LogoFastRouter

Claude Fable 5 vs Muse Spark 1.2

Side-by-side pricing per provider, context window, benchmark scores and speed, all on one OpenAI-compatible API.

Metric
Claude Fable 5Anthropicanthropic/claude-fable-5
Muse Spark 1.2Metameta/muse-spark-1.2
Creator
Anthropic
Meta
Released
Jun 9, 2026
Aug 22, 2025
Context window
1M
1.05M (best)
Max output
128K
131K (best)
Input / 1MLowest provider price
$10.00
$1.25 (best)
Output / 1MLowest provider price
$50.00
$4.25 (best)
Providers
1
1
IntelligenceArtificial Analysis index
49.6 (best)
39.6
CodingArtificial Analysis index
76.5 (best)
72.2
LatencyMedian time to first token
14s
—
ThroughputMedian tokens per second
<1 t/s
—
Accepts
Text, Image, Files
Text, Image, Video, Audio, Files
Produces
Text
Text
Tool calling
Yes
Yes
Structured output
Yes
No
Reasoning
Yes
Yes

Claude Fable 5 vs Muse Spark 1.2: summary

Claude Fable 5 and Muse Spark 1.2 are both available through FastRouter's OpenAI-compatible API, so switching between them is a change of model id, not a new integration.

Claude Fable 5, from Anthropic, has a 1,000,000-token context window, costs $10.00/1M input and $50.00/1M output tokens and scores 49.6 on the Artificial Analysis Intelligence Index.

Muse Spark 1.2, from Meta, has a 1,048,576-token context window, costs $1.25/1M input and $4.25/1M output tokens and scores 39.6 on the Artificial Analysis Intelligence Index.

Muse Spark 1.2 is the cheapest on input, 8× cheaper than the next model, Muse Spark 1.2 has the largest context window, Claude Fable 5 scores highest for intelligence and Claude Fable 5 leads on coding.

Switch with one line

client = OpenAI(base_url="https://api.fastrouter.ai/api/v1", api_key="<FASTROUTER_API_KEY>") client.chat.completions.create(model="anthropic/claude-fable-5", messages=[...]) # or client.chat.completions.create(model="meta/muse-spark-1.2", messages=[...])
Full API docs

Frequently asked questions

More comparisons

Benchmark scores sourced from ArtificialAnalysis