Skip to main content

Head-to-head comparison

DeepSeek-V4.1-Flash vs. Mistral Large 4

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series
0
distinct benchmarks
0
latest retrieval
No data

Change model selection

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for DeepSeek-V4.1-Flash and Mistral Large 4
AttributeDeepSeek-V4.1-FlashMistral Large 4
ProviderDeepSeekMistral AI
ReleasedSep 10, 2026Oct 6, 2026
AvailabilityActivePreview
Model typeOpen WeightsOpen weights announced; currently an API preview
Parameters552B1.05T
ArchitectureMixture of ExpertsMixture of Experts
Context window1,000,000 tokens1M tokens (Mistral); 524,288 tokens (OpenRouter)
Knowledge cutoffNot publishedNot published
Technical sourcesModelModel, Context

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for DeepSeek-V4.1-Flash and Mistral Large 4
Price typeDeepSeek-V4.1-FlashMistral Large 4
API input$0.15 (Off-Peak)$1.36
API output$0.6 (Off-Peak)$4.18
Cache read$0. (Off-Peak)$0.14
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified09/23/2026 Source10/07/2026 Source
DeepSeek-V4.1-Flash: peak pricing is $0.3 input / $1.2 output per 1M tokens during Mon, Tue, Wed, Thu, Fri, 01:00-04:00 UTC; Mon, Tue, Wed, Thu, Fri, 06:00-10:00 UTC; off-peak rates apply at all other times.

Mistral Large 4, Launch pricing announced October 6, 2026

Mistral announced a 50% discount for two weeks. The published introductory rates are $0.68 input, $2.09 output and $0.07 cache read per 1M tokens. Price comparisons use the standard rates. Source

DeepSeek-V4.1-FlashMistral Large 4
API inputUSD per 1M tokens, base tier
DeepSeek-V4.1-FlashLower price$0.15
Mistral Large 4$1.36
API outputUSD per 1M tokens, base tier
DeepSeek-V4.1-FlashLower price$0.6
Mistral Large 4$4.18
Cache readUSD per 1M tokens, base tier
DeepSeek-V4.1-FlashLower price$0.003
Mistral Large 4$0.14

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

No provider tariff for Mistral Large 4 is available in the stored OpenRouter snapshot. The official direct price is still shown.

Provider pricing for DeepSeek-V4.1-Flash and Mistral Large 4
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
DeepSeek-V4.1-FlashDeepSeekDirect from developerStandard API$0.15$0.6Source09/23/2026
AlibabaVia OpenRouteralibaba$0.15$0.6Source10/12/2026
AtlasCloudVia OpenRouteratlas-cloud/fp8$0.3$1.2Source10/12/2026
BaiduVia OpenRouterbaidu/fp8Lowest listed price: $0.0348Lowest listed price: $0.1392Source10/12/2026
BaseTenVia OpenRouterbaseten/fast$0.6$2.4Source10/12/2026
BaseTenVia OpenRouterbaseten/fp8#1$0.3$1.2Source10/12/2026
BaseTenVia OpenRouterbaseten/fp8#2$0.3$1.2Source10/12/2026
CoreWeaveVia OpenRoutercoreweave/fp8$0.2$0.65Source10/12/2026
CrusoeVia OpenRoutercrusoe/fp8$0.29$1.2Source10/12/2026
DecartVia OpenRouterdecart/fp4$0.09$0.18Source10/12/2026
DeepInfraVia OpenRouterdeepinfra/fp8$0.14$0.42Source10/12/2026
DeepSeekVia OpenRouterdeepseek$0.15$0.6Source10/12/2026
DekaLLMVia OpenRouterdekallm$0.12$1.2Source10/12/2026
DigitalOceanVia OpenRouterdigitalocean$0.165$0.66Source10/12/2026
FireworksVia OpenRouterfireworks$0.3$1.2Source10/12/2026
FireworksVia OpenRouterfireworks/us$0.45$1.8Source10/12/2026
GMICloudVia OpenRoutergmicloud/fp8$0.18$0.72Source10/12/2026
InferenceNetVia OpenRouterinference-net/fp8$0.077$0.8Source10/12/2026
IonstreamVia OpenRouterionstream$0.1$0.75Source10/12/2026
MakoraVia OpenRoutermakora/fp8$0.27$1.15Source10/12/2026
ModalVia OpenRoutermodal$0.3$1.2Source10/12/2026
MorphVia OpenRoutermorph/fp8$0.042$0.6Source10/12/2026
NovitaVia OpenRouternovita/fp8$0.195$0.78Source10/12/2026
OpenInferenceVia OpenRouteropen-inference/fp4$0.055$0.36Source10/12/2026
ParasailVia OpenRouterparasail/fp8$0.3$1.2Source10/12/2026
PhalaVia OpenRouterphala$0.21$0.84Source10/12/2026
RelaceVia OpenRouterrelace$0.05$0.6Source10/12/2026
Sail ResearchVia OpenRoutersail-research/fp4$0.08$0.4Source10/12/2026
SiliconFlowVia OpenRoutersiliconflow/fp8$0.3$1.2Source10/12/2026
StreamLakeVia OpenRouterstreamlake/fp8$0.147$0.588Source10/12/2026
TogetherVia OpenRoutertogether$0.3$1.2Source10/12/2026
VeniceVia OpenRoutervenice/fp8$0.3$1.2Source10/12/2026
WaferVia OpenRouterwafer$0.045$0.99Source10/12/2026
Mistral Large 4Mistral AIDirect from developerStandard APILowest listed price: $1.36Lowest listed price: $4.18Source10/07/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

Not enough directly matched categories for a reliable radar

Only 0 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.

No directly comparable result series yet

No published benchmark for DeepSeek-V4.1-Flash and Mistral Large 4 currently matches in version, task, metric, and comparison cohort. We therefore show no estimated or blended values.

Our model tests

Our tests

Compare how the models respond to the same prompt. Each test shows the latest attempt, with no subsequent fixes to the generated code. Earlier runs remain available in the test details. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

DeepSeek-V4.1-Flash

The response reached the token limit. No complete recording is available.

Reasoning (requested): high

Current attempt
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
deepseek/deepseek-v4.1-flash
API model reported in response
deepseek/deepseek-v4.1-flash
Reasoning setting
high
Pinned endpoint
DeepSeek | deepseek/deepseek-v4.1-flash-20260910
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Failed
Response time
25.8 s

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Earlier attempts (2)
  • Oct 2, 2026API request failedReasoning setting: high
  • Oct 1, 2026API request failedReasoning setting: high

Mistral Large 4

Not tested yet

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Related LLM comparisons

Compare DeepSeek-V4.1-Flash and Mistral Large 4 with other leading models using the same data and benchmark logic.

View the complete LLM comparison