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 inclusionAI's Ling 3.1 Flash: vendor list prices, limits, abilities and the Artificial Analysis indexes side by side - and what OpenSmartRoute does when both are available.
Ling 3.1 Flash lists at $0.112 per million tokens blended against $1.65 for Gemini 3.8 Flash - 15x less.
Intelligence index 41 against 41: within a point of each other.
Gemini 3.8 Flash reads 1.0M tokens at once, Ling 3.1 Flash 262k.
only Gemini 3.8 Flash offers image input.
Vendor list prices per million tokens and published limits; indexes are Artificial Analysis composites (0-100).
| Specification | Gemini 3.8 Flash | Ling 3.1 Flash |
|---|---|---|
| Input price / 1M tokens | $0.82 | $0.07 |
| Output price / 1M tokens | $4.13 | $0.23 |
| Blended (3 in : 1 out) | $1.65 | $0.11 |
| Cached input / 1M | $0.08 | $0.01 |
| Context window | 1.0M | 262K |
| Max output | 66K | 236K |
| Input | text, image, video, file, audio | text |
| Output | text | text |
| Tool calls | ||
| Structured output | ||
| Reasoning | ||
| Open weights | ||
| Intelligence index | 41 | 41 |
| Coding index | 76 | - |
| Agentic index | 40 | - |
| Released | Sep 2, 2026 | Oct 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 | Ling 3.1 Flash | Difference |
|---|---|---|---|
| Support chat20M tokens in, 5M out a month - a help desk answering a few thousand conversations. | $37.13 | $2.63 | $34.50 less on Ling 3.1 Flash |
| Document summaries100M in, 5M out - long inputs, short answers. | $103 | $8.63 | $94.50 less on Ling 3.1 Flash |
| Coding assistant60M in, 20M out - a team's editor assistant, output-heavy. | $132 | $9.00 | $123 less on Ling 3.1 Flash |
The two measure the same on the intelligence index, so the router treats them as peers and lets price, observed latency and your outcomes decide: Ling 3.1 Flash wins on cost, and a few bad outcomes on either move the next requests to the other.
# targets.yaml - both models as routing targets (metadata.model links each to the catalogue entry)
targets:
- { id: ling-3.1-flash, kind: llm, metadata: { model: inclusionai/ling-3.1-flash } }
- { id: gemini-3.8-flash, kind: llm, metadata: { model: google/gemini-3.8-flash } }
# 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: [ling-3.1-flash]
weight: 0.8
- name: hard-requests-escalate
when: { min_complexity: 0.45 }
prefer: [gemini-3.8-flash]
weight: 0.8Every Google and inclusionAI model, with prices, is on the vendor pages; the rankings show what the router actually picks.