LLM ReferenceLLM Reference

DeepSeek V3 0324

deepseek-v3-0324

Researched 137d ago

Last refreshed 2026-05-16. Next refresh: weekly.

Open SourceCodingLong context

DeepSeek V3 0324 is worth evaluating for coding and long context when its provider route and context window match the workload.

Decision context: Coding task fit, 2 tracked provider routes, and research from 2026-01-01.

Use it for

  • Teams evaluating coding and long context
  • Workloads that can use a 160K context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows

Cheapest output

$1.68

Fireworks AI per 1M tokens

Provider routes

2

Tracked API hosts

Quality / dollar

Grade C

Ranked by benchmark score divided by cheapest output price

Freshness

2026-01-01

Researched 137d ago

stale

Top use-case fit

Coding

Q/$ C

2 relevant benchmarks in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

ProviderInput / 1MOutput / 1MRoute
Fireworks AI$0.560$1.68
Serverless
Microsoft Foundry--
ServerlessProvisionedPartial

Benchmark peer barsfor Coding

Migration checks

No linked migration route is available for this model yet.

About

DeepSeek: DeepSeek V3 0324 available via OpenRouter. Pricing: $0.2/1M input, $0.77/1M output.

DeepSeek V3 0324 has a 160K-token context window.

DeepSeek V3 0324 input tokens at $0.56/1M, output at $1.68/1M.

Capabilities

No model capability flags are currently sourced.

Benchmark Scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
HumanEval85.52025-03DeepSeek
Aider Polyglot55.12026-04https://aider.chat/docs/leaderboards

Rankings

Specifications

Released2025-01-01
Parameters671B
Context160K
ArchitectureDecoder Only
Specializationgeneral
Trainingpretrained

Created by

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website