Claude Sonnet 5.5 vs Gemini 3.8 Flash: pricing and benchmarks
Gemini 3.8 Flash is 63% cheaper on input tokens ($0.75 vs $2.00 per 1M). Gemini 3.8 Flash is 63% cheaper on output tokens ($3.75 vs $10.00 per 1M). On our document Q&A workload (50,000 questions a month), Gemini 3.8 Flash costs $412.50 a month versus $1,100 for Claude Sonnet 5.5, 63% less. Claude Sonnet 5.5 scores 164.4 on the Epoch Capabilities Index vs 157.2 for Gemini 3.8 Flash.
Which should you choose?
Claude Sonnet 5.5 scores 164.4 on the Epoch Capabilities Index vs 157.2 for Gemini 3.8 Flash.
Claude Sonnet 5.5 scores 88.8% on FrontierMath (Tiers 1–3) vs 68.4% for Gemini 3.8 Flash.
Gemini 3.8 Flash costs $1.50 per 1M tokens (3:1 input-to-output mix) vs $4.00 for Claude Sonnet 5.5, 63% less.
A trade-off: Claude Sonnet 5.5 is 7.3 ECI points more capable but costs 2.7x as much as Gemini 3.8 Flash.
Pricing and specs
| Claude Sonnet 5.5 | Gemini 3.8 Flash | |
|---|---|---|
| Provider | Anthropic | |
| API model ID | claude-sonnet-5-5 | gemini-3.8-flash |
| Input / 1M tokens | $2.00 | $0.75 |
| Cached input / 1M tokens | $0.20 | $0.075 |
| Output / 1M tokens | $10.00 | $3.75 |
| Long-context rates | — | — |
| Context window | 1M tokens | 1.05M tokens |
| Max output | 128K tokens | 66K tokens |
| Batch discount | 50% off | 50% off |
Benchmarks
| Claude Sonnet 5.5 | Gemini 3.8 Flash | |
|---|---|---|
| Epoch Capabilities Index | 164.4 | 157.2 |
| GPQA Diamond· Science reasoning | 95.6% | 95.4% |
| FrontierMath (Tiers 1–3)· Advanced math | 88.8% | 68.4% |
| SimpleQA Verified· Factual accuracy | 46.5% | 69.7% |
| ARC-AGI-2· Abstract reasoning | — | 89.2% |
| DeepSWE· Coding | — | 73.8% |
| APEX-Agents· Agentic work | 75.5% | 64.3% |
Source: Epoch AI, best recorded result per model (CC BY 4.0). A dash means no published score. See all benchmarks
Monthly cost for real workloads
| Workload | Claude Sonnet 5.5 | Gemini 3.8 Flash | Difference |
|---|---|---|---|
Support chatbot 100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each. | $700.00 | $262.50 | Gemini 3.8 Flash 63% cheaper |
Document Q&A (RAG) 50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each. | $1,100 | $412.50 | Gemini 3.8 Flash 63% cheaper |
Coding agent 10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens. | $496.00 | $186.00 | Gemini 3.8 Flash 63% cheaper |
Cached chatbot The same 100,000-reply support chatbot, but 60% of each prompt (system prompt + conversation history) is served from the prompt cache. | $538.00 | $201.75 | Gemini 3.8 Flash 63% cheaper |
Meeting notes 10,000 meetings a month summarized from ~12,000-token transcripts, ~1,000 output tokens each. | $340.00 | $127.50 | Gemini 3.8 Flash 63% cheaper |
Bulk translation 200,000 short translations a month, ~800 input and ~800 output tokens each. | $1,920 | $720.00 | Gemini 3.8 Flash 63% cheaper |
Content moderation 1,000,000 classifications a month, ~400 input tokens and ~80 output tokens each. | $1,600 | $600.00 | Gemini 3.8 Flash 63% cheaper |
Article drafting 300 long-form articles a month written from a ~4,000-token brief and outline, ~5,000 output tokens each. | $17.40 | $6.52 | Gemini 3.8 Flash 63% cheaper |
Code review bot 30,000 pull-request reviews a month, ~5,000 input tokens each (30% cached repository context) and ~700 output tokens. | $429.00 | $160.88 | Gemini 3.8 Flash 63% cheaper |
Invoice extraction 100,000 documents a month parsed into structured JSON, ~1,200 input and ~250 output tokens each. | $490.00 | $183.75 | Gemini 3.8 Flash 63% cheaper |
Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.
Claude Sonnet 5.5 vs Gemini 3.8 Flash cost calculator
- $412.50/mo$0.0083 / req
- Claude Sonnet 5.5Anthropic$1,100/mo$0.02 / req
Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.
Claude Sonnet 5.5 pricing notes
Anthropic’s fast mid-tier model, successor to Claude Sonnet 5 at the same price.
- Cache writes cost $2.50 (5-minute cache) or $4 (1-hour cache) per 1M tokens.
- US-only inference (inference_geo: "us") costs 1.1x.
Gemini 3.8 Flash pricing notes
Google’s newest Flash model, with thinking, tool use and a 1M-token context window.
- Introductory price through December 31, 2026. From January 1, 2027: $1.50 input, $0.15 cached, $7.50 output per 1M tokens.
- Output price includes thinking tokens.
- Priority inference costs 1.8x the standard rate.
Frequently asked questions
- Is Claude Sonnet 5.5 cheaper than Gemini 3.8 Flash?
- Gemini 3.8 Flash is 63% cheaper on input tokens ($0.75 vs $2.00 per 1M). Gemini 3.8 Flash is 63% cheaper on output tokens ($3.75 vs $10.00 per 1M). On our document Q&A workload (50,000 questions a month), Gemini 3.8 Flash costs $412.50 a month versus $1,100 for Claude Sonnet 5.5, 63% less.
- Which is more capable, Claude Sonnet 5.5 or Gemini 3.8 Flash?
- Claude Sonnet 5.5 scores 164.4 on the Epoch Capabilities Index vs 157.2 for Gemini 3.8 Flash.
- How much does Claude Sonnet 5.5 cost per 1M tokens?
- Claude Sonnet 5.5 costs $2.00 per 1M input tokens and $10.00 per 1M output tokens, and $0.20 per 1M cached input tokens on Anthropic’s standard tier.
- How much does Gemini 3.8 Flash cost per 1M tokens?
- Gemini 3.8 Flash costs $0.75 per 1M input tokens and $3.75 per 1M output tokens, and $0.075 per 1M cached input tokens on Google’s standard tier.
- Which has the larger context window, Claude Sonnet 5.5 or Gemini 3.8 Flash?
- Gemini 3.8 Flash has the larger context window: 1.05M tokens versus 1M for Claude Sonnet 5.5.