API price comparison · Updated
Claude Sonnet 5.5 costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-6.1 Sol 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), Claude Sonnet 5.5 costs $0.106 and GPT-6.1 Sol $0.106: they cost the same. But for a long document (300,000 input tokens, 2,000 output), Claude Sonnet 5.5 costs 50% less.
Same cost for this workload. Excludes cache writes, tools and taxes.
| Price | Claude Sonnet 5.5 | GPT-6.1 Sol |
|---|---|---|
| Model ID | claude-sonnet-5-5 | gpt-6.1-sol |
| Input | $2.00 | $2.00 |
| Cache read | $0.10 | $0.10 |
| Cache write | $2.50 | $2.50 |
| Output | $10.00 | $10.00 |
| Batch in / out | $1.00 / $5.00 | $1.00 / $5.00 |
| Long prompts | Same rate | Over 272,000: $4.00 / $15.00 |
| Scheduled change | None announced | None announced |
| Status | Available | Available |
Prices for each provider’s own API, from Anthropic’s pricing page and OpenAI’s pricing page. The lower price in each row is highlighted. Ganivra uses these same rates to price Claude Sonnet 5.5 and GPT-6.1 Sol calls.
Worked out from the prices above at standard rates, with no Batch discount. Long-prompt rates apply where a model has them.
| Request | Claude Sonnet 5.5 | GPT-6.1 Sol | 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 | $0.620 | $1.23 | $620 / $1,230 | Claude Sonnet 5.5 costs 50% less |
Ganivra prices every Claude Sonnet 5.5 and GPT-6.1 Sol 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), Claude Sonnet 5.5 costs 50% less.
$2.00 input and $10.00 output per million tokens on Anthropic'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.
$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.
For a 300,000 input tokens, 2,000 output request, Claude Sonnet 5.5 costs $0.620 and GPT-6.1 Sol $1.23: Claude Sonnet 5.5 costs 50% less. On Claude Sonnet 5.5, one rate at any prompt length; on GPT-6.1 Sol, prompts over 272,000 tokens cost $4.00 input and $15.00 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 Claude Sonnet 5.5 and on GPT-6.1 Sol, next to what each customer pays you.
Every model on one page: Claude Sonnet 5.5 pricing · GPT-6.1 Sol pricing · all model price comparisons · all supported models.