Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Model comparison
Anthropic's Claude Fable 5 against Meta's Muse Spark 1.3: vendor list prices, limits, abilities and the Artificial Analysis indexes side by side - and what OpenSmartRoute does when both are available.
Muse Spark 1.3 lists at $2.00 per million tokens blended against $20 for Claude Fable 5 - 10x less.
Claude Fable 5 scores 50 on the intelligence index against 48 - 2 points apart.
Coding index 77 against 76: within a point of each other.
Muse Spark 1.3 scores 56 on the agentic index against 51 - 5 points apart.
Muse Spark 1.3 reads 1.0M tokens at once, Claude Fable 5 1M.
Muse Spark 1.3 was released about 3 months later.
Vendor list prices per million tokens and published limits; indexes are Artificial Analysis composites (0-100).
| Specification | Claude Fable 5 | Muse Spark 1.3 |
|---|---|---|
| Input price / 1M tokens | $10.0 | $1.25 |
| Output price / 1M tokens | $50.0 | $4.25 |
| Blended (3 in : 1 out) | $20.0 | $2.00 |
| Cached input / 1M | $1.00 | $0.15 |
| Context window | 1M | 1.0M |
| Max output | 128K | 944K |
| Input | text, image, file | text, image, video, file |
| Output | text | text |
| Tool calls | ||
| Structured output | ||
| Reasoning | ||
| Open weights | ||
| Intelligence index | 50 | 48 |
| Coding index | 77 | 76 |
| Agentic index | 51 | 56 |
| Released | Jun 9, 2026 | Sep 2, 2026 |
| Available on this deployment |
List price times tokens for three typical workloads; your mix of input and output decides which model's pricing suits you.
| Workload | Claude Fable 5 | Muse Spark 1.3 | Difference |
|---|---|---|---|
| Support chat20M tokens in, 5M out a month - a help desk answering a few thousand conversations. | $450 | $46.25 | $404 less on Muse Spark 1.3 |
| Document summaries100M in, 5M out - long inputs, short answers. | $1,250 | $146 | $1,104 less on Muse Spark 1.3 |
| Coding assistant60M in, 20M out - a team's editor assistant, output-heavy. | $1,600 | $160 | $1,440 less on Muse Spark 1.3 |
Muse Spark 1.3 takes the short and general requests - at $2.00 blended it is the default - and Claude Fable 5 the ones whose complexity or quality floor rules the cheaper model out. The split is per request, not per app, and every decision carries the scores for both.
# targets.yaml - both models as routing targets (metadata.model links each to the catalogue entry)
targets:
- { id: muse-spark-1.3, kind: llm, metadata: { model: meta/muse-spark-1.3 } }
- { id: claude-fable-5, kind: llm, metadata: { model: anthropic/claude-fable-5 } }
# rules.yaml - the cheaper model by default, the stronger one when the request is hard
rules:
- name: simple-requests-stay-cheap
when: { max_complexity: 0.45 }
prefer: [muse-spark-1.3]
weight: 0.8
- name: hard-requests-escalate
when: { min_complexity: 0.45 }
prefer: [claude-fable-5]
weight: 0.8Every Anthropic and Meta model, with prices, is on the vendor pages; the rankings show what the router actually picks.