Qwen3-Coder-480B-A35B vs Claude Sonnet 4.5

Qwen3-Coder-480B-A35B is cheaper than Claude Sonnet 4.5 by about 90% on a blended (75% input / 25% output) basis. Qwen3-Coder-480B-A35B charges $0.22 / $1.80 per 1M input/output tokens; Claude Sonnet 4.5 charges $3.00 / $15.00.

FieldQwen3-Coder-480B-A35BClaude Sonnet 4.5
Input $/Mtok$0.22$3.00
Output $/Mtok$1.80$15.00
Cache read $/Mtok$0.0220$0.30
Cache write $/Mtok–$3.75
Input $/Mchar0.0663n/a
Output $/Mchar0.54n/a
Context window262144200000
Tokenizerqwen2claude
Confidence?aggregatorofficial
Sourcelitellmofficial-anthropic

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-A35BClaude Sonnet 4.5
Coding agent$2.99$36.00
RAG chat$4.57$48.00
Summarisation (batch)$3.78$42.00
Classification$2.52$32.40
Chat assistant$8.52$78.00
Content generation$14.84$126.00

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

Batch pricing not published for Claude Sonnet 4.5; standard rate used for the batch share of a workload.

Cite this page

Qwen3-Coder-480B-A35B vs Claude Sonnet 4.5: $0.22/$1.80 vs $3.00/$15.00 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-anthropic_claude-sonnet-4-5

Qwen3-Coder-480B-A35B page | Claude Sonnet 4.5 page | Open Qwen3-Coder-480B-A35B in calculator | Open Claude Sonnet 4.5 in calculator