API price comparison · Updated
Gemini 3.5 Flash-Lite costs $0.30 per million input tokens and $2.50 per million output tokens; Claude Haiku 5.5 costs $0.10 and $0.50. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), Gemini 3.5 Flash-Lite costs $0.023 and Claude Haiku 5.5 $0.0056: Gemini 3.5 Flash-Lite costs 4.1× as much. For a long document (300,000 input tokens, 2,000 output) the order flips: Gemini 3.5 Flash-Lite costs 39% less.
Claude Haiku 5.5 costs 74% less for this workload. Excludes cache writes, tools and taxes.
| Price | Gemini 3.5 Flash-Lite | Claude Haiku 5.5 |
|---|---|---|
| Model ID | gemini-3.5-flash-lite | claude-haiku-5-5 |
| Input | $0.30 | $0.10 |
| Cache read | $0.03 | $0.01 |
| Cache write | Storage billed per hour | $0.125 |
| Output | $2.50 | $0.50 |
| Batch in / out | $0.15 / $1.25 | $0.05 / $0.25 |
| Long prompts | Same rate | Over 100,000: $0.50 / $2.50 |
| Scheduled change | None announced | None announced |
| Status | Available | Available |
Prices for each provider’s own API, from Google Gemini’s pricing page and Anthropic’s pricing page. The lower price in each row is highlighted. Ganivra uses these same rates to price Gemini 3.5 Flash-Lite and Claude Haiku 5.5 calls.
Worked out from the prices above at standard rates, with no Batch discount. Long-prompt rates apply where a model has them.
| Request | Gemini 3.5 Flash-Lite | Claude Haiku 5.5 | Per 1,000 requests | Difference |
|---|---|---|---|---|
| Chat reply3,000 input tokens, 500 output | $0.0022 | $0.0006 | $2.15 / $0.550 | Gemini 3.5 Flash-Lite costs 3.9× as much |
| Document summary30,000 input tokens, 1,500 output | $0.013 | $0.0037 | $12.75 / $3.75 | Gemini 3.5 Flash-Lite costs 3.4× as much |
| Agent task80,000 input tokens (60,000 cached), 6,000 output | $0.023 | $0.0056 | $22.80 / $5.60 | Gemini 3.5 Flash-Lite costs 4.1× as much |
| Long document300,000 input tokens, 2,000 output | $0.095 | $0.155 | $95.00 / $155 | Gemini 3.5 Flash-Lite costs 39% less |
Ganivra prices every Gemini 3.5 Flash-Lite and Claude Haiku 5.5 call you make and adds it up by customer, feature and workflow, next to what each customer pays. Switch a workflow and see what it did to each customer’s margin.
Per million tokens, Gemini 3.5 Flash-Lite costs $0.30 input and $2.50 output, and Claude Haiku 5.5 $0.10 input and $0.50 output. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), Gemini 3.5 Flash-Lite costs 4.1× as much: $22.80 against $5.60 per 1,000 tasks. For a long document (300,000 input tokens, 2,000 output) the order flips: Gemini 3.5 Flash-Lite costs 39% less.
$0.30 input and $2.50 output per million tokens on Google Gemini's API, with cached input at $0.03 and Batch at $0.15 input and $1.25 output. The rate is the same at any prompt length.
$0.10 input and $0.50 output per million tokens on Anthropic's API, with cached input at $0.01 and Batch at $0.05 input and $0.25 output. Prompts over 100,000 tokens cost $0.50 input and $2.50 output.
For a 300,000 input tokens, 2,000 output request, Gemini 3.5 Flash-Lite costs $0.095 and Claude Haiku 5.5 $0.155: Gemini 3.5 Flash-Lite costs 39% less. On Gemini 3.5 Flash-Lite, one rate at any prompt length; on Claude Haiku 5.5, prompts over 100,000 tokens cost $0.50 input and $2.50 output for the whole request.
Record what each call actually used, then price the same usage on both models. Ganivra does this from your recorded calls: it shows what each customer, feature and workflow would cost on Gemini 3.5 Flash-Lite and on Claude Haiku 5.5, next to what each customer pays you.
Every model on one page: Gemini 3.5 Flash-Lite pricing · Claude Haiku 5.5 pricing · all model price comparisons · all supported models.