API price comparison · Updated
Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 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 3.8 Flash costs $0.042 and Claude Haiku 5.5 $0.0056: Gemini 3.8 Flash costs 7.5× as much. Gemini 3.8 Flash's price changes on Jan 1, 2027 to $1.50 input and $7.50 output per million tokens.
Claude Haiku 5.5 costs 87% less for this workload. Excludes cache writes, tools and taxes.
| Price | Gemini 3.8 Flash | Claude Haiku 5.5 |
|---|---|---|
| Model ID | gemini-3.8-flash | claude-haiku-5-5 |
| Input | $0.75 | $0.10 |
| Cache read | $0.075 | $0.01 |
| Cache write | Storage billed per hour | $0.125 |
| Output | $3.75 | $0.50 |
| Batch in / out | $0.375 / $1.875 | $0.05 / $0.25 |
| Long prompts | Same rate | Over 100,000: $0.50 / $2.50 |
| Scheduled change | From Jan 1, 2027: $1.50 / $7.50 | 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 3.8 Flash 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 3.8 Flash | Claude Haiku 5.5 | Per 1,000 requests | Difference |
|---|---|---|---|---|
| Chat reply3,000 input tokens, 500 output | $0.0041 | $0.0006 | $4.13 / $0.550 | Gemini 3.8 Flash costs 7.5× as much |
| Document summary30,000 input tokens, 1,500 output | $0.028 | $0.0037 | $28.13 / $3.75 | Gemini 3.8 Flash costs 7.5× as much |
| Agent task80,000 input tokens (60,000 cached), 6,000 output | $0.042 | $0.0056 | $42.00 / $5.60 | Gemini 3.8 Flash costs 7.5× as much |
| Long document300,000 input tokens, 2,000 output | $0.233 | $0.155 | $233 / $155 | Claude Haiku 5.5 costs 33% less |
Ganivra prices every Gemini 3.8 Flash 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 3.8 Flash costs $0.75 input and $3.75 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 3.8 Flash costs 7.5× as much: $42.00 against $5.60 per 1,000 tasks.
$0.75 input and $3.75 output per million tokens on Google Gemini's API, with cached input at $0.075 and Batch at $0.375 input and $1.875 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 3.8 Flash costs $0.233 and Claude Haiku 5.5 $0.155: Claude Haiku 5.5 costs 33% less. On Gemini 3.8 Flash, 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.
Yes. On Jan 1, 2027, Gemini 3.8 Flash goes from $0.75 input and $3.75 output to $1.50 input and $7.50 output per million tokens. After the change, the agent task costs $0.084 on Gemini 3.8 Flash against $0.0056 on Claude Haiku 5.5.
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 3.8 Flash and on Claude Haiku 5.5, next to what each customer pays you.
Every model on one page: Gemini 3.8 Flash pricing · Claude Haiku 5.5 pricing · all model price comparisons · all supported models.