Loading
90 days of the enterprise, pro and team plans free, no card needed. See the plans
Model comparison
Anthropic's Claude Opus 4.7 against Google's Gemini 3.8 Flash: 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 $10 for Claude Opus 4.7 - 6.1x less.
Intelligence index 41 against 41: within a point of each other.
Gemini 3.8 Flash scores 76 on the coding index against 74 - 3 points apart.
Gemini 3.8 Flash scores 40 on the agentic index against 39 - 2 points apart.
Gemini 3.8 Flash reads 1.0M tokens at once, Claude Opus 4.7 1M.
Gemini 3.8 Flash was released about 5 months later.
Vendor list prices per million tokens and published limits; indexes are Artificial Analysis composites (0-100).
| Specification | Claude Opus 4.7 | Gemini 3.8 Flash |
|---|---|---|
| Input price / 1M tokens | $5.00 | $0.82 |
| Output price / 1M tokens | $25.0 | $4.13 |
| Blended (3 in : 1 out) | $10.0 | $1.65 |
| Cached input / 1M | $0.50 | $0.08 |
| Context window | 1M | 1.0M |
| Max output | 128K | 66K |
| Input | text, image, file | text, image, video, file, audio |
| Output | text | text |
| Tool calls | ||
| Structured output | ||
| Reasoning | ||
| Open weights | ||
| Intelligence index | 41 | 41 |
| Coding index | 74 | 76 |
| Agentic index | 39 | 40 |
| Released | Apr 16, 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 Opus 4.7 | Gemini 3.8 Flash | Difference |
|---|---|---|---|
| Support chat20M tokens in, 5M out a month - a help desk answering a few thousand conversations. | $225 | $37.13 | $188 less on Gemini 3.8 Flash |
| Document summaries100M in, 5M out - long inputs, short answers. | $625 | $103 | $522 less on Gemini 3.8 Flash |
| Coding assistant60M in, 20M out - a team's editor assistant, output-heavy. | $800 | $132 | $668 less on Gemini 3.8 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: Gemini 3.8 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: gemini-3.8-flash, kind: llm, metadata: { model: google/gemini-3.8-flash } }
- { id: claude-opus-4.7, kind: llm, metadata: { model: anthropic/claude-opus-4.7 } }
# 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: [claude-opus-4.7]
weight: 0.8Every Anthropic and Google model, with prices, is on the vendor pages; the rankings show what the router actually picks.