Claude Sonnet 5.5vsGemini 3.8 Flash
Both language models, compared at each maker’s own API list prices. Every figure links to its source.
Compare at your usage
Every model priced for the same request8,000 tokens in, 2,000 out
| Claude Sonnet 5.5 on Claude API | Gemini 3.8 Flash on Gemini API | |
|---|---|---|
| Rate applied | Base rate | Base rate |
| Inputper 1M tokens | $2.00 | $0.75 |
| Cache readper 1M tokens | $0.10 | $0.075 |
| Outputper 1M tokens | $10.00 | $3.75 |
| Cost per request | $0.036 | $0.0135 |
| Per 1,000 requests | $36.00 | $13.50 |
- Claude Sonnet 5.5 Claude API pricing · as of Nov 1, 2026
- Gemini 3.8 Flash Gemini API pricing · as of Nov 1, 2026
Every model is priced for the same request at its maker’s own list prices (each with its source and date), so bold marks the cheapest. A model that can’t serve the request is named, not ranked; a condition its seller doesn’t price says which rate was used.
Cost per request as prompts grow
2K tokens out, list price on each maker’s API.
- Claude Sonnet 5.5 · Claude API
- Gemini 3.8 Flash · Gemini API
Where each stands among all scored models
Each line runs from the lowest to the highest score on the board; the tick is the median.
- Claude Sonnet 5.5
- Gemini 3.8 Flash
Key differences
InputMaker’s official API · global · USD
$2.00 / 1M tokens Claude API pricing · as of Nov 1, 2026
$0.75 / 1M tokens Gemini API pricing · as of Nov 1, 2026
OutputMaker’s official API · global · USD
$10.00 / 1M tokens Claude API pricing · as of Nov 1, 2026
$3.75 / 1M tokens Gemini API pricing · as of Nov 1, 2026
Context
1,000,000 Context windows · as of Oct 30, 2026
1,048,576 Gemini 3.8 Flash model · as of Nov 1, 2026
Max output
128,000 Claude Sonnet 5.5 model overview · as of Nov 1, 2026
65,536 Gemini 3.8 Flash model · as of Nov 1, 2026
Input modalities
Text, Image Claude Sonnet 5.5 model overview · as of Nov 1, 2026
Text, Image, Video, Audio, PDF Gemini 3.8 Flash model · as of Nov 1, 2026
Knowledge cutoff
Jun 2026 Claude Sonnet 5.5 model overview · as of Nov 1, 2026
Mar 2026 Gemini 3.8 Flash - Model Card — Google DeepMind · as of Oct 31, 2026
These differences use verified vendor specifications or each maker’s official API on the same region, currency, meter and billing conditions. Different conditions remain side by side in the full table; they do not establish which model is cheaper. Declared features describe support, not measured quality or a recommendation. Missing evidence does not mean a feature is unsupported.
Full comparison
| Claude Sonnet 5.5 Anthropic | Gemini 3.8 Flash Google | |
|---|---|---|
| Overview | ||
| Released | Sep 28, 2026 | Sep 2, 2026 |
| Open weights | — | — |
| Knowledge cutoff | Jun 2026 | Mar 2026 |
| Specs | ||
| Context | 1M | 1.05M |
| Max output | 128K | 65.54K |
| Input modalities | Text, Image | Text, Image, Video, Audio, PDF |
| Output modalities | Text | Text |
| Reasoning | ||
| Reasoning efforts | low, medium, high, xhigh, max | low, medium, high |
| Tool use | ||
| Structured output | ||
| Built-in tools | Not stated | Web search, Web fetch, Code execution, Computer use, Maps |
| Pricing · per 1M tokens | ||
| Input price | $2.00 | $0.75 |
| Output price | $10.00 | $3.75 |
| Cache read price | $0.10 | $0.075 |
| Cache write price | $2.505-minute cache | — |
| Cache write price (1-hour cache) | $4.001-hour cache | Not offered |
| Blended price (3 input : 1 output) | $4.00 | $1.50 |
| Pricing under conditions · per 1M tokens | ||
| Batch input price | $1.00Batch | $0.375Batch |
| Batch output price | $5.00Batch | $1.875Batch |
| Flex tier input price | Not offered | $0.375Flex tier |
| Flex tier output price | Not offered | $1.875Flex tier |
| Priority tier input price | Not offered | $1.35Priority tier |
| Priority tier output price | Not offered | $6.75Priority tier |
| Cited scores | ||
| Epoch Capabilities Index | 166.2 | 158.6 |
| LMArena Text | 1,477 xhigh effort | 1,496 high effort |
| LMArena Text · Coding | 1,529 xhigh effort | 1,530 high effort |
| LMArena Vision | 1,287 xhigh effort | 1,315 high effort |
| LMArena Text · Chinese | 1,545 xhigh effort | 1,536 high effort |
| Epoch AI · GPQA Diamond | 95.6% max effort | 95.4% high effort |
| Epoch AI · FrontierMath Tiers 1–3 | 88.8% max effort | 68.4% high effort |
Headline prices may come from different channels, regions or tiers. Check each source before choosing a model; missing facts stay blank.
Model details and sources
- Claude Sonnet 5.5 → Available
- Gemini 3.8 Flash → Available
Cited scores
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · Epoch AI Benchmarking Hub data · CC BY 4.0 · as of Nov 5, 2026
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · Epoch AI Benchmarking Hub data · CC BY 4.0 · as of Oct 28, 2026
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · Epoch AI Benchmarking Hub data · CC BY 4.0 · as of Nov 4, 2026
- LiveBench (White et al.), release 2026-06-25, livebench.ai, licensed CC BY-SA 4.0. This board, adapted from it, is shared under CC BY-SA 4.0. · LiveBench release 2026-06-25 · CC BY-SA 4.0 · as of Jun 25, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · LMArena leaderboard dataset (Hugging Face) · CC BY 4.0 · as of Oct 28, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · LMArena leaderboard dataset (Hugging Face) · CC BY 4.0 · as of Oct 19, 2026
- Terminal-Bench 4.0 leaderboard (Marten, Shaw et al., Terminal-Bench; harbor-framework/terminal-bench on GitHub), licensed Apache-2.0. · harbor-framework/terminal-bench leaderboard submissions · Apache-2.0 · as of Sep 29, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · EQ-Bench: Longform Writing · MIT · as of Oct 28, 2026