command-code 1.5.0 → 1.6.0

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.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,15 @@
1
1
  # command-code
2
2
 
3
+ ## 1.6.0
4
+
5
+ ### Minor Changes
6
+
7
+ - feat: add add thinkingmachines/inkling-small model
8
+
9
+ ### Patch Changes
10
+
11
+ - fix: mark Qwen 3.7 Flash as vision-capable
12
+
3
13
  ## 1.5.0
4
14
 
5
15
  ### Minor Changes
@@ -34,6 +34,7 @@ The model catalog — every id `/model`, `--model`, `model:effort` shorthand, an
34
34
  | `tencent/hy3-paid` | Tencent Hy3 | 262K | — | $0.14/$0.58 | sparse-MoE reasoning & agentic tool use |
35
35
  | `nvidia/nemotron-3-ultra-550b-a55b` | Nemotron 3 Ultra | 1M | — | $0.6/$2.4 | open reasoning model for long-horizon autonomous agents |
36
36
  | `thinkingmachines/inkling` | Inkling | 256K | — | $1/$4.05 | multimodal MoE reasoning |
37
+ | `thinkingmachines/inkling-small` | Inkling Small | 1M | — | $0.5/$1.2 | lightweight MoE reasoning at lower cost and latency |
37
38
  | `poolside/laguna-s-2.1-free` | Laguna S 2.1 | 256K | — | $0/$0 | open-weight agentic coding and long-horizon work |
38
39
  | `inclusionai/ling-3.0-flash-free` | Ling 3.0 Flash | 256K | — | $0/$0 | fast lightweight-MoE coding & agentic work |
39
40
  ## Anthropic
@@ -265,6 +265,7 @@ Valid model ids (the /model catalog — use these EXACT ids):
265
265
  - MiniMaxAI/MiniMax-M3-Free
266
266
  - moonshotai/Kimi-K3
267
267
  - thinkingmachines/inkling
268
+ - thinkingmachines/inkling-small
268
269
  - deepseek/deepseek-v4-pro
269
270
  - deepseek/deepseek-v4-flash
270
271
  - moonshotai/Kimi-K2.7-Code