Muse Spark 1.2
LLM Provider / Model ยท Real coding workflows and long-running tasks in a single session
At a glance
| Input price | $1.25 |
| Output price | $4.25 |
| Price tier | Mid |
| Context window | 1M+ |
| Max output | 64K |
| Context tier | 500K+ |
| Speed tier | Standard |
| Latency | medium |
| Modality | Multimodal (vision) |
| Model ID | muse-spark-1.2 |
| Provider | Meta |
| Benchmark | Higher first-attempt accuracy and more reliable tool calling than 1.1 |
| Released | Aug 2026 |
| Hosting | Closed/API |
| Capabilities | Tool use, Agentic coding, Streaming, Structured output, Long-running sessions |
What Muse Spark 1.2 does
Tool use, Agentic coding, Streaming, Structured output, Long-running sessions
Best for
Real coding workflows and long-running tasks in a single session
Works well with
Agent / Orchestration
Conflicts & caveats
- Trae's built-in model menu may not include Muse Spark 1.2 โ Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
- Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Muse Spark 1.2 is not in the supported model list.
- Kiro's spec mode is tuned for Claude models โ Muse Spark 1.2 may work but spec-driven flows are best with Claude.
- Cursor's built-in model menu may not include Muse Spark 1.2 โ verify it's available in your Cursor model picker.
- OpenAI Codex (VS Code) is tied to OpenAI's hosted GPT-5 and Codex models โ Muse Spark 1.2 is not selectable inside this integration.
- Gemini CLI is locked to Google Gemini models โ your LLM is Muse Spark 1.2.
- Claude Code only works with Claude models โ your LLM is Muse Spark 1.2.
- Devin uses Cognition's proprietary model internally โ your selected Muse Spark 1.2 will be ignored.
- OpenAI Codex (Cloud) runs GPT-5.1 Codex internally โ your selected Muse Spark 1.2 will be ignored.
- Jules runs Gemini models internally โ your selected Muse Spark 1.2 will be ignored.
- The Claude Code SDK is tuned for Claude models โ Muse Spark 1.2 may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
- Lovable uses a fixed internal model โ your selected Muse Spark 1.2 will be ignored.
- Replit Agent 3 uses its own model selection internally โ your selected Muse Spark 1.2 will be ignored.
Build a full stack around Muse Spark 1.2 โ Flowpicker shows compatibility warnings before you commit.
Open the stack planner โ