Last verified
RETIRING OCT 10 2026CODE MODEL262K CONTEXTTEXT APIINTERNATIONAL

Qwen3 Coder Next API Pricing

Retiring October 10, 2026: Alibaba has announced that qwen3-coder-next goes offline on that date, after which calls fail. Alibaba recommends Qwen3.7 Plus instead. Qwen3 Coder Next is Alibaba's code-generation model for repository-level work and multi-turn tool interactions. The official International 0-32K tier lists $0.30/M input and $1.50/M output.

Input - per 1M tokens
$0.30/M
International 0-32K input tier 0-32K
Output - per 1M tokens
$1.50/M
Output 0-32K input tier 0-32K
Cache N/A
$0.30/M
Cache no public rate not listed
Effective - agentic blend
$0.396/M
92/8 split - no cache discount
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with Qwen3 Coder Next International list pricing. Alibaba publishes higher 32K-128K and 128K-256K tiers; the quote board uses the public 0-32K baseline.

$ /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

$0.032/task
80,000 in / 5,000 out~3,174 tasks/$100
CODE REVIEW

Pull request review

$0.013/review
30,000 in / 3,000 out~7,407 reviews/$100
TEST GEN

Unit test drafting

$0.00585/task
12,000 in / 1,500 out~17,094 tasks/$100
CHATBOT

Developer assistant

$0.0015/turn
2,500 in / 500 out~66,666 turns/$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 394
Words 55
Tokens (estimated) 75 tokens
Cost as input · uncached $0.00002 USD
Cost as output · uncached $0.00011 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Qwen3 Coder Next Current $0.30 $1.50 $0.396 agentic 92/8 262K Repository-level coding and tool use
Qwen3 Coder Plus $1.00 $5.00 $1.32 deprecated · +3.3× 1M Agentic coding and code review
Qwen 3.5 Plus $0.40 $2.40 $0.56 +41% 256K General Qwen production workloads
Qwen 3.5 Flash $0.10 $0.40 $0.124 −3.2× 1M Cheap long-context Qwen traffic
Qwen3 Coder Flash $0.30 $1.50 $0.396 same 1M High-volume coding assistants
QwQ Plus $0.80 $2.40 $0.928 deprecated · +2.3× 131K Proprietary reasoning workloads

Frequently asked.

Practical Qwen3 Coder Next pricing questions, with International list prices separated from long-context tiers and model capabilities.

Q · 01 When does Qwen3 Coder Next stop working? +
Alibaba announced on June 8, 2026 that qwen3-coder-next 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 Next priced at? +
Alibaba lists $0.30/M input and $1.50/M output for the International 0-32K tier, verified 2026-06-20.
Q · 03 Does pricing change with a long prompt? +
Yes. Alibaba lists $0.50/$2.50 for 32K-128K input and $0.80/$4.00 for 128K-256K. The headline tiles use the 0-32K baseline.
Q · 04 Is a cache-read price published? +
No. The model supports cache, but the official International price table does not itemize a cache-read token price. This page does not assume a discount.
Q · 05 What context and output limits apply? +
The official Qwen Cloud page lists 262.14K context, 204.80K maximum input, and 65.53K maximum output tokens.
Q · 06 Which model ID should I use? +
Use qwen3-coder-next with the DashScope-compatible endpoint shown in Qwen Cloud documentation.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against alibabacloud.com · Last verified Jun 20, 2026
Methodology Report a correction More by Y.V.