GVGanivra

API price comparison · Updated

Claude Opus 5.5 vs Gemini 4 Argon pricing

Quick answer

Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; Gemini 4 Argon costs $2.00 and $10.00. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), Claude Opus 5.5 costs $0.212 and Gemini 4 Argon $0.106: Claude Opus 5.5 costs 2× as much. Gemini 4 Argon's price changes on Dec 1, 2026 to $4.00 input and $20.00 output per million tokens.

Compare your monthly cost on Claude Opus 5.5 and Gemini 4 Argon

Estimated monthly cost
Claude Opus 5.5$2,200$0.022 per request
Gemini 4 Argon$1,100$0.011 per request

Gemini 4 Argon costs 50% less for this workload. Excludes cache writes, tools and taxes.

Claude Opus 5.5 vs Gemini 4 Argon prices per million tokens

PriceClaude Opus 5.5Gemini 4 Argon
Model IDclaude-opus-5-5gemini-4-argon
Input$4.00$2.00
Cache read$0.20$0.10
Cache write$5.00Storage billed per hour
Output$20.00$10.00
Batch in / out$2.00 / $10.00$1.00 / $5.00
Long promptsSame rateSame rate
Scheduled changeNone announcedFrom Dec 1, 2026: $4.00 / $20.00
StatusAvailablePaid tier only

Prices for each provider’s own API, from Anthropic’s pricing page and Google Gemini’s pricing page. The lower price in each row is highlighted. Ganivra uses these same rates to price Claude Opus 5.5 and Gemini 4 Argon calls.

What one request costs on Claude Opus 5.5 and Gemini 4 Argon

Worked out from the prices above at standard rates, with no Batch discount. Long-prompt rates apply where a model has them.

RequestClaude Opus 5.5Gemini 4 ArgonPer 1,000 requestsDifference
Chat reply3,000 input tokens, 500 output$0.022$0.011$22.00 / $11.00Claude Opus 5.5 costs 2× as much
Document summary30,000 input tokens, 1,500 output$0.150$0.075$150 / $75.00Claude Opus 5.5 costs 2× as much
Agent task80,000 input tokens (60,000 cached), 6,000 output$0.212$0.106$212 / $106Claude Opus 5.5 costs 2× as much
Long document300,000 input tokens, 2,000 output$1.24$0.620$1,240 / $620Claude Opus 5.5 costs 2× as much

What changes which one costs less

Prompt caching
Cache reads cost $0.20 per million, 5% of the input price on Claude Opus 5.5, and $0.10 per million, 5% of the input price on Gemini 4 Argon. The more of each prompt you reuse, the more this decides the bill.
Cache writes
Claude Opus 5.5 charges $5.00 per million tokens written to cache. Gemini 4 Argon charges no write fee; Gemini bills cache storage per million tokens per hour.
Long prompts
On Claude Opus 5.5, one rate at any prompt length. On Gemini 4 Argon, one rate at any prompt length. A 300 prompt costs $1.24 on Claude Opus 5.5 and $0.620 on Gemini 4 Argon.
Batch API
Claude Opus 5.5 costs 50% less through the Batch API: $2.00 input and $10.00 output. Gemini 4 Argon costs 50% less through the Batch API: $1.00 input and $5.00 output.
Price change on Dec 1, 2026
Gemini 4 Argon goes from $2.00 input and $10.00 output to $4.00 input and $20.00 output per million tokens. Calls before then keep the old price; the agent task goes from $0.106 to $0.212.
Gemini 4 Argon availability
Paid tier only.
Token counts
Anthropic and Google Gemini use different tokenizers, so the same text becomes a different number of tokens. The model with the lower per-token price can still cost more per request; compare on your own prompts before switching.

Compare them on your own customers, not a sample request.

Ganivra prices every Claude Opus 5.5 and Gemini 4 Argon 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.

Start free 14-day trial

Claude Opus 5.5 vs Gemini 4 Argon pricing questions

Is Claude Opus 5.5 cheaper than Gemini 4 Argon?

Per million tokens, Claude Opus 5.5 costs $4.00 input and $20.00 output, and Gemini 4 Argon $2.00 input and $10.00 output. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), Claude Opus 5.5 costs 2× as much: $212 against $106 per 1,000 tasks.

How much does Claude Opus 5.5 cost per million tokens?

$4.00 input and $20.00 output per million tokens on Anthropic's API, with cached input at $0.20 and Batch at $2.00 input and $10.00 output. The rate is the same at any prompt length.

How much does Gemini 4 Argon cost per million tokens?

$2.00 input and $10.00 output per million tokens on Google Gemini's API, with cached input at $0.10 and Batch at $1.00 input and $5.00 output. The rate is the same at any prompt length.

Which is cheaper for long prompts, Claude Opus 5.5 or Gemini 4 Argon?

For a 300,000 input tokens, 2,000 output request, Claude Opus 5.5 costs $1.24 and Gemini 4 Argon $0.620: Claude Opus 5.5 costs 2× as much. On Claude Opus 5.5, one rate at any prompt length; on Gemini 4 Argon, one rate at any prompt length.

Is Gemini 4 Argon getting more expensive?

Yes. On Dec 1, 2026, Gemini 4 Argon goes from $2.00 input and $10.00 output to $4.00 input and $20.00 output per million tokens. After the change, the agent task costs $0.212 on Gemini 4 Argon against $0.212 on Claude Opus 5.5.

How do I compare Claude Opus 5.5 and Gemini 4 Argon on my own traffic?

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 Claude Opus 5.5 and on Gemini 4 Argon, next to what each customer pays you.

Every model on one page: Claude Opus 5.5 pricing · Gemini 4 Argon pricing · all model price comparisons · all supported models.