LLM / Claude vs Gemini

Claude vs Gemini: API pricing compared

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.

Prices verified June 2026 · changes logged in the changelog

Claude vs Gemini: the short answer

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.

Claude and Gemini models, priced side by side

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.

Claude or Gemini for your workload?
The cheaper option depends on your volume and cache share — run both through the calculator.
Open calculator
All 28 models → OpenAI pricing → Anthropic pricing → Gemini pricing → DeepSeek pricing → Grok pricing → Mistral pricing → Cheapest LLM API → Open calculator →

Frequently asked questions

On our example chatbot workload, Claude's cheapest model (Claude Haiku 4.5) is $224/mo and Gemini's (Gemini 3.1 Flash-Lite) is $63.5/mo. So Gemini is lower-cost at the budget end. The cheaper choice can flip with your token mix — check the calculator.
The largest context window we've verified is 1M tokens for Claude and 1M tokens for Gemini. Context windows vary by model within each provider — see the pricing pages for the per-model figures.
It depends on your workload. Compare the side-by-side table above for list prices and the ≈ $/mo column for a like-for-like cost, then run your own volume through the calculator. We rank on cost and published specs only — the changelog records every price change.
Every per-token rate is taken from each provider's official pricing and verified by hand (June 2026); the monthly figure is computed by our cost engine, not quoted.