Model profile
DeepSeek

DeepSeek: DeepSeek V3.1

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

Best for: Coding / Long-context researchN/A latencyExtended contextBudget pricing
Intelligence
21.0

Benchmark blend

Coding
0.784

Dev workflow signal

Context
164K Tokens

Extended

Input Price
$0.59

Budget tier

Decision snapshot
56

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

Overall profile
Selective fit
Best for
Coding / Long-context research
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
21.0
21

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
$0.59
86

$1.69 output / 1M

Efficient

Editorial Profile

DeepSeek: DeepSeek V3.1 in one narrative

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

Selective fitCoding score 78Math score 90

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Identity

DeepSeek text-first profile

Positioning

Coding / Long-context research 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
  • Coding indicators point to a strong developer workflow fit.

  • 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
  • Code generation, refactors, test writing, and tool-assisted debugging.

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

Explore Next

Similar profiles worth opening next

DeepSeek

DeepSeek: DeepSeek V4 Pro 0423

Intelligence
53.2
Context
1049K Tokens
Input Price
$1.32
DeepSeek

DeepSeek: DeepSeek V4 Flash 0423

Intelligence
51.8
Context
1049K Tokens
Input Price
$0.44
DeepSeek

DeepSeek V4 Flash Vision (Reasoning, Max Effort)

Intelligence
51.5
Context
N/A
Input Price
$0.44

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
21.0
MMLU Pro
85.1%
GPQA
77.9%
HLE
14.3%
Coding

Software implementation, debugging quality, and coding benchmark signal.

LiveCodeBench
0.784
SciCode
39.1%
Math

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

Math Index
89.7
AIME 2025
89.7%
Agent / tool use

Long-horizon execution quality and interactive benchmark evidence.

IFBench
41.5%
TAU2
37.4%
TerminalBench Hard
25.0%
LCR
56.7%

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
Max Completion
144900
Moderation
No
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Input Modalities
text
Output Modalities
text
Price architecture
Input
per 1M input tokens
$0.59
Output
per 1M output tokens
$1.69
Blended
AA 3:1 mix
$0.86

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.