D
DeepSeek V3.1 TerminusOPEN
DeepSeek V3.1 Terminus (DeepSeek): live API pricing, context window and the best open-source alternatives, tracked daily by OpenSourceAI.tech.
Prices update automatically — checked hourly against provider list prices.
Benchmarks & performance
Independent benchmark scores for DeepSeek V3.1 Terminus, measured by Artificial Analysis. Higher is better. Measurement mode: Non-reasoning.
For the same budget, DeepSeek V3.1 Terminus delivers 7.7 times more capability. Open weights also mean you can self-host it and pay nothing per token.
About this model
DeepSeek V3.1 Terminus is an open-weight AI model by DeepSeek. You can download and self-host it for free; the prices below are hosted-API list prices, tracked hourly, for when you prefer convenience over self-hosting.
Frequently asked questions
What is DeepSeek V3.1 Terminus?
DeepSeek V3.1 Terminus is an AI language model from DeepSeek. It is open-weight: you can download it and run it on your own hardware, for free. It scores 21.4 on the Artificial Analysis intelligence index.
Is DeepSeek V3.1 Terminus free?
The weights are free and open — you can self-host DeepSeek V3.1 Terminus and pay nothing per token. If you prefer a hosted API, list prices are $0.27 per million input tokens and $1 per million output tokens.
What is DeepSeek V3.1 Terminus good at?
Independent benchmarks from Artificial Analysis give it GPQA 75.1%, MMLU-Pro 83.6%, Humanity's Last Exam 8.4%, Long Context Reasoning 43.3%, LiveCodeBench 52.9%, SciCode 32.1%, AIME 2025 53.7%, IFBench 41.2%, τ²-Bench 37.1%, Terminal-Bench Hard 31.8%. It is particularly used for mathematical reasoning.
Can I self-host DeepSeek V3.1 Terminus?
Yes. DeepSeek V3.1 Terminus has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.
Open-source alternatives
Depending on your workload, an open-weight model that you can self-host may cut costs dramatically or remove per-token pricing entirely. Our comparison pages put this model side by side with the strongest open-source contenders.