Context
164K
Max output
164K
Serving providers
2
Cheapest input
$0.27 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
43.5
of 100
18.1
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt2%reasoning: true
EvalComputeProxy1036.4reasoning: true
GDPval889.3reasoning: true
GPQA Diamond79%reasoning: true
Humanity's Last Exam15%reasoning: true
IFBench57%reasoning: true
LiveCodeBench80%reasoning: true
Long-Context Reasoning65%reasoning: true
MMLU-Pro85%reasoning: true
Omniscience-24.3reasoning: true
SciCode41%reasoning: true
TerminalBench Hard32%default
TerminalBench v2.145%reasoning: true
τ-bench Banking16%reasoning: true
τ²-bench37%reasoning: true

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
DeepInfraCheapest$0.27$1.001
ComponentUnitStandardBatchCached
Text cached in/1M tok$0.2160
Text input/1M tok$0.2700
Text output/1M tok$1.00
NovitaCheapest$0.27$1.001

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00Sep 26Jan 13Jun 22$1.00$0.270

Cost calculator

estimate your monthly spend on this model
$134
estimated / month

Model IDs

copy the exact identifier for your platform
deepinfra/deepseek-ai/DeepSeek-V3.1-Terminusnovita/deepseek/deepseek-v3.1-terminus

Frequently asked questions

DeepSeek V3.1 Terminus pricing, context and availability

How much does DeepSeek V3.1 Terminus cost?

DeepSeek V3.1 Terminus costs $0.27 per 1M input tokens and $1.00 per 1M output tokens at its cheapest provider via DeepInfra.

What is the context window of DeepSeek V3.1 Terminus?

DeepSeek V3.1 Terminus accepts up to 164K tokens of context and can return up to 164K output tokens.

Which providers serve DeepSeek V3.1 Terminus?

DeepSeek V3.1 Terminus is available from 2 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.

What can DeepSeek V3.1 Terminus do?

DeepSeek V3.1 Terminus supports tool use, reasoning and structured output.

Other DeepSeek models

compare pricing across the DeepSeek lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI