Last verified
RETIRING OCT 10 2026CODE MODEL1M CONTEXTCONTEXT CACHE FLAGGEDSINGAPORE BASELINE

Qwen3 Coder Plus API Pricing

Retiring October 10, 2026: Alibaba has announced that qwen3-coder-plus goes offline on that date, after which calls fail. Alibaba recommends Qwen3.7 Plus instead. Qwen3 Coder Plus is Alibaba's code-specialized Qwen3 model for agentic software work. Alibaba publishes the International / Singapore 0-32K row directly in US dollars: $1/M input and $5/M output.

Input - per 1M tokens
$1.00/M
International 0-32K input tier 0-32K
Output - per 1M tokens
$5.00/M
Output 0-32K input tier 0-32K
Cache flagged
$1.00/M
Cache discount noted, price not itemized not itemized
Effective - agentic blend
$1.32/M
92/8 split - no cache discount
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with the official Qwen3 Coder Plus International/Singapore 0-32K token row, exactly as Alibaba publishes it in US dollars. Alibaba publishes higher prices for longer input bands up to 1M context.

$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

CODING AGENT

Repo patch

$0.160/task
120,000 in - 8,000 out~625 units/$100
CODE REVIEW

Pull request review

$0.063/review
45,000 in - 3,500 out~1,600 units/$100
TEST GEN

Unit test drafting

$0.030/file
18,000 in - 2,500 out~3,278 units/$100
CHATBOT

Developer assistant

$0.007/turn
3,500 in - 700 out~14,285 units/$100
§ 03 / TOKENIZER

Paste text. See tokens. See cost.

What's a token →
Calibrated · measured on the vendor's tokenizer · 2026-06-10 Auto-counts as you type

Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (Qwen/Qwen3.5-397B-A17B, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.

Characters 381
Words 53
Tokens (estimated) 73 tokens
Cost as input · uncached $0.00007 USD
Cost as output · uncached $0.00036 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Qwen3 Coder Plus Current $1.00 $5.00 $1.32 agentic 92/8 1M Agentic coding and code review
Qwen3 Max $1.20 $6.00 $1.58 deprecated · +20% 252K Frontier Qwen proprietary reasoning
Qwen 3.5 Plus $0.40 $2.40 $0.56 −2.4× 256K General Qwen production workloads
Qwen 3.5 Flash $0.10 $0.40 $0.124 −11× 1M Cheap long-context Qwen traffic
Qwen3 Coder Flash $0.30 $1.50 $0.396 −3.3× 1M High-volume coding assistants
QwQ Plus $0.80 $2.40 $0.928 deprecated · −30% 131K Proprietary reasoning workloads
QwQ 32B $0.287 $0.861 $0.333 deprecated · −4.0× 131K Open reasoning on a budget
Qwen3 235B A22B $0.70 $2.80 $0.868 deprecated · −34% 131K Open MoE reasoning baseline
GPT-5.4 mini $0.75 cache $0.075 $4.50 $0.541 −2.4× 400K Coding and computer-use workloads
Gemini 3.8 Flash $0.75 cache $0.075 $3.75 $0.481 −2.7× · promo 1M Low-latency multimodal RAG
DeepSeek V4.1 Flash $0.30 cache $0.006 $1.20 $0.15 −8.8× 1M Ultra-cheap API throughput

Frequently asked.

Practical pricing questions, separated from calculator assumptions and regional tiers.

Q · 01 When does Qwen3 Coder Plus stop working? +
Alibaba announced on June 8, 2026 that qwen3-coder-plus goes offline on October 10, 2026 (00:00, UTC+8) in the Beijing and Singapore regions; after that, calls fail. Its notice recommends Qwen3.7 Plus. Until then the model bills at the rates on this page.
Q · 02 What is Qwen3 Coder Plus priced at? +
Alibaba Cloud Model Studio lists Qwen3 Coder Plus at $1/M input and $5/M output on its International/Singapore 0-32K deployment row. That is a published US dollar list price, not a converted one.
Q · 03 Does this page include higher context pricing tiers? +
The quote tiles use the 0-32K International/Singapore tier. Alibaba also lists 32K-128K at $1.8/M input and $9/M output, 128K-256K at $3 and $15, and 256K-1M at $6 and $60.
Q · 04 Is prompt caching priced separately? +
Alibaba marks Qwen3 Coder Plus as eligible for Context Cache discount, but the pricing table does not publish a separate cache-read token amount. AI//COST therefore keeps cached input at $1/M until Alibaba lists the exact cache-read price.
Q · 05 How is the effective price calculated? +
AI//COST uses the same 92/8 agentic blend everywhere. With no exact cache-read token price published for this row, Qwen3 Coder Plus's effective blended cost is $1.32/M.
Q · 06 Is there a free quota or batch discount? +
Alibaba lists a 90-day activation free quota for many International Qwen rows, but not every open-source row includes one. Batch and context-cache support are model-specific; this page only publishes prices that are explicit in the vendor table.
Q · 07 Which API model ID should I use? +
Use the rolling model ID qwen3-coder-plus. Alibaba states its current capability is equivalent to qwen3-coder-plus-2025-09-23.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against alibabacloud.com · Last verified Jul 27, 2026
Methodology Report a correction More by Y.V.