GVGanivra

API price comparison · Updated

GPT-6.1 Sol vs GPT-6.1 Terra pricing

Quick answer

GPT-6.1 Sol costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-6.1 Terra costs $1.00 and $5.00. 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 GPT-6.1 Terra $0.053: GPT-6.1 Sol costs 2× as much.

Compare your monthly cost on GPT-6.1 Sol and GPT-6.1 Terra

Estimated monthly cost
GPT-6.1 Sol$1,100$0.011 per request
GPT-6.1 Terra$550$0.0055 per request

GPT-6.1 Terra costs 50% less for this workload. Excludes cache writes, tools and taxes.

GPT-6.1 Sol vs GPT-6.1 Terra prices per million tokens

PriceGPT-6.1 SolGPT-6.1 Terra
Model IDgpt-6.1-solgpt-6.1-terra
Input$2.00$1.00
Cache read$0.10$0.05
Cache write$2.50$1.25
Output$10.00$5.00
Batch in / out$1.00 / $5.00$0.50 / $2.50
Long promptsOver 272,000: $4.00 / $15.00Over 272,000: $2.00 / $7.50
Scheduled changeNone announcedNone announced
StatusAvailableAvailable

Prices for each provider’s own API, from OpenAI’s pricing page. The lower price in each row is highlighted. Ganivra uses these same rates to price GPT-6.1 Sol and GPT-6.1 Terra calls.

What one request costs on GPT-6.1 Sol and GPT-6.1 Terra

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

RequestGPT-6.1 SolGPT-6.1 TerraPer 1,000 requestsDifference
Chat reply3,000 input tokens, 500 output$0.011$0.0055$11.00 / $5.50GPT-6.1 Sol costs 2× as much
Document summary30,000 input tokens, 1,500 output$0.075$0.037$75.00 / $37.50GPT-6.1 Sol costs 2× as much
Agent task80,000 input tokens (60,000 cached), 6,000 output$0.106$0.053$106 / $53.00GPT-6.1 Sol costs 2× as much
Long document300,000 input tokens, 2,000 output$1.23$0.615$1,230 / $615GPT-6.1 Sol costs 2× as much

What changes which one costs less

Prompt caching
Cache reads cost $0.10 per million, 5% of the input price on GPT-6.1 Sol, and $0.05 per million, 5% of the input price on GPT-6.1 Terra. The more of each prompt you reuse, the more this decides the bill.
Cache writes
GPT-6.1 Sol charges $2.50 per million tokens written to cache. GPT-6.1 Terra charges $1.25 per million tokens written to cache.
Long prompts
On GPT-6.1 Sol, prompts over 272,000 tokens cost $4.00 input and $15.00 output for the whole request. On GPT-6.1 Terra, prompts over 272,000 tokens cost $2.00 input and $7.50 output for the whole request. A 300 prompt costs $1.23 on GPT-6.1 Sol and $0.615 on GPT-6.1 Terra.
Batch API
GPT-6.1 Sol costs 50% less through the Batch API: $1.00 input and $5.00 output. GPT-6.1 Terra costs 50% less through the Batch API: $0.50 input and $2.50 output.
Quality and retries
Price is half the decision. A cheaper model that needs more retries, longer prompts or a human fix can cost more per finished task.

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

Ganivra prices every GPT-6.1 Sol and GPT-6.1 Terra 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

GPT-6.1 Sol vs GPT-6.1 Terra pricing questions

Is GPT-6.1 Sol cheaper than GPT-6.1 Terra?

Per million tokens, GPT-6.1 Sol costs $2.00 input and $10.00 output, and GPT-6.1 Terra $1.00 input and $5.00 output. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), GPT-6.1 Sol costs 2× as much: $106 against $53.00 per 1,000 tasks.

How much does GPT-6.1 Sol cost per million tokens?

$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.

How much does GPT-6.1 Terra cost per million tokens?

$1.00 input and $5.00 output per million tokens on OpenAI's API, with cached input at $0.05 and Batch at $0.50 input and $2.50 output. Prompts over 272,000 tokens cost $2.00 input and $7.50 output.

Which is cheaper for long prompts, GPT-6.1 Sol or GPT-6.1 Terra?

For a 300,000 input tokens, 2,000 output request, GPT-6.1 Sol costs $1.23 and GPT-6.1 Terra $0.615: GPT-6.1 Sol costs 2× as much. On GPT-6.1 Sol, prompts over 272,000 tokens cost $4.00 input and $15.00 output for the whole request; on GPT-6.1 Terra, prompts over 272,000 tokens cost $2.00 input and $7.50 output for the whole request.

How do I compare GPT-6.1 Sol and GPT-6.1 Terra 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 GPT-6.1 Sol and on GPT-6.1 Terra, next to what each customer pays you.

Every model on one page: GPT-6.1 Sol pricing · all model price comparisons · all supported models.