Muse Spark 1.3 on QuickSilver Pro
Muse Spark 1.3 is Meta's flagship coding & agentic reasoning model — its most capable Muse yet, with stronger agentic and coding performance and better usability than Muse Spark 1.2, over a 1M-token context with multimodal input. On QuickSilver Pro it's $1.00 input / $3.40 output per million tokens — ~20% below Meta's published API list price of $1.25 / $4.25 on both legs.
At a glance
Repository-scale coding and long-horizon agentic development with extended reasoning over a 1M-token context.
Pricing comparison ($/1M tokens)
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $1.00 | $3.40 | lowest-cost |
| Meta list price (meta/muse-spark-1.3) | $1.25 | $4.25 | 20% lower |
When to use
Reach for Muse Spark 1.3 on the hardest coding and agentic work: end-to-end feature generation across a whole repository, complex multi-file debugging, codebase understanding, and long-horizon agents that plan and iterate across many tool calls. It is Meta's most capable Muse model, its 1M-token context holds large working sets, and it accepts images alongside code so an agent can iterate against screenshots, diagrams, and rendered output.
When to use something else
It reasons at length and is verbose, so for routine chat, short single-shot codegen, or latency-sensitive loops the token budget is overkill — DeepSeek V4 Flash ($0.086/$0.173) or Qwen3.7 Flash land those far lower. Reasoning is mandatory here, so it spends output tokens even on trivial turns; rein that in with `reasoning_effort: "low"` where cost matters (a small `max_tokens` only truncates the answer, not the thinking). Weights are closed and API-only; if you need self-hosting, choose an open-weight model such as Kimi K3.
Quickstart (curl)
curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-spark-1.3",
"messages": [{"role": "user", "content": "Hello!"}]
}'OpenAI-compatible. One-line migration via base_url.
FAQ
Coding and long-horizon agents. Meta trained it on whole-repository generation, large end-to-end projects, complex debugging, and codebase understanding, and pairs it with Muse Code, its coding agent. Meta describes 1.3 as its most capable model yet — stronger at agentic and coding tasks than Muse Spark 1.2, with better usability. It accepts text and images as input and returns text, over a 1M-token context.
1.3 is the newer flagship: Meta reports stronger agentic and coding performance and improved usability over 1.2, at the same price and the same 1M-token context. Muse Spark 1.2 remains available on QuickSilver Pro for anyone pinned to it — set model="muse-spark-1.2" — but 1.3 is the default recommendation for new work.
Reasoning is always on — it is mandatory on this endpoint and cannot be disabled (a request that tries to turn it off is rejected). Use `reasoning_effort` (`low`, `high`, or `max`) to trade depth against latency and cost; `low` roughly halves reasoning-token spend on simple turns. Reasoning tokens are drawn from your `max_tokens` budget before the visible answer, so set `max_tokens` generously — 1024 or more — or the reply can come back empty because the budget was spent thinking.
Meta's published API list price is $1.25 input / $4.25 output per 1M tokens; QuickSilver Pro is $1.00 / $3.40 — ~20% below on both legs. Same OpenAI-compatible surface: point base_url at https://api.quicksilverpro.io/v1 and use model="muse-spark-1.3".
Yes — it's an OpenAI-compatible chat completions endpoint, with the Responses API available too. Set base_url=https://api.quicksilverpro.io/v1 and model="muse-spark-1.3", and point coding agents (the same ones you'd run Muse Code-style workflows with) at that base URL.