@caupulican/pi-ai 0.80.45 → 0.80.47

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.
@@ -3875,7 +3875,7 @@ export const MODELS = {
3875
3875
  cacheRead: 0.26,
3876
3876
  cacheWrite: 0,
3877
3877
  },
3878
- contextWindow: 1048576,
3878
+ contextWindow: 1048575,
3879
3879
  maxTokens: 131072,
3880
3880
  },
3881
3881
  "accounts/fireworks/models/gpt-oss-120b": {
@@ -4022,6 +4022,24 @@ export const MODELS = {
4022
4022
  contextWindow: 202800,
4023
4023
  maxTokens: 131072,
4024
4024
  },
4025
+ "accounts/fireworks/routers/glm-5p2-fast": {
4026
+ id: "accounts/fireworks/routers/glm-5p2-fast",
4027
+ name: "GLM 5.2 Fast",
4028
+ api: "anthropic-messages",
4029
+ provider: "fireworks",
4030
+ baseUrl: "https://api.fireworks.ai/inference",
4031
+ compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
4032
+ reasoning: true,
4033
+ input: ["text"],
4034
+ cost: {
4035
+ input: 2.1,
4036
+ output: 6.6,
4037
+ cacheRead: 0.21,
4038
+ cacheWrite: 0,
4039
+ },
4040
+ contextWindow: 1048575,
4041
+ maxTokens: 131072,
4042
+ },
4025
4043
  "accounts/fireworks/routers/kimi-k2p6-fast": {
4026
4044
  id: "accounts/fireworks/routers/kimi-k2p6-fast",
4027
4045
  name: "Kimi K2.6 Fast",
@@ -12581,7 +12599,7 @@ export const MODELS = {
12581
12599
  input: ["text", "image"],
12582
12600
  cost: {
12583
12601
  input: 0.28850000000000003,
12584
- output: 3.17,
12602
+ output: 2.65,
12585
12603
  cacheRead: 0,
12586
12604
  cacheWrite: 0,
12587
12605
  },
@@ -16140,13 +16158,13 @@ export const MODELS = {
16140
16158
  reasoning: true,
16141
16159
  input: ["text"],
16142
16160
  cost: {
16143
- input: 0.35,
16144
- output: 0.75,
16145
- cacheRead: 0.25,
16161
+ input: 0.09999999999999999,
16162
+ output: 0.5,
16163
+ cacheRead: 0,
16146
16164
  cacheWrite: 0,
16147
16165
  },
16148
16166
  contextWindow: 131072,
16149
- maxTokens: 131000,
16167
+ maxTokens: 131072,
16150
16168
  },
16151
16169
  "openai/gpt-oss-20b": {
16152
16170
  id: "openai/gpt-oss-20b",
@@ -16684,13 +16702,13 @@ export const MODELS = {
16684
16702
  reasoning: true,
16685
16703
  input: ["text"],
16686
16704
  cost: {
16687
- input: 2.25,
16688
- output: 2.75,
16689
- cacheRead: 2.25,
16705
+ input: 0.6,
16706
+ output: 2.2,
16707
+ cacheRead: 0.12,
16690
16708
  cacheWrite: 0,
16691
16709
  },
16692
- contextWindow: 131000,
16693
- maxTokens: 40000,
16710
+ contextWindow: 200000,
16711
+ maxTokens: 120000,
16694
16712
  },
16695
16713
  "zai/glm-4.7-flash": {
16696
16714
  id: "zai/glm-4.7-flash",
@@ -16735,8 +16753,8 @@ export const MODELS = {
16735
16753
  reasoning: true,
16736
16754
  input: ["text"],
16737
16755
  cost: {
16738
- input: 1,
16739
- output: 3.1999999999999997,
16756
+ input: 0.95,
16757
+ output: 3.15,
16740
16758
  cacheRead: 0.19999999999999998,
16741
16759
  cacheWrite: 0,
16742
16760
  },
@@ -16769,13 +16787,13 @@ export const MODELS = {
16769
16787
  reasoning: true,
16770
16788
  input: ["text"],
16771
16789
  cost: {
16772
- input: 1.4,
16773
- output: 4.4,
16790
+ input: 1.3,
16791
+ output: 4.300000000000001,
16774
16792
  cacheRead: 0.26,
16775
16793
  cacheWrite: 0,
16776
16794
  },
16777
- contextWindow: 202800,
16778
- maxTokens: 64000,
16795
+ contextWindow: 202000,
16796
+ maxTokens: 202000,
16779
16797
  },
16780
16798
  "zai/glm-5.2": {
16781
16799
  id: "zai/glm-5.2",