DeepSeek V4 Pro 0813 vs Phi-4 Mini Instruct

At a Glance

Compare
Intelligence, Cost, and Efficiency
IntelligenceHigher is better · MM Intelligence v2.5#20 of 4665.0 score · 3/3 sources · completeUnrankedNot in the 46-model eligible cohort
CostLower is better · Published-token output estimate#20 of 44$0.094 per LiveBench caseUnrankedNot in the 44-model eligible cohort
EfficiencyHigher is better · MM Efficiency v1.5#14 of 3857.4 score · 3/3 sources · completeUnrankedNot in the 38-model eligible cohort
Pricing and Limits
Input priceFrom · USD / 1M tokens$1.30Deepinfra · Sep 22, 2026Not reported
Output priceFrom · USD / 1M tokens$2.60Deepinfra · Sep 22, 2026Not reported
Context windowMaximum documented tokens1,049K131K
Model facts checkedSep 3, 2026View model evidence →Aug 28, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

Available Benchmarks

All benchmark results →
No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.

Side-by-Side Facts

FieldDeepSeek-V4-Pro-0813Phi-4-mini-instruct
DeveloperDeepSeekMicrosoft
FamilyDeepseek V4 ProPhi 4 Mini Instruct
ModelDeepSeek-V4-Pro-0813Phi-4-mini-instruct
VersionDeepSeek-V4-Pro-0813Phi-4-mini-instruct
Lifecycleactiveactive
Released2026-08-132025-02-26
Knowledge cutoffUnknownUnknown
Input modalitiesTextText
Output modalitiesTextText
Context window1,049K131K
Total parameters1.6T3.8B
Active parameters49BUnknown
Licensemitmit
Open weightsYesYes
API availableYesYes
Self-hostableYesYes
Provider accessDeepinfra (Standard), Fireworks Ai (Standard), Together Ai (Standard)Hugging Face (Standard)
Capabilitiesagents, chat, coding, generation, reasoning, toolschat, generation

DeepSeek V4 Pro 0813 Capabilities

agentschatcodinggenerationreasoningtools
Serving providers3
Canonical IDdeepseek-ai/DeepSeek-V4-Pro-0813

Phi-4 Mini Instruct Capabilities

chatgeneration
Serving providers1
Canonical IDmicrosoft/Phi-4-mini-instruct

Primary Evidence

Sources and Freshness

Questions

DeepSeek V4 Pro 0813 vs Phi-4 Mini Instruct FAQs

Is DeepSeek V4 Pro 0813 or Phi-4 Mini Instruct better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both DeepSeek V4 Pro 0813 and Phi-4 Mini Instruct, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, DeepSeek V4 Pro 0813 or Phi-4 Mini Instruct?+

Only DeepSeek V4 Pro 0813 has a directly sourced input price: $1.30 per million tokens. Only DeepSeek V4 Pro 0813 has a directly sourced output price: $2.60 per million tokens.

Which has a larger context window, DeepSeek V4 Pro 0813 or Phi-4 Mini Instruct?+

DeepSeek V4 Pro 0813 has the larger sourced context window. DeepSeek V4 Pro 0813 supports 1,049K and Phi-4 Mini Instruct supports 131K.

Which performs better in benchmarks, DeepSeek V4 Pro 0813 or Phi-4 Mini Instruct?+

There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.

Can DeepSeek V4 Pro 0813 or Phi-4 Mini Instruct be self-hosted?+

Both models have the same recorded self-hosting status: supported. DeepSeek V4 Pro 0813 is open weight; Phi-4 Mini Instruct is open weight.

Can DeepSeek V4 Pro 0813 and Phi-4 Mini Instruct understand images?+

DeepSeek V4 Pro 0813 is not documented with image input; Phi-4 Mini Instruct is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, DeepSeek V4 Pro 0813 or Phi-4 Mini Instruct?+

Neither has a larger sourced maximum output. DeepSeek V4 Pro 0813 is — and Phi-4 Mini Instruct is —.

Do DeepSeek V4 Pro 0813 and Phi-4 Mini Instruct support reasoning and tool use?+

DeepSeek V4 Pro 0813: reasoning and tool calling. Phi-4 Mini Instruct: none of these features are definitively sourced. Feature support does not establish relative quality.

Which is available from more inference providers, DeepSeek V4 Pro 0813 or Phi-4 Mini Instruct?+

DeepSeek V4 Pro 0813 has 3 sourced provider routes; Phi-4 Mini Instruct has 1, so DeepSeek V4 Pro 0813 has broader tracked availability.

Which offers better value, DeepSeek V4 Pro 0813 or Phi-4 Mini Instruct?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback