API price comparison · Updated
GPT-6.1 Sol costs $2.00 per million input tokens and $10.00 per million output tokens; Gemini 4 Argon costs $2.00 and $10.00. The list prices are identical, so caching, long prompts and token counts decide which costs less. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), GPT-6.1 Sol costs $0.106 and Gemini 4 Argon $0.106: they cost the same. But for a long document (300,000 input tokens, 2,000 output), Gemini 4 Argon costs 50% less. Gemini 4 Argon's price changes on Dec 1, 2026 to $4.00 input and $20.00 output per million tokens.
Same cost for this workload. Excludes cache writes, tools and taxes.
| Price | GPT-6.1 Sol | Gemini 4 Argon |
|---|---|---|
| Model ID | gpt-6.1-sol | gemini-4-argon |
| Input | $2.00 | $2.00 |
| Cache read | $0.10 | $0.10 |
| Cache write | $2.50 | Storage billed per hour |
| Output | $10.00 | $10.00 |
| Batch in / out | $1.00 / $5.00 | $1.00 / $5.00 |
| Long prompts | Over 272,000: $4.00 / $15.00 | Same rate |
| Scheduled change | None announced | From Dec 1, 2026: $4.00 / $20.00 |
| Status | Available | Paid tier only |
Prices for each provider’s own API, from OpenAI’s pricing page and Google Gemini’s pricing page. The lower price in each row is highlighted. Ganivra uses these same rates to price GPT-6.1 Sol and Gemini 4 Argon calls.
Worked out from the prices above at standard rates, with no Batch discount. Long-prompt rates apply where a model has them.
| Request | GPT-6.1 Sol | Gemini 4 Argon | Per 1,000 requests | Difference |
|---|---|---|---|---|
| Chat reply3,000 input tokens, 500 output | $0.011 | $0.011 | $11.00 / $11.00 | Same cost |
| Document summary30,000 input tokens, 1,500 output | $0.075 | $0.075 | $75.00 / $75.00 | Same cost |
| Agent task80,000 input tokens (60,000 cached), 6,000 output | $0.106 | $0.106 | $106 / $106 | Same cost |
| Long document300,000 input tokens, 2,000 output | $1.23 | $0.620 | $1,230 / $620 | Gemini 4 Argon costs 50% less |
Ganivra prices every GPT-6.1 Sol 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.
Per token, they cost the same. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), they cost the same: $106 against $106 per 1,000 tasks. But for a long document (300,000 input tokens, 2,000 output), Gemini 4 Argon costs 50% less.
$2.00 input and $10.00 output per million tokens on OpenAI's API, with cached input at $0.10 and Batch at $1.00 input and $5.00 output. Prompts over 272,000 tokens cost $4.00 input and $15.00 output.
$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.
For a 300,000 input tokens, 2,000 output request, GPT-6.1 Sol costs $1.23 and Gemini 4 Argon $0.620: Gemini 4 Argon costs 50% less. On GPT-6.1 Sol, prompts over 272,000 tokens cost $4.00 input and $15.00 output for the whole request; on Gemini 4 Argon, one rate at any prompt length.
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 $0.106 on GPT-6.1 Sol.
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 GPT-6.1 Sol and on Gemini 4 Argon, next to what each customer pays you.
Every model on one page: GPT-6.1 Sol pricing · Gemini 4 Argon pricing · all model price comparisons · all supported models.