BroadRouter

GPT-6.1 Sol vs GPT-6.1 Terra API pricing

Updated

GPT-6.1 Sol: USD 2 input, USD 10 output per 1M tokens (OpenAI and 4 others). GPT-6.1 Terra: USD 1 input, USD 5 output per 1M tokens (OpenAI and 2 others). At 3 input tokens per output token, GPT-6.1 Sol costs 2× as much as GPT-6.1 Terra (USD 4 vs USD 2 per 1M).

GPT-6.1 Sol and GPT-6.1 Terra are neighbouring tiers of one OpenAI generation (Sol and Terra, by name), so this page shows what the step up costs. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do GPT-6.1 Sol and GPT-6.1 Terra differ on price?

GPT-6.1 Sol and GPT-6.1 Terra prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

GPT-6.1 Sol and GPT-6.1 Terra API prices compared
PriceGPT-6.1 SolGPT-6.1 Terra
Model pageGPT-6.1 Sol
OpenAI · 6 providers
GPT-6.1 Terra
OpenAI · 4 providers
Cheapest standard price, blended 3:1USD 4
USD 2 in / USD 10 out at OpenAI and 4 others
OpenAI page checked 2026-11-14
USD 2 lower
USD 1 in / USD 5 out at OpenAI and 2 others
OpenAI page checked 2026-11-14
Cheapest inputUSD 2
OpenAI source
USD 1 lower
OpenAI source
Cheapest cached inputUSD 0.10
OpenAI source
USD 0.05 lower
OpenAI source
Cheapest outputUSD 10
OpenAI source
USD 5 lower
OpenAI source
Maker's own APIUSD 2 / USD 10
OpenAI source
USD 1 / USD 5
OpenAI source
Median standard priceUSD 2 / USD 10
input / output, 6 prices
USD 1 / USD 5
input / output, 4 prices
Context window1,050,000 tokens, largest stated1,050,000 tokens, largest stated
Providers with a standard price64

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do GPT-6.1 Sol and GPT-6.1 Terra cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on GPT-6.1 Sol and GPT-6.1 Terra
WorkloadGPT-6.1 SolGPT-6.1 TerraDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 257.40
OpenAI
USD 128.70
OpenAI
USD 128.70
GPT-6.1 Terra lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 493.20
OpenAI
USD 246.60
OpenAI
USD 246.60
GPT-6.1 Terra lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 1,593
OpenAI
USD 796.50
OpenAI
USD 796.50
GPT-6.1 Terra lower

GPT-6.1 Terra is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 2× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

GPT-6.1 Terra is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below GPT-6.1 Sol's, so the input:output ratio never changes the answer.

Price per 1M tokens of GPT-6.1 Sol and GPT-6.1 Terra at different input:output mixes
Input : output tokensGPT-6.1 SolGPT-6.1 Terra
1 : 3 (long answers)USD 8
OpenAI
USD 4 lower
OpenAI
1 : 1USD 6
OpenAI
USD 3 lower
OpenAI
3 : 1 (the site’s blend)USD 4
OpenAI
USD 2 lower
OpenAI
10 : 1 (retrieval, long prompts)USD 2.727
OpenAI
USD 1.364 lower
OpenAI
30 : 1 (agents, big contexts)USD 2.258
OpenAI
USD 1.129 lower
OpenAI

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do GPT-6.1 Sol and GPT-6.1 Terra cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and GPT-6.1 Sol and GPT-6.1 Terra are not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: GPT-6.1 Sol vs GPT-6 Sol · GPT-6.1 Terra vs Gemini 4 Hydrogen · GPT-6.1 Terra vs GPT-5.6 Terra · every GPT-6.1 Sol comparison · every GPT-6.1 Terra comparison · all 662 price comparisons

Questions

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

No. On a blend of 3 input tokens to 1 output token, GPT-6.1 Terra costs USD 2 per 1M tokens and GPT-6.1 Sol USD 4, at each model's cheapest standard price. For input alone, GPT-6.1 Terra is cheaper (USD 1 against USD 2 per 1M); for output alone, GPT-6.1 Terra is (USD 5 against USD 10). This compares price only, not quality.

What do GPT-6.1 Sol and GPT-6.1 Terra cost per 1M tokens?

GPT-6.1 Sol: from USD 2 input and USD 10 output at OpenAI and 4 others; OpenAI's own API charges USD 2 / USD 10; median of 6 standard prices USD 2 / USD 10. GPT-6.1 Terra: from USD 1 input and USD 5 output at OpenAI and 2 others; OpenAI's own API charges USD 1 / USD 5; median of 4 standard prices USD 1 / USD 5. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both GPT-6.1 Sol and GPT-6.1 Terra?

4 providers have a standard price for both: DigitalOcean (USD 4 and USD 2 at 3:1), Microsoft Azure (USD 4 and USD 2 at 3:1), OpenAI (USD 4 and USD 2 at 3:1), Amazon Bedrock (USD 4.40 and USD 2.20 at 3:1). The first 3 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 4 and USD 2.

Which is cheaper for a coding agent or a chatbot, GPT-6.1 Sol or GPT-6.1 Terra?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 1,593 a month on GPT-6.1 Sol (OpenAI) against USD 796.50 on GPT-6.1 Terra (OpenAI), a difference of USD 796.50. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 257.40 a month on GPT-6.1 Sol (OpenAI) against USD 128.70 on GPT-6.1 Terra (OpenAI), a difference of USD 128.70. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of GPT-6.1 Sol and GPT-6.1 Terra change?

GPT-6.1 Terra is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below GPT-6.1 Sol's, so the input:output ratio never changes the answer.

Do GPT-6.1 Sol and GPT-6.1 Terra have cached input pricing?

GPT-6.1 Sol from USD 0.10 per 1M cached input tokens (OpenAI; 6 of 6 standard prices list a discount). GPT-6.1 Terra from USD 0.05 per 1M cached input tokens (OpenAI; 4 of 4 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, GPT-6.1 Sol or GPT-6.1 Terra?

Both go up to 1,050,000 tokens on the providers that state it.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity