Last week these models went live in Command Code.
- DeepSeek V4.1 Flash
- Muse Spark 1.3 (with max reasoning)
- Ling 3.0 Flash Sante (free model)
🐐
DeepSeek V4.1 Flash, Muse Spark 1.3 and Ling 3.0 Flash Sante at a glance
- DeepSeek V4.1 Flash: V4.1 hybrid-attention reasoning with vision.
- Muse Spark 1.3: multimodal reasoning for long-horizon agentic and coding workflows.
| Model | Context | Intelligence Index | Input | Output | Cache read | Plans |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 1M tokens | 39.5 | $0.15/M | $0.60/M | $0.003/M | Go and above |
| Muse Spark 1.3 | 1.05M tokens | 48.1 | $1.25/M | $4.25/M | $0.15/M | GOAT and above |
| Ling 3.0 Flash Sante | 262K tokens | - | $0.00/M | $0.00/M | $0.00/M | Go and above |
Prices are per 1M tokens. Specs, pricing and plans are from each model's page as of September 28, 2026, including any deal running that day, so they can differ from the launch pricing above: DeepSeek V4.1 Flash, Muse Spark 1.3, Ling 3.0 Flash Sante. Intelligence Index scores are from Artificial Analysis.
Use them
1cmd --model deepseek/deepseek-v4.1-flash
2cmd --model meta/muse-spark-1.3
3cmd --model inclusionai/ling-3.0-flash-sante:freeOr type /model in a session and pick one. You can switch mid-session without losing context.
Try Command Code
The best coding agent for open models, in your terminal or on your desktop.
1npm i -g command-codeDesktop App · Docs · X · Discord
