Sponsored
Advertise to people comparing AI plans. Sponsor slots openReach buyers deciding between ChatGPT, Claude, Cursor and moreOne sponsor per slot. Pricing on request
LimitDigest
Home / Compare / AI models / GPT-6.1 Terra vs Gemini 3.8 Flash

GPT-6.1 Terra vs Gemini 3.8 Flash

Official OpenAI and Google API prices and LMArena scores, checked 2026-10-29. Add up to 2 more models to compare 4.

Verdict

Gemini 3.8 Flash costs less; GPT-6.1 Terra wins more LMArena tasks.

Gemini 3.8 Flash is 1.3x cheaper on input and output. GPT-6.1 Terra scores 33 points higher for coding. Across 1 shared LMArena task, GPT-6.1 Terra leads 1 to 0. A medium month (20M input + 5M output tokens) costs $45 on GPT-6.1 Terra and $33.75 on Gemini 3.8 Flash.

  • Pick GPT-6.1 Terra if you care most about coding (+33) or you reuse long prompts (cached input $0.05 vs $0.075).
  • Pick Gemini 3.8 Flash if you want the lower bill ($33.75 vs $45 for a medium month).
Sample month

Medium: 20M input + 5M output tokens a month at list price (short-context rate, no caching or batch discounts).

GPT-6.1 TerravsGemini 3.8 Flash
Price per 1M tokens
Input$1$0.75 (better)
Cached input$0.05 (better)$0.075
Output$5$3.75 (better)
Sample month, medium$45$33.75 (better)
Context
Context window1.05M (better)1M
Quality (LMArena relative score, out of 100)
Coding49 (better)16
Chatn/a54
Creative writingn/a56
Roleplay and charactersn/a46
Reasoning and mathn/a85
Visionn/a80
Long documentsn/an/a
Cheap bulk and agentsn/a52

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 Terra
Gemini 3.8 Flash
Price per 1M tokens
Input$1$0.75
Cached input$0.05$0.075
Output$5$3.75
Blend 3:1$2$1.50
Sample month, medium$45$33.75
Context
Context window1.05M tokens1M tokens
Quality (LMArena, out of 100)
Coding49/100 #11 of 5016/100 #25 of 50
ChatNot ranked54/100 #5 of 51
Creative writingNot ranked56/100 #5 of 51
Roleplay and charactersNot ranked46/100 #3 of 51
Reasoning and mathNot ranked85/100 #3 of 51
VisionNot ranked80/100 #4 of 33
Long documentsNot rankedNot ranked
Cheap bulk and agentsNot ranked52/100 #12 of 34
Details
ProviderOpenAIGoogle
API model idgpt-6.1-terragemini-3.8-flash
NotesNew Oct 26, 2026. Prompts up to 272K. Longer prompts cost $2 in, $7.50 out.Through Dec 31, 2026. From Jan 1, 2027: $1.50 in, $7.50 out.
Sources
Last checked2026-10-292026-10-29
Official pricingOpenAI pricingGoogle pricing

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 Terra #11 of 50 (49/100), Gemini 3.8 Flash #25 of 50 (16/100)
  • Chat (Text Arena): GPT-6.1 Terra not ranked, Gemini 3.8 Flash #5 of 51 (54/100)
  • Creative writing (Text Arena creative writing): GPT-6.1 Terra not ranked, Gemini 3.8 Flash #5 of 51 (56/100)
  • Roleplay and characters (Text Arena multi-turn): GPT-6.1 Terra not ranked, Gemini 3.8 Flash #3 of 51 (46/100)
  • Reasoning and math (Text Arena math): GPT-6.1 Terra not ranked, Gemini 3.8 Flash #3 of 51 (85/100)
  • Vision (Vision Arena): GPT-6.1 Terra not ranked, Gemini 3.8 Flash #4 of 33 (80/100)
  • Long documents (Document Arena): GPT-6.1 Terra not ranked, Gemini 3.8 Flash not ranked
  • Cheap bulk and agents (Agent Arena): GPT-6.1 Terra not ranked, Gemini 3.8 Flash #12 of 34 (52/100)

Pricing details from the official pages

GPT-6.1 Terra lists $1 input, $5 output, $0.05 cached input per 1M tokens on OpenAI pricing. Gemini 3.8 Flash lists $0.75 input, $3.75 output, $0.075 cached input per 1M tokens on Google pricing. Prices checked 2026-10-29.

  • GPT-6.1 Terra: New Oct 26, 2026. Prompts up to 272K. Longer prompts cost $2 in, $7.50 out.
  • Gemini 3.8 Flash: Through Dec 31, 2026. From Jan 1, 2027: $1.50 in, $7.50 out.

Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $4.50 vs $3.38. Medium (20M input + 5M output tokens): $45 vs $33.75. Heavy (200M input + 50M output tokens): $450 vs $337.50.

FAQ

Is GPT-6.1 Terra cheaper than Gemini 3.8 Flash?

GPT-6.1 Terra costs $1 input and $5 output per 1M tokens; Gemini 3.8 Flash costs $0.75 and $3.75. For a medium month (20M input + 5M output tokens) Gemini 3.8 Flash is cheaper: $33.75 vs $45.

Which is better for coding, GPT-6.1 Terra or Gemini 3.8 Flash?

On LMArena's Code Arena GPT-6.1 Terra scores 49/100 (#11 of 50) and Gemini 3.8 Flash 16/100 (#25 of 50), so GPT-6.1 Terra is ahead by 33 points.

Which has the bigger context window?

GPT-6.1 Terra: 1.05M tokens. Gemini 3.8 Flash: 1M tokens. Long prompts can cost more; see the pricing notes above.

How much do GPT-6.1 Terra and Gemini 3.8 Flash cost per month?

Light (2M input + 0.5M output tokens): $4.50 vs $3.38. Medium (20M input + 5M output tokens): $45 vs $33.75. Heavy (200M input + 50M output tokens): $450 vs $337.50. 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