Qwen3-Coder-480B-A35B vs DeepSeek V3.2 (chat)

DeepSeek V3.2 (chat) is cheaper than Qwen3-Coder-480B-A35B by about 49% on a blended (75% input / 25% output) basis. Qwen3-Coder-480B-A35B charges $0.22 / $1.80 per 1M input/output tokens; DeepSeek V3.2 (chat) charges $0.28 / $0.42.

FieldQwen3-Coder-480B-A35BDeepSeek V3.2 (chat)
Input $/Mtok$0.22$0.28
Output $/Mtok$1.80$0.42
Cache read $/Mtok$0.0220$0.0280
Cache write $/Mtok––
Input $/Mchar0.06630.0918
Output $/Mchar0.540.14
Context window262144128000
Tokenizerqwen2deepseek
Confidence?aggregatoraggregator
Sourcelitellmlitellm

Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence

Price history

No price changes recorded yet for either model.

Same workload, monthly cost

Illustrative monthly cost at 10M tokens/month, split per workload preset. Not a substitute for the calculator, which uses your own volume, cache and batch assumptions.

WorkloadQwen3-Coder-480B-A35BDeepSeek V3.2 (chat)
Coding agent$2.99$2.87
RAG chat$4.57$3.01
Summarisation (batch)$3.78$2.94
Classification$2.52$2.83
Chat assistant$8.52$3.36
Content generation$14.84$3.92

Batch pricing not published for Qwen3-Coder-480B-A35B; standard rate used for the batch share of a workload.

Batch pricing not published for DeepSeek V3.2 (chat); standard rate used for the batch share of a workload.

Cite this page

Qwen3-Coder-480B-A35B vs DeepSeek V3.2 (chat): $0.22/$1.80 vs $0.28/$0.42 per 1M tokens as of 2026-11-19. Token Barometer by Dejan Strbad, https://tokenbarometer.com, data CC BY 4.0. https://tokenbarometer.com/compare/alibaba_qwen3-coder-480b-a35b-vs-deepseek_deepseek-chat

Qwen3-Coder-480B-A35B page | DeepSeek V3.2 (chat) page | Open Qwen3-Coder-480B-A35B in calculator | Open DeepSeek V3.2 (chat) in calculator