Compare DeepSeek: R1 (DeepSeek) and DeepSeek: DeepSeek V3.1 Terminus (DeepSeek) by price, context, capabilities, and latency.
Side by side
Compare price, provider, context, capabilities, latency, and source basis.
| Model | Provider | Input | Output | Context | Capabilities | Best for | Latency | Status | Source |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek: R1deepseek/deepseek-r1 | DeepSeek | $0.132 / 1M tokens | $0.47 / 1M tokens | 163.8k | StreamingTool callingJSON modeLong context | Chinese Q&A, general chat | 1000-3000ms | Catalog | Platform curated |
| DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus | DeepSeek | $0.052 / 1M tokens | $0.179 / 1M tokens | 163.8k | StreamingTool callingJSON modeLong context | Chinese Q&A, general chat | 1000-3000ms | Catalog | Platform curated |
FAQ
DeepSeek: DeepSeek V3.1 Terminus is cheaper ($0.052 / 1M tokens input / $0.179 / 1M tokens output) vs DeepSeek: R1 ($0.132 / 1M tokens input / $0.47 / 1M tokens output). Actual cost depends on your input/output token mix — estimate it with the pricing calculator.
Both offer the same context window: 163.8k tokens.
Both target Long context. Pick DeepSeek: DeepSeek V3.1 Terminus to optimize cost, or DeepSeek: R1 for the longer context window. Test both on real prompts before committing production traffic.