DeepSeek logo

DeepSeek V3.1 Terminus

Pricing & Specs API
Free REST API for prices, specs and benchmarks
DeepSeek V3.1 Terminus is DeepSeek's language model with a 164K context window and up to 66K output tokens, available from 6 providers, starting at $0.27 / 1M input and $1.00 / 1M output. An update to DeepSeek V3.1 that addresses language consistency and agent capability issues while preserving the model's core performance.
Specifications
Canonical IDdeepseek-v3-1-terminus
TypeLanguage
StatusActive
CreatorDeepSeekDeepSeek
Providers
Context Window164K tokens
Max Output66K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters685B
HuggingFace Likes363
HuggingFace Downloads (30d)3,879
HuggingFace Downloads (all-time)180,017
Release Date · 10 months ago
Knowledge Cutoff · 1 year ago
Benchmarks
Intelligence Index
21.4
#160
Math Index
53.7
#126
MMLU-Pro
0.8
#48
GPQA
0.8
#163
HLE
0.1
#184
LiveCodeBench
0.5
#129
IFBench
0.4
#226
Time to First Token
0.00s
#83
SciCode
0.3
#225
AIME 2025
0.5
#126
LCR
0.4
#180
TerminalBench Hard
0.3
#82
TAU2
0.4
#205
Output TPS
0.0
#339

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
DeepInfra logo
DeepInfra
deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus
$0.27$1.00$0.216
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus
$0.56$1.68N/A
Hugging Face logo
Hugging Face
novita:deepseek/deepseek-v3.1-terminus
$0.27$1.00N/A
Novita logo
Novita
novita/deepseek/deepseek-v3.1-terminus
$0.27$1.00$0.135
OpenRouter logo
OpenRouter
deepseek/deepseek-v3.1-terminus
$0.27$1.00$0.135
Vercel AI Gateway logo
Vercel AI Gateway
deepseek/deepseek-v3.1-terminus
$0.27$1.00$0.135

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host DeepSeek V3.1 Terminus, ranked by cheapest on-demand price. The model needs about 1643 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
p6-b300.48xlargeAWS8× B3002149 GB$142.42/hrus-east-1

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
DeepSeek V3.2—164K$0.269$0.400
DeepSeek V3.2 Speciale—164K$0.580$1.68
DeepSeek V3.2 Thinking—128K$0.620$1.85
DeepSeek V3.2 ExpExp164K$0.270$0.410
DeepSeek V3.2 Exp Reasoning—————
DeepSeek V3.2 Exp—————
DeepSeek V3.1—164K$0.250$0.950
DeepSeek V3.1 671B——164K——
DeepSeek V3—164K$0.200$0.200
DeepSeek V3 324——164K$0.200$0.400

Model IDs

accounts/fireworks/models/deepseek-v3p1-terminus
deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus
deepseek-ai/DeepSeek-V3.1-Terminus
deepseek-v3-1-terminus
deepseek-v3-1-terminus-reasoning
deepseek/deepseek-v3.1-terminus
fireworks_ai/accounts/fireworks/models/deepseek-v3p1-terminus
novita/deepseek/deepseek-v3.1-terminus