LLM Comparison
Trinity Large Thinking vs DeepSeek V3.1 Terminus
Side-by-side specs, pricing & capabilities · Updated April 2026
Add to comparison
2/6 modelsSame tier:
T Trinity Large Thinking | D DeepSeek V3.1 Terminus | |
|---|---|---|
| Organization | Arcee AI | DeepSeek |
| OpenTools Score | 64 128 | |
| Family | Trinity | DeepSeek |
| Status | Current | Current |
| Release Date | Apr 2026 | Sep 2025 |
| Context Window | 262K tokens | 164K tokens |
| Input Price | $0.22/M tokens | $0.21/M tokens |
| Output Price | $0.85/M tokens | $0.79/M tokens |
| Pricing Notes | Cache read: $0.0600/M tokens | Cache read: $0.1300/M tokens |
| Capabilities | textcodeextended-thinking | textcode |
| Max Output | 262K tokens | — |
| API Identifier | arcee-ai/trinity-large-thinking | deepseek/deepseek-v3.1-terminus |
| Benchmarks | ||
| MMLU | — | 87.1 |
| HumanEval | — | 89.2 |
| MATH | — | 90.2 |
| View Trinity Large Thinking | View DeepSeek V3.1 Terminus | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| DeepSeek V3.1 TerminusCheapest | $0.21 | $0.40 | $0.61 | — |
| Trinity Large Thinking | $0.22 | $0.43 | $0.65 | +7% |
Arcee AI
Trinity Large Thinking
Trinity Large Thinking is a large language model from Arcee AI. Supports up to 262,144 token context window. Available from $0.22/M input tokens.
DeepSeek
DeepSeek V3.1 Terminus
DeepSeek V3.1 Terminus is a large language model from DeepSeek. Supports up to 163,840 token context window. Achieves 87.1% on MMLU. Available from $0.21/M input tokens.
More Comparisons
Looking for more AI models?
Browse All LLMs