By the toolist.ai editors. Researched from public sources, not hands-on tested by toolist.ai. Updated October 27, 2026; prices checked October 21, 2026.

GPT-6.1 Terra vs GPT-6.1 Sol

Verdict

Pick GPT-6.1 Terra when price and speed matter most, and GPT-6.1 Sol when answer quality matters more. Terra costs half as much per token ($1 and $5 per million against $2 and $10) and produces about one and a half times as many output tokens a second on Artificial Analysis (91.0 against 58.9, both at medium effort). Sol scores higher: 55 against 51 on the Intelligence Index at max effort, and 46 against 38 at medium, the API default for both.

Verdict based on published prices, limits and benchmarks, not on our own tests.

Choose GPT-6.1 Terra if

  • Cost matters most: Terra's $1 and $5 per million tokens against Sol's $2 and $10
  • You build visual or computer-use work, which OpenAI says Terra is built for: product photos, technical drawings and application screens
  • You want speed: 91.0 against 58.9 output tokens a second at medium effort

Choose GPT-6.1 Sol if

  • You want the higher score at the default effort: 46 against 38 on the Intelligence Index at medium
  • You want the higher score at max effort too: 55 against 51
  • You run hard, long agent work where the score gap matters more than the price gap

Price

Input costs 2 times as much on GPT-6.1 Sol as on GPT-6.1 Terra. Output costs 2 times as much on GPT-6.1 Sol as on GPT-6.1 Terra.

Per million tokensGPT-6.1 TerraGPT-6.1 Sol
Input$1 source$2 source
Cached input$0.05 source$0.10 source
Output$5 source$10 source

GPT-6.1 Terra: Prompts over 272,000 input tokens cost twice the input and cache rates and 1.5 times the output rate for the whole request. Batch and Flex cost half; Fast mode costs double. Cache writes cost $1.25 per million tokens with 30-minute retention and $2.50 with 12-hour retention.

GPT-6.1 Sol: Prompts over 272,000 input tokens are billed at twice the input rate and 1.5 times the output rate for the whole request. Batch and Flex processing cost half; Fast mode costs double and Ultrafast six times.

Worked example: what a month costs

We priced three monthly workloads at the standard rates. The provider does not publish these figures.

WorkloadGPT-6.1 TerraGPT-6.1 Sol
Support chatbot
100,000 replies, each 3,000 input and 400 output tokens, no caching (300M in, 40M out)		 $500$1,000
Document Q&A
5,000 questions over the same 60,000-token document set (90% cache hits), 800 output tokens each (300M in, 4M out)		 $63.50$127
Coding agent
200 tasks, each 1.5 million input tokens (90% cache hits) and 50,000 output tokens (300M in, 10M out)		 $93.50$187

Price your own workload

ModelCost a month
GPT-6.1 Terra $75.00
GPT-6.1 Sol $150

Standard API prices, no batch or priority discounts. Cached input is billed at the cache-read price; cache-write charges are not included. Reasoning models bill their thinking as output tokens.

Limits and release dates

GPT-6.1 TerraGPT-6.1 Sol
ReleasedOctober 26, 2026 sourceSeptember 29, 2026 source
Context window1,050,000 tokens source1,050,000 tokens source
Maximum output128,000 tokens source128,000 tokens source
Knowledge cutoffJune 1, 2026 sourceApril 30, 2026 source
Input and outputText and images in; text out sourceText and images in; text out source
API model namegpt-6.1-terragpt-6.1-sol

Benchmarks

Scores as published by the provider or measured by Artificial Analysis; higher is better. A dash means no score was published.

BenchmarkGPT-6.1 TerraGPT-6.1 Sol
Artificial Analysis Intelligence Index
max effort		 51.0 source55.0 source
Intelligence Index at everyday effort
medium effort, the API default		 38.0 source46.0 source
Terminal-Bench 4.0 –56.0% (max effort) source
HLE-Diamond –59.0% (max effort) source
Terminal-Bench-Science 0.1 –58.0% (max effort) source
Output speed 91 tokens/s (medium effort, Artificial Analysis) source58.9 tokens/s (medium effort, Artificial Analysis) source

Benchmark and speed data from Artificial Analysis where linked.

Read more

Sources