LLM Reference

DeepSeek R1 0528 vs DeepSeek V3.2

DeepSeek R1 0528 (2025) and DeepSeek V3.2 (2025) are frontier reasoning models from DeepSeek. DeepSeek R1 0528 ships a 130k-token context window, while DeepSeek V3.2 ships a 160k-token context window. On SWE-bench Verified, DeepSeek V3.2 leads by 12.4 pts. On pricing, DeepSeek V3.2 costs $0.25/1M input tokens versus $0.50/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

DeepSeek V3.2 is ~98% cheaper at $0.25/1M; pay for DeepSeek R1 0528 only for coding workflow support.

Decision scorecard

Local evidence first
SignalDeepSeek R1 0528DeepSeek V3.2
Best forreasoning-heavy apps and provider-routed productionprovider-routed production
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window130k160k
Cheapest output$2.15/1M tokens$0.38/1M tokens
Provider routes6 tracked7 tracked
Shared benchmarks2 rowsSWE-bench Verified leader

Decision tradeoffs

Choose DeepSeek R1 0528 when...
  • DeepSeek R1 0528 uniquely exposes Reasoning in local model data.
  • Local decision data tags DeepSeek R1 0528 for Coding, RAG, and Agents.
Choose DeepSeek V3.2 when...
  • DeepSeek V3.2 holds a shared-benchmark lead on SWE-bench Verified, ahead by 12.4 points.
  • DeepSeek V3.2 has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • DeepSeek V3.2 has the lower cheapest tracked output price at $0.38/1M tokens.
  • DeepSeek V3.2 has broader tracked provider coverage for fallback and procurement flexibility.
  • Local decision data tags DeepSeek V3.2 for Coding, RAG, and Agents.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Lower estimate DeepSeek V3.2

DeepSeek R1 0528

$938

Cheapest tracked route/tier: OpenRouter

DeepSeek V3.2

$296

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $641. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

DeepSeek R1 0528 -> DeepSeek V3.2
  • Provider overlap exists on Fireworks AI, OpenRouter, and Microsoft Foundry; start route-level A/B tests there.
  • DeepSeek V3.2 is $1.77/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Reasoning before moving production traffic.
DeepSeek V3.2 -> DeepSeek R1 0528
  • Provider overlap exists on Fireworks AI, Novita AI, and OpenRouter; start route-level A/B tests there.
  • DeepSeek R1 0528 is $1.77/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • DeepSeek R1 0528 adds Reasoning in local capability data.

Specs

Specification
Released2025-05-282025-12-01
Context window130k160k
Parameters685B total, 37B active (MoE)671B
Architecturedecoder onlydecoder only
LicenseMIT(OSI)MIT(OSI)
OpennessOpen sourceOpen source
Commercial useCommercial use allowedCommercial use allowed
Knowledge cutoff--

Pricing and availability

Pricing attributeDeepSeek R1 0528DeepSeek V3.2
Input price$0.50/1M tokens$0.25/1M tokens
Output price$2.15/1M tokens$0.38/1M tokens
Providers

Capabilities

CapabilityDeepSeek R1 0528DeepSeek V3.2
VisionNoNo
MultimodalNoNo
ReasoningYesNo
Function callingNoNo
Tool useNoNo
Structured outputsYesYes
Code executionYesYes
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkDeepSeek R1 0528DeepSeek V3.2
SWE-bench Verified57.670.0
Google-Proof Q&A81.084.0

Deep dive

On shared benchmark coverage, SWE-bench Verified has DeepSeek R1 0528 at 57.6 and DeepSeek V3.2 at 70, with DeepSeek V3.2 ahead by 12.4 points; Google-Proof Q&A has DeepSeek R1 0528 at 81 and DeepSeek V3.2 at 84, with DeepSeek V3.2 ahead by 3 points. The largest visible gap is 12.4 points on SWE-bench Verified, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.

The capability footprint differs most on reasoning mode: DeepSeek R1 0528. Both models share structured outputs and code execution, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.

For cost, DeepSeek R1 0528 lists $0.50/1M input and $2.15/1M output tokens on the cheapest tracked provider, while DeepSeek V3.2 lists $0.25/1M input and $0.38/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts DeepSeek V3.2 lower by about $0.71 per million blended tokens. Availability is 6 providers versus 7, so concentration risk also matters.

Choose DeepSeek R1 0528 when coding workflow support are central to the workload. Choose DeepSeek V3.2 when coding workflow support, larger context windows, and lower input-token cost are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.

FAQ

Which has a larger context window, DeepSeek R1 0528 or DeepSeek V3.2?

DeepSeek V3.2 supports 160k tokens, while DeepSeek R1 0528 supports 130k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Which is cheaper, DeepSeek R1 0528 or DeepSeek V3.2?

DeepSeek V3.2 is cheaper on tracked token pricing. DeepSeek R1 0528 costs $0.50/1M input and $2.15/1M output tokens. DeepSeek V3.2 costs $0.25/1M input and $0.38/1M output tokens. Provider discounts or batch pricing can still change the final bill.

Is DeepSeek R1 0528 or DeepSeek V3.2 open source?

DeepSeek R1 0528 is listed under MIT. DeepSeek V3.2 is listed under MIT. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.

Which is better for reasoning mode, DeepSeek R1 0528 or DeepSeek V3.2?

DeepSeek R1 0528 has the clearer documented reasoning mode signal in this comparison. If reasoning mode is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.

Which is better for structured outputs, DeepSeek R1 0528 or DeepSeek V3.2?

Both DeepSeek R1 0528 and DeepSeek V3.2 expose structured outputs. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface.

Where can I run DeepSeek R1 0528 and DeepSeek V3.2?

DeepSeek R1 0528 is available on Together AI, Fireworks AI, GCP Vertex AI, Novita AI, and OpenRouter. DeepSeek V3.2 is available on Fireworks AI, NVIDIA NIM, AWS Bedrock, OpenRouter, and Microsoft Foundry. Provider coverage can affect latency, region availability, compliance posture, and fallback options.

Continue comparing

Last reviewed: 2026-05-22. Data sourced from public model cards and provider documentation.