Daily blended price ($/1M) — recorded each day, builds into a trend over time.
Typical 3:1 output-to-input mix, per 1M tokens
Price as of 2026-04-28 · Source: legacy_model_catalog
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizin...
deepseek-v3.1-terminus is a Text model from DeepSeek (CN). HotON.ai tracks it at $0.21 per 1M input tokens and $0.79 per 1M output tokens, with a 164K-token context window. Its composite efficiency score is 89/100 at an estimated $0.001 per successful task.
deepseek-v3.1-terminus is tracked at $0.21 per 1M input tokens and $0.79 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.65 per 1M tokens. Figures are illustrative demo data.
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
deepseek-v3.1-terminus supports up to a 164K-token context window — large enough for long documents and extended conversations in a single request.
Within the HotON.ai tracked set, deepseek-v3.1-terminus is cheaper than 61% of models on input price and ranks #158 of 521 by overall efficiency.
Yes — deepseek/deepseek-v4-flash is a lower-cost option at $0.28 per 1M output tokens, while still covering similar Text use cases. Compare them side by side on HotON.ai.
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.