Claude vs Gemini, compared on real cost. We ran every model from both on the same example workload (chatbot, 100k requests/mo, 70% cached) so the prices line up directly. The lowest-cost model across both is Gemini 3.1 Flash-Lite ($63.5/mo). Full table and verdict below.
At the budget end, Gemini is the lower-cost option on this workload: Claude's cheapest (Claude Haiku 4.5) is $224/mo vs Gemini's (Gemini 3.1 Flash-Lite) $63.5/mo.
At the top end, Claude's flagship Claude Fable 5 runs $2,240/mo vs Gemini's Gemini 3.1 Pro Preview at $508/mo. Largest verified context window — Claude: 1M tokens; Gemini: 1M tokens.
Both are priced by the same engine, so compare your own workload in the calculator — the cheaper choice flips with your token mix and cache share.
Every model from both providers on one example workload (100k requests/mo, 2,000 input / 300 output tokens, 70% cached), cheapest first. The single lowest-cost model is highlighted.
| Model | $ input /1M | $ output /1M | $ cached /1M | ≈ $/mo * |
|---|---|---|---|---|
| Gemini 3.1 Flash-LiteBUDGETGoogle (Gemini) | $0.25 | $1.50 | $0.025 | $63.5 |
| Gemini 3 Flash PreviewMIDGoogle (Gemini) | $0.50 | $3 | $0.05 | $127 |
| Claude Haiku 4.5BUDGETAnthropic | $1 | $5 | $0.10 | $224 |
| Gemini 3.5 FlashMIDGoogle (Gemini) | $1.50 | $9 | $0.15 | $381 |
| Gemini 3.1 Pro PreviewFRONTIERGoogle (Gemini) | $2 | $12 | $0.20 | $508 |
| Claude Sonnet 4.6MIDAnthropic | $3 | $15 | $0.30 | $672 |
| Claude Opus 4.8FRONTIERAnthropic | $5 | $25 | $0.50 | $1,120 |
| Claude Fable 5FRONTIERAnthropic | $10 | $50 | $1 | $2,240 |
* Same engine as the calculator. See Claude pricing · Gemini pricing in full.