pi-hypercharm-provider 1.3.10 → 1.3.12

package/README.md

@@ -15,7 +15,7 @@ _Hyperoptimized coding models — DeepSeek, GLM, Kimi, Qwen, MiniMax, Gemma, GPT
 
 ## Features
 
-- **31+ AI Models** including DeepSeek V4 Flash/Pro, GLM 5/5.1, Kimi K2.5/K2.6, Qwen3.6/3.7, MiniMax M2.7, Gemma 4, GPT-OSS, and Llama
+- **32+ AI Models** including DeepSeek V4 Flash/Pro, GLM 5/5.1, Kimi K2.5/K2.6, Qwen3.6/3.7, MiniMax M2.7, Gemma 4, GPT-OSS, and Llama
 - **DeepSeek Native Thinking** — Uses the `deepseek` thinking format for Charm Hyper requests, with native `reasoning_effort` on models that publish levels
 - **OpenAI-compatible API** via Charm Hyper's `/v1/chat/completions` endpoint
 - **OAuth Device Flow** — sign in with `/login` under the `hypercharm` provider (independent of the official provider's `hyper` registration)
@@ -31,20 +31,21 @@ _Hyperoptimized coding models — DeepSeek, GLM, Kimi, Qwen, MiniMax, Gemma, GPT
 | DeepSeek V4 Flash 0731 | Text | 1.0M | 384K | $0.44 | $1.32 |
 | DeepSeek V4 Pro | Text | 1.0M | 384K | $2.40 | $4.80 |
 | DeepSeek V4 Pro 0813 | Text | 1.0M | 262K | $1.44 | $4.31 |
-| Gemma 4 26B A4B | Text | 256K | 26K | $0.12 | $0.42 |
+| Gemma 4 26B A4B | Text | 256K | 26K | $0.11 | $0.37 |
 | GLM 5.3 | Text | 1.0M | 262K | $1.52 | $4.79 |
 | GLM 5.3 Flash | Text + Image | 1.0M | 131K | $0.16 | $0.54 |
-| GLM-5 | Text | 203K | 20K | $0.91 | $2.93 |
-| GLM-5.1 | Text | 203K | 3K | $1.33 | $4.31 |
+| GLM-5 | Text | 203K | 20K | $0.93 | $2.88 |
+| GLM-5.1 | Text | 203K | 3K | $1.29 | $4.22 |
 | GLM-5.2 | Text | 1.0M | 33K | $1.52 | $4.79 |
-| gpt-oss-120b | Text | 128K | 13K | $0.19 | $0.63 |
-| Kimi K2.5 | Text | 262K | 26K | $0.55 | $2.88 |
+| gpt-oss-120b | Text | 128K | 13K | $0.19 | $0.70 |
+| Kimi K2 Thinking | Text | 262K | 26K | $0.60 | $2.50 |
+| Kimi K2.5 | Text | 262K | 26K | $0.53 | $2.79 |
 | Kimi K2.6 | Text + Image | 262K | 26K | $1.03 | $4.36 |
 | Kimi K2.7 Code | Text + Image | 262K | 16K | $1.03 | $4.36 |
 | Kimi K3 | Text + Image | 1.0M | 16K | $3.27 | $16.33 |
 | Llama 3.3 70B Instruct | Text | 128K | 13K | $0.61 | $1.04 |
 | Llama 4 Maverick 17B 128E Instruct FP8 | Text | 430K | 43K | $0.27 | $0.90 |
-| MiniMax M2.7 | Text | 262K | 7K | $0.40 | $1.50 |
+| MiniMax M2.7 | Text | 262K | 7K | $0.42 | $1.59 |
 | MiniMax M3 | Text + Image | 512K | 512K | $0.33 | $1.31 |
 | Qwen3 Coder 480B A35B Instruct INT4 Mixed AR | Text | 106K | 11K | $0.45 | $2.15 |
 | Qwen3 Next 80B A3B Instruct | Text | 262K | 26K | $0.12 | $1.14 |

package/models.json

@@ -140,10 +140,10 @@
       "text"
     ],
     "cost": {
-      "input": 0.12,
-      "output": 0.42,
+      "input": 0.106,
+      "output": 0.368,
       "cacheRead": 0,
-      "cacheWrite": 0.06
+      "cacheWrite": 0.053
     },
     "contextWindow": 256000,
     "maxTokens": 25600,
@@ -234,10 +234,10 @@
       "text"
     ],
     "cost": {
-      "input": 0.91,
-      "output": 2.934,
+      "input": 0.93,
+      "output": 2.878,
       "cacheRead": 0,
-      "cacheWrite": 0.455
+      "cacheWrite": 0.465
     },
     "contextWindow": 202752,
     "maxTokens": 20275,
@@ -265,10 +265,10 @@
       "text"
     ],
     "cost": {
-      "input": 1.332,
-      "output": 4.312,
+      "input": 1.29,
+      "output": 4.22,
       "cacheRead": 0,
-      "cacheWrite": 0.666
+      "cacheWrite": 0.645
     },
     "contextWindow": 202750,
     "maxTokens": 3276,
@@ -327,10 +327,10 @@
       "text"
     ],
     "cost": {
-      "input": 0.19,
-      "output": 0.63,
+      "input": 0.188,
+      "output": 0.7,
       "cacheRead": 0,
-      "cacheWrite": 0.095
+      "cacheWrite": 0.094
     },
     "contextWindow": 128072,
     "maxTokens": 13107,
@@ -341,6 +341,37 @@
       "maxTokensField": "max_tokens"
     }
   },
+  {
+    "id": "kimi-k2-thinking",
+    "name": "Kimi K2 Thinking",
+    "reasoning": true,
+    "thinkingLevelMap": {
+      "off": "off",
+      "minimal": null,
+      "low": null,
+      "medium": null,
+      "high": null,
+      "xhigh": null,
+      "max": "max"
+    },
+    "input": [
+      "text"
+    ],
+    "cost": {
+      "input": 0.6,
+      "output": 2.5,
+      "cacheRead": 0,
+      "cacheWrite": 0.3
+    },
+    "contextWindow": 262144,
+    "maxTokens": 26214,
+    "compat": {
+      "supportsStore": false,
+      "supportsReasoningEffort": false,
+      "thinkingFormat": "deepseek",
+      "maxTokensField": "max_tokens"
+    }
+  },
   {
     "id": "kimi-k2.5",
     "name": "Kimi K2.5",
@@ -358,10 +389,10 @@
       "text"
     ],
     "cost": {
-      "input": 0.5504,
-      "output": 2.885,
+      "input": 0.5284,
+      "output": 2.785,
       "cacheRead": 0,
-      "cacheWrite": 0.2752
+      "cacheWrite": 0.2642
     },
     "contextWindow": 262144,
     "maxTokens": 26214,
@@ -538,10 +569,10 @@
       "text"
     ],
     "cost": {
-      "input": 0.404,
-      "output": 1.496,
+      "input": 0.418,
+      "output": 1.588,
       "cacheRead": 0,
-      "cacheWrite": 0.202
+      "cacheWrite": 0.209
     },
     "contextWindow": 262100,
     "maxTokens": 6553,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-hypercharm-provider",
-  "version": "1.3.10",
+  "version": "1.3.12",
   "description": "HyperCharm provider extension for pi - Access DeepSeek, GLM, Kimi, Qwen, MiniMax, Gemma, and GPT-OSS models through the Charm Hyper API",
   "type": "module",
   "main": "index.ts",