindow: 262144,
12675
12657
  maxTokens: 262144,
12676
12658
  },
12677
- "Qwen/Qwen3-Coder-Next-FP8": {
12678
- id: "Qwen/Qwen3-Coder-Next-FP8",
12679
- name: "Qwen3 Coder Next FP8",
12659
+ "Qwen/Qwen3.5-397B-A17B": {
12660
+ id: "Qwen/Qwen3.5-397B-A17B",
12661
+ name: "Qwen3.5 397B A17B",
12680
12662
  api: "openai-completions",
12681
12663
  provider: "together",
12682
12664
  baseUrl: "https://api.together.ai/v1",
12683
12665
  compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12684
12666
  reasoning: true,
12685
12667
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12686
- input: ["text"],
12668
+ input: ["text", "image"],
12687
12669
  cost: {
12688
- input: 0.5,
12689
- output: 1.2,
12670
+ input: 0.6,
12671
+ output: 3.6,
12690
12672
  cacheRead: 0,
12691
12673
  cacheWrite: 0,
12692
12674
  },
12693
12675
  contextWindow: 262144,
12694
- maxTokens: 262144,
12676
+ maxTokens: 130000,
12695
12677
  },
12696
- "Qwen/Qwen3.5-397B-A17B": {
12697
- id: "Qwen/Qwen3.5-397B-A17B",
12698
- name: "Qwen3.5 397B A17B",
12678
+ "Qwen/Qwen3.5-9B": {
12679
+ id: "Qwen/Qwen3.5-9B",
12680
+ name: "Qwen3.5 9B",
12699
12681
  api: "openai-completions",
12700
12682
  provider: "together",
12701
12683
  baseUrl: "https://api.together.ai/v1",
@@ -12704,13 +12686,13 @@ export const MODELS = {
12704
12686
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12705
12687
  input: ["text", "image"],
12706
12688
  cost: {
12707
- input: 0.6,
12708
- output: 3.6,
12689
+ input: 0.17,
12690
+ output: 0.25,
12709
12691
  cacheRead: 0,
12710
12692
  cacheWrite: 0,
12711
12693
  },
12712
12694
  contextWindow: 262144,
12713
- maxTokens: 130000,
12695
+ maxTokens: 65536,
12714
12696
  },
12715
12697
  "Qwen/Qwen3.6-Plus": {
12716
12698
  id: "Qwen/Qwen3.6-Plus",
@@ -12737,9 +12719,8 @@ export const MODELS = {
12737
12719
  api: "openai-completions",
12738
12720
  provider: "together",
12739
12721
  baseUrl: "https://api.together.ai/v1",
12740
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12741
- reasoning: true,
12742
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12722
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
12723
+ reasoning: false,
12743
12724
  input: ["text"],
12744
12725
  cost: {
12745
12726
  input: 2.5,
@@ -12750,44 +12731,6 @@ export const MODELS = {
12750
12731
  contextWindow: 1000000,
12751
12732
  maxTokens: 500000,
12752
12733
  },
12753
- "deepseek-ai/DeepSeek-V3": {
12754
- id: "deepseek-ai/DeepSeek-V3",
12755
- name: "DeepSeek-V3",
12756
- api: "openai-completions",
12757
- provider: "together",
12758
- baseUrl: "https://api.together.ai/v1",
12759
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12760
- reasoning: true,
12761
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12762
- input: ["text"],
12763
- cost: {
12764
- input: 1.25,
12765
- output: 1.25,
12766
- cacheRead: 0,
12767
- cacheWrite: 0,
12768
- },
12769
- contextWindow: 131072,
12770
- maxTokens: 131072,
12771
- },
12772
- "deepseek-ai/DeepSeek-V3-1": {
12773
- id: "deepseek-ai/DeepSeek-V3-1",
12774
- name: "DeepSeek V3.1",
12775
- api: "openai-completions",
12776
- provider: "together",
12777
- baseUrl: "https://api.together.ai/v1",
12778
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12779
- reasoning: true,
12780
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12781
- input: ["text"],
12782
- cost: {
12783
- input: 0.6,
12784
- output: 1.7,
12785
- cacheRead: 0,
12786
- cacheWrite: 0,
12787
- },
12788
- contextWindow: 131072,
12789
- maxTokens: 131072,
12790
- },
12791
12734
  "deepseek-ai/DeepSeek-V4-Pro": {
12792
12735
  id: "deepseek-ai/DeepSeek-V4-Pro",
12793
12736
  name: "DeepSeek V4 Pro",
@@ -12799,8 +12742,8 @@ export const MODELS = {
12799
12742
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
12800
12743
  input: ["text"],
12801
12744
  cost: {
12802
- input: 2.1,
12803
- output: 4.4,
12745
+ input: 1.74,
12746
+ output: 3.48,
12804
12747
  cacheRead: 0.2,
12805
12748
  cacheWrite: 0,
12806
12749
  },
@@ -12836,8 +12779,8 @@ export const MODELS = {
12836
12779
  thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12837
12780
  input: ["text", "image"],
12838
12781
  cost: {
12839
- input: 0.2,
12840
- output: 0.5,
12782
+ input: 0.39,
12783
+ output: 0.97,
12841
12784
  cacheRead: 0,
12842
12785
  cacheWrite: 0,
12843
12786
  },
@@ -12862,25 +12805,6 @@ export const MODELS = {
12862
12805
  contextWindow: 131072,
12863
12806
  maxTokens: 131072,
12864
12807
  },
12865
- "moonshotai/Kimi-K2.5": {
12866
- id: "moonshotai/Kimi-K2.5",
12867
- name: "Kimi K2.5",
12868
- api: "openai-completions",
12869
- provider: "together",
12870
- baseUrl: "https://api.together.ai/v1",
12871
- compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12872
- reasoning: true,
12873
- thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12874
- input: ["text", "image"],
12875
- cost: {
12876
- input: 0.5,
12877
- output: 2.8,
12878
- cacheRead: 0,
12879
- cacheWrite: 0,
12880
- },
12881
- contextWindow: 262144,
12882
- maxTokens: 262144,
12883
- },
12884
12808
  "moonshotai/Kimi-K2.6": {
12885
12809
  id: "moonshotai/Kimi-K2.6",
12886
12810
  name: "Kimi K2.6",
@@ -12938,6 +12862,44 @@ export const MODELS = {
12938
12862
  contextWindow: 131072,
12939
12863
  maxTokens: 131072,
12940
12864
  },
12865
+ "openai/gpt-oss-20b": {
12866
+ id: "openai/gpt-oss-20b",
12867
+ name: "GPT OSS 20B",
12868
+ api: "openai-completions",
12869
+ provider: "together",
12870
+ baseUrl: "https://api.together.ai/v1",
12871
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
12872
+ reasoning: true,
12873
+ thinkingLevelMap: { "off": null, "minimal": null },
12874
+ input: ["text"],
12875
+ cost: {
12876
+ input: 0.05,
12877
+ output: 0.2,
12878
+ cacheRead: 0,
12879
+ cacheWrite: 0,
12880
+ },
12881
+ contextWindow: 131072,
12882
+ maxTokens: 131072,
12883
+ },
12884
+ "zai-org/GLM-5": {
12885
+ id: "zai-org/GLM-5",
12886
+ name: "GLM-5",
12887
+ api: "openai-completions",
12888
+ provider: "together",
12889
+ baseUrl: "https://api.together.ai/v1",
12890
+ compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
12891
+ reasoning: true,
12892
+ thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
12893
+ input: ["text"],
12894
+ cost: {
12895
+ input: 1,
12896
+ output: 3.2,
12897
+ cacheRead: 0,
12898
+ cacheWrite: 0,
12899
+ },
12900
+ contextWindow: 202752,
12901
+ maxTokens: 131072,
12902
+ },
12941
12903
  "zai-org/GLM-5.1": {
12942
12904
  id: "zai-org/GLM-5.1",
12943
12905
  name: "GLM-5.1",
@@ -14513,40 +14475,6 @@ export const MODELS = {
14513
14475
  contextWindow: 262114,
14514
14476
  maxTokens: 262114,
14515
14477
  },
14516
- "moonshotai/kimi-k2-thinking-turbo": {
14517
- id: "moonshotai/kimi-k2-thinking-turbo",
14518
- name: "Kimi K2 Thinking Turbo",
14519
- api: "anthropic-messages",
14520
- provider: "vercel-ai-gateway",
14521
- baseUrl: "https://ai-gateway.vercel.sh",
14522
- reasoning: true,
14523
- input: ["text"],
14524
- cost: {
14525
- input: 1.15,
14526
- output: 8,
14527
- cacheRead: 0.15,
14528
- cacheWrite: 0,
14529
- },
14530
- contextWindow: 262114,
14531
- maxTokens: 262114,
14532
- },
14533
- "moonshotai/kimi-k2-turbo": {
14534
- id: "moonshotai/kimi-k2-turbo",
14535
- name: "Kimi K2 Turbo",
14536
- api: "anthropic-messages",
14537
- provider: "vercel-ai-gateway",
14538
- baseUrl: "https://ai-gateway.vercel.sh",
14539
- reasoning: false,
14540
- input: ["text"],
14541
- cost: {
14542
- input: 1.15,
14543
- output: 8,
14544
- cacheRead: 0.15,
14545
- cacheWrite: 0,
14546
- },
14547
- contextWindow: 256000,
14548
- maxTokens: 16384,
14549
- },
14550
14478
  "moonshotai/kimi-k2.5": {
14551
14479
  id: "moonshotai/kimi-k2.5",
14552
14480
  name: "Kimi K2.5",