Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Model comparison
Google's Gemini 3.8 Flash 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.
Gemini 3.8 Flash lists at $1.65 per million tokens blended against $2.00 for Muse Spark 1.3 - 1.2x less.
Muse Spark 1.3 scores 48 on the intelligence index against 41 - 7 points apart.
Coding index 76 against 76: within a point of each other.
Muse Spark 1.3 scores 56 on the agentic index against 40 - 15 points apart.
Vendor list prices per million tokens and published limits; indexes are Artificial Analysis composites (0-100).
| Specification | Gemini 3.8 Flash | Muse Spark 1.3 |
|---|---|---|
| Input price / 1M tokens | $0.82 | $1.25 |
| Output price / 1M tokens | $4.13 | $4.25 |
| Blended (3 in : 1 out) | $1.65 | $2.00 |
| Cached input / 1M | $0.08 | $0.15 |
| Context window | 1.0M | 1.0M |
| Max output | 66K | 944K |
| Input | text, image, video, file, audio | text, image, video, file |
| Output | text | text |
| Tool calls | ||
| Structured output | ||
| Reasoning | ||
| Open weights | ||
| Intelligence index | 41 | 48 |
| Coding index | 76 | 76 |
| Agentic index | 40 | 56 |
| Released | Sep 2, 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 | Gemini 3.8 Flash | Muse Spark 1.3 | Difference |
|---|---|---|---|
| Support chat20M tokens in, 5M out a month - a help desk answering a few thousand conversations. | $37.13 | $46.25 | $9.13 less on Gemini 3.8 Flash |
| Document summaries100M in, 5M out - long inputs, short answers. | $103 | $146 | $43.13 less on Gemini 3.8 Flash |
| Coding assistant60M in, 20M out - a team's editor assistant, output-heavy. | $132 | $160 | $28.00 less on Gemini 3.8 Flash |
Gemini 3.8 Flash takes the short and general requests - at $1.65 blended it is the default - and Muse Spark 1.3 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: gemini-3.8-flash, kind: llm, metadata: { model: google/gemini-3.8-flash } }
- { id: muse-spark-1.3, kind: llm, metadata: { model: meta/muse-spark-1.3 } }
# 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: [gemini-3.8-flash]
weight: 0.8
- name: hard-requests-escalate
when: { min_complexity: 0.45 }
prefer: [muse-spark-1.3]
weight: 0.8Every Google and Meta model, with prices, is on the vendor pages; the rankings show what the router actually picks.