- 1M context
- Multimodal
- Reasoning
- Responses API
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.
- 1M context
- Vision
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$1.00 / $3.40
20% lower
on both legs vs Meta list price
Pricing comparison ($/1M tokens)
Bar length = price relative to the list price
| 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 |
Meta list source: openrouter.ai/meta/muse-spark-1.3
At a glance
- Context
- 1M tokens
- Input / 1M
- $1.00
- Output / 1M
- $3.40
- Thinks by default
- Yes
- Latency · live
- —
- AA Intelligence Index
- 53
Repository-scale coding and long-horizon agentic development with extended reasoning over a 1M-token context.
When is Muse Spark 1.3 the right call?
Curated from catalog capabilities and published prices, not a benchmark.
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.
- Long documents and codebases, up to 1M tokens of context
- Agents that call tools, with strict JSON Schema output
- Prompts that include images
- Multi-step reasoning, on by default
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 ($0.06/$0.18) 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)
Get an API key →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!"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="muse-spark-1.3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.quicksilverpro.io/v1",
apiKey: process.env.QSP_KEY,
});
const response = await client.chat.completions.create({
model: "muse-spark-1.3",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);curl https://api.quicksilverpro.io/v1/responses \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "muse-spark-1.3",
"input": "Hello!"
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="muse-spark-1.3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)OpenAI-compatible. One-line migration via base_url.
Gateway behavior
Compatibility notes for this model.
prompt- Prompts up to 1M tokens.
- /v1/chat/completions: Supported
- /v1/responses: Supported
- streaming: Supported
- tools: Supported
- image input: Supported
- JSON Schema: Supported
- reasoning: Supported
Where the price comes from
- Provider reference
- $1.25 / $4.25openrouter.ai/meta/muse-spark-1.3
- Catalog verified
- Prompt cache · not compared
- $0.12 read
usage.cost = prompt_tokens × $1.00/1M + completion_tokens × $3.40/1M
FAQ
Common questions
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.