DeepSeek V3.1 Terminus
MoE workstation685B total, ~37B active per token (MoE) - same backbone as DeepSeek V3. Instruct/agent-tuned variant of V3.1-Base: improves language consistency (less mixed Chinese-English) and adds Code Agent + Search Agent tool-use. FP8 quantization. Open weights under MIT.
AI-generated content marks
This model embeds text watermarks in generated text and adds C2PA provenance metadata to supported files such as .png, .jpg, and .svg. Marks can be lost through editing, screenshots, or format conversion, so their absence does not prove a file is human-made.
- 685.0B
- 128k
- mit
- 🇨🇳 China
- Sep 2025
Scores
Score per dollar
304 pts per $/M input
general_score (82) divided by cheapest input price ($0.27/M). Higher is better value. See live pricing.
Related models
Save your hardware and every model page answers the real question: will it run on your machine, and how fast?
Join free - save your rig →Or run it in the cloud
Live per-provider pricing, throughput and uptime - refreshed about 3 hours ago via OpenRouter. Click a column to sort.
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
|
StreamLake
|
API | 0.34 | 1.03 | - | - | - | 100.00% | best uptime |
|
SiliconFlow
|
API | 0.27 | 1.00 | - | - | - | 97.35% | cheapest |
Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.
Detailed API pricing page + JSON endpoint →
See who runs DeepSeek in production →
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.