GPT-6.1 Sol vs GPT-6.1 Terra
Official OpenAI API prices and LMArena scores, checked 2026-10-29. Add up to 2 more models to compare 4.
GPT-6.1 Terra costs less; GPT-6.1 Sol wins more LMArena tasks.
GPT-6.1 Terra is 2x cheaper on input and output. GPT-6.1 Sol scores 29 points higher for coding. Across 1 shared LMArena task, GPT-6.1 Sol leads 1 to 0. A medium month (20M input + 5M output tokens) costs $90 on GPT-6.1 Sol and $45 on GPT-6.1 Terra.
- Pick GPT-6.1 Sol if you care most about coding (+29).
- Pick GPT-6.1 Terra if you want the lower bill ($45 vs $90 for a medium month) or you reuse long prompts (cached input $0.05 vs $0.10).
Medium: 20M input + 5M output tokens a month at list price (short-context rate, no caching or batch discounts).
Marked side is better: lower for prices, higher for context and scores. Bars are scaled to the larger of the two.
| Spec | GPT-6.1 Sol | GPT-6.1 Terra |
|---|---|---|
| Price per 1M tokens | ||
| Input | $2 | $1 |
| Cached input | $0.10 | $0.05 |
| Output | $10 | $5 |
| Blend 3:1 | $4 | $2 |
| Sample month, medium | $90 | $45 |
| Context | ||
| Context window | 1.05M tokens | 1.05M tokens |
| Quality (LMArena, out of 100) | ||
| Coding | 78/100 #4 of 50 | 49/100 #11 of 50 |
| Chat | 26/100 #13 of 51 | Not ranked |
| Creative writing | 11/100 #14 of 51 | Not ranked |
| Roleplay and characters | 4/100 #14 of 51 | Not ranked |
| Reasoning and math | 59/100 #6 of 51 | Not ranked |
| Vision | 85/100 #2 of 33 | Not ranked |
| Long documents | Not ranked | Not ranked |
| Cheap bulk and agents | 78/100 #5 of 34 | Not ranked |
| Details | ||
| Provider | OpenAI | OpenAI |
| API model id | gpt-6.1-sol | gpt-6.1-terra |
| Notes | Prompts up to 272K. Longer prompts cost $4 in, $15 out. | New Oct 26, 2026. Prompts up to 272K. Longer prompts cost $2 in, $7.50 out. |
| Sources | ||
| Last checked | 2026-10-29 | 2026-10-29 |
| Official pricing | OpenAI pricing | OpenAI pricing |
Plans from data checked hourly against each vendor's official pricing page. Vendors state limits in different units, so we quote them as published. Team and enterprise plans are per seat.
API prices in USD per 1M tokens from each provider's official pricing page. Blend 3:1 = (3 x input + output) / 4. Sample month = stated input and output tokens at the list price, no caching. Quality: relative score out of 100 on each LMArena leaderboard (100 = top model we price on that board, n/a = not ranked there), data licensed CC BY 4.0. See how we pick.
Where each one ranks on LMArena
Relative score out of 100 on each leaderboard (100 = the top model we price there), with the rank among the models from our API price table that appear on that board.
- Coding (Code Arena): GPT-6.1 Sol #4 of 50 (78/100), GPT-6.1 Terra #11 of 50 (49/100)
- Chat (Text Arena): GPT-6.1 Sol #13 of 51 (26/100), GPT-6.1 Terra not ranked
- Creative writing (Text Arena creative writing): GPT-6.1 Sol #14 of 51 (11/100), GPT-6.1 Terra not ranked
- Roleplay and characters (Text Arena multi-turn): GPT-6.1 Sol #14 of 51 (4/100), GPT-6.1 Terra not ranked
- Reasoning and math (Text Arena math): GPT-6.1 Sol #6 of 51 (59/100), GPT-6.1 Terra not ranked
- Vision (Vision Arena): GPT-6.1 Sol #2 of 33 (85/100), GPT-6.1 Terra not ranked
- Long documents (Document Arena): GPT-6.1 Sol not ranked, GPT-6.1 Terra not ranked
- Cheap bulk and agents (Agent Arena): GPT-6.1 Sol #5 of 34 (78/100), GPT-6.1 Terra not ranked
Pricing details from the official pages
GPT-6.1 Sol lists $2 input, $10 output, $0.10 cached input per 1M tokens on OpenAI pricing. GPT-6.1 Terra lists $1 input, $5 output, $0.05 cached input per 1M tokens on OpenAI pricing. Prices checked 2026-10-29.
- GPT-6.1 Sol: Prompts up to 272K. Longer prompts cost $4 in, $15 out.
- GPT-6.1 Terra: New Oct 26, 2026. Prompts up to 272K. Longer prompts cost $2 in, $7.50 out.
Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $9 vs $4.50. Medium (20M input + 5M output tokens): $90 vs $45. Heavy (200M input + 50M output tokens): $900 vs $450.
FAQ
Is GPT-6.1 Sol cheaper than GPT-6.1 Terra?
GPT-6.1 Sol costs $2 input and $10 output per 1M tokens; GPT-6.1 Terra costs $1 and $5. For a medium month (20M input + 5M output tokens) GPT-6.1 Terra is cheaper: $45 vs $90.
Which is better for coding, GPT-6.1 Sol or GPT-6.1 Terra?
On LMArena's Code Arena GPT-6.1 Sol scores 78/100 (#4 of 50) and GPT-6.1 Terra 49/100 (#11 of 50), so GPT-6.1 Sol is ahead by 29 points.
Which has the bigger context window?
GPT-6.1 Sol: 1.05M tokens. GPT-6.1 Terra: 1.05M tokens. Both list the same window. Long prompts can cost more; see the pricing notes above.
How much do GPT-6.1 Sol and GPT-6.1 Terra cost per month?
Light (2M input + 0.5M output tokens): $9 vs $4.50. Medium (20M input + 5M output tokens): $90 vs $45. Heavy (200M input + 50M output tokens): $900 vs $450. Pick your own token counts in the plan vs API calculator.
Where do these numbers come from?
Prices come from each provider's official pricing page, checked daily. Quality is the relative score on the LMArena leaderboard dataset, licensed CC BY 4.0. Where a model is not ranked we show n/a.
Sources
Related
- GPT-6 Astra vs GPT-6.1 Sol: cost and Codex limits
- OpenAI API pricing, every model
- GPT-6.1 Sol vs Claude Opus 5.5
- GPT-6.1 Sol vs Gemini 4 Argon
- GPT-6.1 Sol vs Claude Sonnet 5.5
- DeepSeek V4 Pro vs GPT-6.1 Sol
- Grok 4.7 vs GPT-6.1 Sol
- Muse Wonder 1.0 vs GPT-6.1 Sol
- GPT-6.1 Terra vs Claude Opus 5.5
- GPT-6.1 Terra vs Claude Sonnet 5.5