DeepSeek V3.1 Terminus
Open-weights frontier model that matched GPT-4-class quality at a fraction of the inference cost. Sparked the late-2024 cost reset.
DeepSeek V3.1 Terminus is a efficient AI model from DeepSeek. It costs $0.270 per million input tokens and $1.000 per million output tokens (blended $0.489/M), with a 163,840-token context window.
Profile inherited from upstream DeepSeek-V3 ↗ — this is a hosted variant of the same open-weights model.
+7.6%over 91 days · hover to read
- Frontier quality, open weights
- Aggressive pricing
- Strong code & math
- MoE architecture
- Self-hosted frontier inference
- Cost-sensitive chat
- Code generation
Benchmarks
More from DeepSeek
See all 11 →Price history
6 recorded changes| Date | Rate | Was | Now | Change |
|---|---|---|---|---|
| 29 Sept 2026 | Input | $0.270 | $0.300 | +11% |
| 21 Aug 2026 | Output | $0.950 | $1.000 | +5.3% |
| 12 Aug 2026 | Output | $1.000 | $0.950 | -5% |
| 16 Jul 2026 | Output | $0.950 | $1.000 | +5.3% |
| 4 May 2026 | Input | $0.210 | $0.270 | +29% |
| 4 May 2026 | Output | $0.790 | $0.950 | +20% |
Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.
Frequently asked questions
How much does DeepSeek V3.1 Terminus cost?
DeepSeek V3.1 Terminus costs $0.270 per million input tokens and $1.000 per million output tokens, for a blended reference rate of $0.489 per million tokens.
What is DeepSeek V3.1 Terminus's context window?
DeepSeek V3.1 Terminus supports up to 163,840 tokens of context in a single request.
What is DeepSeek V3.1 Terminus best for?
DeepSeek V3.1 Terminus is well suited to Frontier quality, open weights, Aggressive pricing and Strong code & math.
Who makes DeepSeek V3.1 Terminus?
DeepSeek V3.1 Terminus is developed and served by DeepSeek.