LLM Reference

DeepSeek R1 0528 vs Qwen3-235B-A22B

DeepSeek R1 0528 (2025) and Qwen3-235B-A22B (2025) are frontier reasoning models from DeepSeek and Alibaba. DeepSeek R1 0528 ships a 130k-token context window, while Qwen3-235B-A22B ships a 128k-token context window. On MMLU PRO, DeepSeek R1 0528 leads by 2.2 pts. On pricing, Qwen3-235B-A22B costs $0.09/1M 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.

Qwen3-235B-A22B is ~456% cheaper at $0.09/1M; pay for DeepSeek R1 0528 only for coding workflow support.

Decision scorecard

Local evidence first
SignalDeepSeek R1 0528Qwen3-235B-A22B
Best forreasoning-heavy apps and provider-routed productionprovider-routed production
Decision fitCoding, RAG, and AgentsCoding, RAG, and Long context
Context window130k128k
Cheapest output$2.15/1M tokens$0.58/1M tokens
Provider routes7 tracked5 tracked
Shared benchmarksMMLU PRO leader5 shared

Decision tradeoffs

Choose DeepSeek R1 0528 when...
  • DeepSeek R1 0528 holds a shared-benchmark lead on MMLU PRO, ahead by 2.2 points.
  • DeepSeek R1 0528 has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • DeepSeek R1 0528 has broader tracked provider coverage for fallback and route flexibility.
  • DeepSeek R1 0528 uniquely exposes Reasoning and Code execution in local model data.
  • Local decision data tags DeepSeek R1 0528 for Coding, RAG, and Agents.
Choose Qwen3-235B-A22B when...
  • Qwen3-235B-A22B holds a shared-benchmark lead on Google-Proof Q&A, ahead by 5.1 points.
  • Qwen3-235B-A22B has the lower cheapest tracked output price at $0.58/1M tokens.
  • Local decision data tags Qwen3-235B-A22B for Coding, RAG, and Long context.

Monthly cost at traffic

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

Lower estimate Qwen3-235B-A22B

DeepSeek R1 0528

$938

Cheapest tracked route/tier: OpenRouter

Qwen3-235B-A22B

$217

Cheapest tracked route/tier: Novita AI

Estimated monthly gap: $721. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.

Switch friction

DeepSeek R1 0528 -> Qwen3-235B-A22B
  • Provider overlap exists on Fireworks AI, OpenRouter, and Novita AI; start route-level A/B tests there.
  • Qwen3-235B-A22B is $1.57/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
  • Check replacement coverage for Reasoning and Code execution before moving production traffic.
Qwen3-235B-A22B -> DeepSeek R1 0528
  • Provider overlap exists on Fireworks AI, Novita AI, and OpenRouter; start route-level A/B tests there.
  • DeepSeek R1 0528 is $1.57/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
  • DeepSeek R1 0528 adds Reasoning and Code execution in local capability data.

Specs

Specification
Released2025-05-282025-04-29
Context window130k128k
Parameters685B total, 37B active (MoE)235B
ArchitectureDecoder OnlyDecoder Only
LicenseMITOSI-approvedApache 2.0OSI-approved
OpennessOpen sourceOpen source
WeightsUnknownUnknown
CodeUnknownUnknown
Commercial useCommercial use: permittedCommercial use: permitted
Knowledge cutoff--

Pricing and availability

Pricing attributeDeepSeek R1 0528Qwen3-235B-A22B
Input price$0.50/1M tokens$0.09/1M tokens
Output price$2.15/1M tokens$0.58/1M tokens
Providers

Capabilities

CapabilityDeepSeek R1 0528Qwen3-235B-A22B
VisionNoNo
MultimodalNoNo
ReasoningYesNo
JSON / Tool useNoNo
Structured outputsYesYes
Code executionYesNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

BenchmarkDeepSeek R1 0528Qwen3-235B-A22B
MMLU PRO85.082.8
Google-Proof Q&A81.086.1
LiveCodeBench73.380.4
AIME 202491.485.7
Aider Polyglot71.459.6

Continue comparing

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