gpt-6.1-terra vs Gemini 3.8 Flash
Gemini 3.8 Flash is 1.3× cheaper: $1.50 per million tokens blended, against $2.00 for gpt-6.1-terra. On the Vals Index v2.2, gpt-6.1-terra scores 60.54% and Gemini 3.8 Flash 55.95%, so gpt-6.1-terra leads.
Price
| Per million tokens | gpt-6.1-terra | Gemini 3.8 Flash |
|---|---|---|
| Maker | OpenAI | |
| Input | $1.00 | $0.75 |
| Output | $5.00 | $3.75 |
| Cache read | $0.05 | $0.075 |
| Blended (3:1) | $2.00 | $1.50 |
| Context window | 1,050K | n/a |
| Output speed | 91 tokens/s | 137 tokens/s |
| Status | Available | Available |
Sources
OpenAI: official API pricing, read 2026-11-20
Google: Gemini API pricing, read 2026-11-20
Benchmarks
| Benchmark | gpt-6.1-terra | Gemini 3.8 Flash |
|---|---|---|
| Vals Index v2.2 Vals AI | 60.54% | 55.95% |
| Artificial Analysis Intelligence Index Artificial Analysis | 51max | 31high |
| Epoch Capabilities Index Epoch AI | 167.7 | 158.8 |
| Arena Text Arena | 1474Max | 1497High |
| Terminal-Bench 4.0 Vals AI | 49.49% | 19.70% |
| SWE-bench Verified Vals AI | not scored | 80.00% |
| GPQA Diamond Vals AI | not scored | 94.44% |