LLM Reference

DeepSeek R1 0528 vs Qwen3.6 Max Preview

DeepSeek R1 0528 (2025) and Qwen3.6 Max Preview (2026) are frontier-tier reasoning models from DeepSeek and Alibaba. DeepSeek R1 0528 ships a 130k-token context window, while Qwen3.6 Max Preview ships a 256k-token context window. On MMLU PRO, Qwen3.6 Max Preview leads by 3.5 pts. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Qwen3.6 Max Preview is safer overall; choose DeepSeek R1 0528 when coding workflow support matters.

Decision scorecard

Local evidence first
SignalDeepSeek R1 0528Qwen3.6 Max Preview
Best forreasoning-heavy apps and provider-routed productionreasoning-heavy apps, multimodal apps, and tool-calling agents
Decision fitCoding, RAG, and AgentsCoding, RAG, and Agents
Context window130k256k
Cheapest output$2.15/1M tokens$6.24/1M tokens
Provider routes7 tracked3 tracked
Shared benchmarks4 sharedMMLU PRO leader

Decision tradeoffs

Choose DeepSeek R1 0528 when...
  • DeepSeek R1 0528 has the lower cheapest tracked output price at $2.15/1M tokens.
  • DeepSeek R1 0528 has broader tracked provider coverage for fallback and route flexibility.
  • DeepSeek R1 0528 uniquely exposes Code execution in local model data.
  • Local decision data tags DeepSeek R1 0528 for Coding, RAG, and Agents.
Choose Qwen3.6 Max Preview when...
  • Qwen3.6 Max Preview holds a shared-benchmark lead on MMLU PRO, ahead by 3.5 points.
  • Qwen3.6 Max Preview has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Qwen3.6 Max Preview uniquely exposes Vision, Multimodal, and JSON / Tool use in local model data.
  • Local decision data tags Qwen3.6 Max Preview 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 R1 0528

DeepSeek R1 0528

$938

Cheapest tracked route/tier: OpenRouter

Qwen3.6 Max Preview

$2,392

Cheapest tracked route/tier: OpenRouter

Estimated monthly gap: $1,455. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

DeepSeek R1 0528 -> Qwen3.6 Max Preview
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • Qwen3.6 Max Preview is $4.09/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • Check replacement coverage for Code execution before moving production traffic.
  • Qwen3.6 Max Preview adds Vision, Multimodal, and JSON / Tool use in local capability data.
Qwen3.6 Max Preview -> DeepSeek R1 0528
  • Provider overlap exists on OpenRouter; start route-level A/B tests there.
  • DeepSeek R1 0528 is $4.09/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Vision, Multimodal, and JSON / Tool use before moving production traffic.
  • DeepSeek R1 0528 adds Code execution in local capability data.

Specs

Specification
Released2025-05-282026-04-20
Context window130k256k
Parameters685B total, 37B active (MoE)
ArchitectureDecoder OnlyMixture of Experts
LicenseMITOSI-approvedApache 2.0OSI-approved
OpennessOpen sourceOpen source
WeightsUnknownUnknown
CodeUnknownUnknown
Commercial useCommercial use: permittedCommercial use: permitted
Knowledge cutoff--

Pricing and availability

Pricing attributeDeepSeek R1 0528Qwen3.6 Max Preview
Input price$0.50/1M tokens
0-128,000t
$1.30/1M tokens
128,000t+
$2/1M tokens
Output price$2.15/1M tokens
0-128,000t
$7.80/1M tokens
128,000t+
$12/1M tokens
Providers

Capabilities

CapabilityDeepSeek R1 0528Qwen3.6 Max Preview
VisionNoYes
MultimodalNoYes
ReasoningYesYes
JSON / Tool useNoYes
Structured outputsYesYes
Code executionYesNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkDeepSeek R1 0528Qwen3.6 Max Preview
MMLU PRO85.088.5
SWE-bench Verified57.678.8
Google-Proof Q&A81.086.0
LiveCodeBench73.387.1

Continue comparing

Last reviewed: 2026-06-29. Data sourced from public model cards and provider documentation.