API pricing per million tokens
- Input
- $0.27
- per 1M, SiliconFlow (fp8)
- Output
- $1
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 164K
- 33K max output
Where to buy it (4)
Novita AIfp8, fp8$0.27 / $1cached $0.135
SiliconFlowfp8, fp8$0.27 / $1$0.453 blended
- AtlasCloudfp8, fp8$0.3 / $0.95cached $0.13
- StreamLakedefault region$0.343 / $1.03$0.514 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $47.00 direct.
Helicone$47.00+0%
Kong AI Gateway$47.00+0%
LiteLLM$47.00+0%
Vercel AI Gateway$47.00+0%
AWS Bedrock$47.00+0%
Azure AI Foundry$47.00+0%
Google Vertex AI$47.00+0%
Databricks Mosaic AI$47.00+0%
Hugging Face Inference$47.00+0%
Cloudflare AI Gateway$49.35+5%
Requesty$49.35+5%
Eden AI$49.59+5.5%
OpenRouter$49.59+5.5%
Snowflake Cortex AI$56.40+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
BigQuery MLn/a
Cloudflare Workers AIn/a
NVIDIA NIMn/a
Related models
DeepSeek V4.1 FlashDeepSeek · 1M$0.15 / $0.6in / out per 1M$0.15$0.6$0.0031MSep 10, 2026
DeepSeek V4 Flash Vision ExpDeepSeek · via DeepInfra (fp8) · 1M$0.216 / $0.647in / out per 1M$0.216$0.647$0.00691MAug 21, 2026
DeepSeek V4 Pro 0813DeepSeek · 1M$0.66 / $1.98in / out per 1M$0.66$1.98$0.0221MAug 12, 2026
DeepSeek V4 Flash 0731DeepSeek · via StreamLake (fp8) · 1.31M$0.053 / $0.158in / out per 1M$0.053$0.158$0.00171.31MJul 31, 2026
GLM 4.6Z.ai · via Venice (fp4) · 205K$0.43 / $1.75in / out per 1M$0.43$1.75$0.08205KSep 30, 2025
Kimi K2.5Moonshot AI · via SiliconFlow (int4) · 262K$0.45 / $2.25in / out per 1M$0.45$2.25$0.07262KJan 27, 2026
Gemini 3.1 Flash LiteGoogle Gemini API · 1M$0.25 / $1.5in / out per 1M$0.25$1.5$0.0251MMay 7, 2026
Gemini 3.1 Flash Lite PreviewGoogle Gemini API · 1M$0.25 / $1.5in / out per 1M$0.25$1.5$0.0251MMar 3, 2026
About DeepSeek V3.1 Terminus
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further
Takes text in and returns text. First listed Sep 23, 2026. Blended price $0.453 per 1M tokens at 3 input to 1 output.
Questions
How much does DeepSeek V3.1 Terminus cost?
$0.27 per million input tokens and $1 per million output tokens.
What is the context window of DeepSeek V3.1 Terminus?
164K tokens, with up to 33K tokens of output.
Where is DeepSeek V3.1 Terminus cheapest?
Of 4 routes tracked, Novita AI is cheapest at $0.27 input and $1 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.