Model profile
DeepSeek

DeepSeek: DeepSeek V3.1 Terminus

DeepSeek: DeepSeek V3.1 Terminus is a budget-priced text-first model from DeepSeek with partial runtime data, extended context posture, and the clearest fit around long-context research / agent workflows.

Best for: Long-context research / Agent workflowsN/A latencyExtended contextBudget pricing
Intelligence
28.5

Benchmark blend

Coding
31.9

Dev workflow signal

Context
164K Tokens

Extended

Input Price
$0.34

Budget tier

Decision snapshot
50

DeepSeek: DeepSeek V3.1 Terminus currently reads as a budget text-first option with extended context and a partially published runtime profile.

Overall profile
Use-case specific
Best for
Long-context research / Agent workflows
Latency tier
N/A
Price tier
Budget
Source coverage
OpenRouterArtificial Analysis

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
28.5
29

General reasoning and benchmark headroom.

Limited
Speed
N/A
N/A

Latency data is partial.

Unavailable
Context
164K Tokens
76

How much prompt and task state can stay in view.

Competitive
Price
$0.34
86

$1.50 output / 1M

Efficient

Editorial Profile

DeepSeek: DeepSeek V3.1 Terminus in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Use-case specificCoding score 32Math score 54

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 optimizing the model's...

Identity

DeepSeek text-first profile

Positioning

Long-context research / Agent workflows with extended context and partially published runtime.

Cost posture

Efficient spend profile. More comfortable for sustained prompt volume if the capability fit is right.

Strengths
  • Large context headroom supports repo-wide prompts and long research sessions.

Tradeoffs
  • Budget-friendly input pricing is a strength, but raw capability may vary by workload.

  • Latency data is incomplete, so interactive responsiveness is harder to rank confidently.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

Best fit
  • Long-context summarization, repo analysis, and policy or document review.

Explore Next

Similar profiles worth opening next

DeepSeek

DeepSeek: DeepSeek V3.2

Intelligence
41.7
Context
164K Tokens
Input Price
$0.28
DeepSeek

DeepSeek V3.1 Terminus (Reasoning)

Intelligence
33.9
Context
N/A
Input Price
$0.40
DeepSeek

DeepSeek V3.2 Exp (Reasoning)

Intelligence
32.9
Context
N/A
Input Price
$0.28

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

General intelligence

Broad reasoning, knowledge depth, and flagship benchmark posture.

Intelligence Index
28.5
MMLU Pro
83.6%
GPQA
75.1%
HLE
8.4%
Coding

Software implementation, debugging quality, and coding benchmark signal.

Coding Index
31.9
LiveCodeBench
0.529
SciCode
32.1%
Math

Formal reasoning, structured problem solving, and competition-style math.

Math Index
53.7
AIME 2025
53.7%
Agent / tool use

Long-horizon execution quality and interactive benchmark evidence.

IFBench
41.2%
TAU2
37.1%
TerminalBench Hard
31.8%
LCR
43.3%

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
164K Tokens
Vision
Text-first
Modalities
text
Tokenizer
DeepSeek
Moderation
No
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Input Modalities
text
Output Modalities
text
Price architecture
Input
per 1M input tokens
$0.34
Output
per 1M output tokens
$1.50
Blended
AA 3:1 mix
$0.63

This model is relatively efficient on price. It is the easier fit when sustained prompt volume matters.

OR Cache Read
$0.00

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.