Compare the listed model data for DeepSeek-V3.1 by DeepSeek and Command A (Mar 25) by Cohere. Benchmark and pricing records are not a controlled test and may change.
Data last updated: 2026-10-16. Verify current model details with each provider.
What the listed data says
DeepSeek-V3.1: 128K tokens; Command A (Mar 25): 256K tokens. Command A (Mar 25) has the larger listed context window. DeepSeek-V3.1 is listed for no specific capability flags; Command A (Mar 25) is listed for coding, agentic workflows, long-context tasks. Shared catalog benchmark entries: MMLU: DeepSeek-V3.1 91.7%; Command A (Mar 25) 81.0%; HumanEval: DeepSeek-V3.1 93.8%; Command A (Mar 25) 78.4%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
Catalog source links
Use these model and provider links to verify current specifications, pricing, and availability.
The listed context windows are 128K tokens and 256K tokens; the larger is 2× the smaller.
On shared numeric benchmark entries, MMLU: DeepSeek-V3.1 − Command A (Mar 25) = +10.7 percentage points (91.7% vs 81.0%); HumanEval: DeepSeek-V3.1 − Command A (Mar 25) = +15.4 percentage points (93.8% vs 78.4%).
The first listed parameter quantities are 671B total (37B active via MoE) and 111B; the larger quantity is 6.05× the smaller. Total and active MoE parameters are not directly equivalent.
The catalog release dates are June 2025 and March 2025, about 3 months apart at the precision supplied.
Cost example: 1M input and 1M output tokens
A cost example for 1M input plus 1M output tokens cannot be calculated reliably because separate numeric input and output rates are not listed for both models.
Choose DeepSeek-V3.1 if…
Choose DeepSeek-V3.1 when your task aligns with catalog-listed uses or strengths such as Enterprise software development requiring high quality at low latency, Document intelligence and knowledge base applications, API providers serving general business customers, DeepSeek's most capable non-reasoning model as of June 2025.
Choose Command A (Mar 25) if…
Choose Command A (Mar 25) when your task aligns with catalog-listed uses or strengths such as Enterprise search and RAG deployments, Multi-step business process automation, Legal, financial, medical document analysis in 23 languages, Cohere's flagship enterprise model for RAG and tool-use workflows.
Feature Comparison — DeepSeek-V3.1 vs Command A (Mar 25)
Catalog specifications for DeepSeek-V3.1 and Command A (Mar 25)
Specification
DeepSeek-V3.1
Command A (Mar 25)
Provider
DeepSeek
Cohere
Parameters
671B total (37B active via MoE)
111B
Context window
128K tokens
256K tokens
Maximum output
Not listed
Not listed
Catalog pricing
MIT open source. DeepSeek API: ~$0.27/MTok input, ~$1.10/MTok output
Cohere API: $2.50/MTok input, $10.00/MTok output
Listed input/output cost per 1M tokens
Separate numeric input/output rates not listed
input $0.15, output $0.6 per 1M tokens
License
MIT
CC BY-NC 4.0 for research; commercial requires API agreement
Coding support
Not listed
Listed
Reasoning support
Not listed
Not listed
Vision input
Not listed
Not listed
Multimodal
Not listed
Not listed
Open weights
Yes
No
Benchmark: MMLU
91.7%
81.0%
Benchmark: HumanEval
93.8%
78.4%
Figures are transcribed from LITHOVEX model records. Benchmark versions and evaluation setups may differ; pricing and specifications can change. Check each provider's current documentation before making a decision.
Frequently Asked Questions
What is different between DeepSeek-V3.1 and Command A (Mar 25)?
DeepSeek-V3.1: 128K tokens; Command A (Mar 25): 256K tokens. Command A (Mar 25) has the larger listed context window. DeepSeek-V3.1 is listed for no specific capability flags; Command A (Mar 25) is listed for coding, agentic workflows, long-context tasks. Shared catalog benchmark entries: MMLU: DeepSeek-V3.1 91.7%; Command A (Mar 25) 81.0%; HumanEval: DeepSeek-V3.1 93.8%; Command A (Mar 25) 78.4%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
What benchmark values are listed for DeepSeek-V3.1 and Command A (Mar 25)?
MMLU: DeepSeek-V3.1 91.7%; Command A (Mar 25) 81.0%; HumanEval: DeepSeek-V3.1 93.8%; Command A (Mar 25) 78.4%. The catalog values may use different versions and evaluation setups, so they are reference points rather than a controlled head-to-head result.
Which model has the larger listed context window?
DeepSeek-V3.1: 128K tokens; Command A (Mar 25): 256K tokens. Command A (Mar 25) has the larger listed context window.
What are the listed costs per million tokens for DeepSeek-V3.1 and Command A (Mar 25)?
DeepSeek-V3.1: Separate numeric input/output rates not listed (MIT open source. DeepSeek API: ~$0.27/MTok input, ~$1.10/MTok output). Command A (Mar 25): input $0.15, output $0.6 per 1M tokens (Cohere API: $2.50/MTok input, $10.00/MTok output). Where separate numeric input and output rates are available, the worked example uses 1M input plus 1M output tokens. Confirm current terms with each provider.
How far apart are the listed release dates for DeepSeek-V3.1 and Command A (Mar 25)?
The catalog lists DeepSeek-V3.1 as June 2025 and Command A (Mar 25) as March 2025, about 3 months apart at the precision supplied.
When was the comparison data last updated?
The model catalog records 2026-10-16 as its data update date. Provider specifications and prices may have changed since then.
How should I choose between DeepSeek-V3.1 and Command A (Mar 25)?
Compare the listed specifications and capabilities, review the benchmark notes, then test both with the same representative prompt for your task. This page does not claim a universal winner.
Create your free LITHOVEX account and compare DeepSeek-V3.1 and Command A (Mar 25) on your actual tasks. No credit card, no API key, no subscriptions needed.