Qwen3 Coder Next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per token, delivering performance comparable to models with 10 to 20x higher active compute, which makes it well suited for cost-sensitive, always-on agent deployment.

The model is trained with a strong agentic focus and performs reliably on long-horizon coding tasks, complex tool usage, and recovery from execution failures. With a native 256k context window, it integrates cleanly into real-world CLI and IDE environments and adapts well to common agent scaffolds used by modern coding tools. The model operates exclusively in non-thinking mode and does not emit blocks, simplifying integration for production coding agents.

alibaba/qwen3-coder-next

Organization: Alibaba
Family: qwen
Providers: 11
Context: 262,144
Output limit: 65,536
Knowledge: 2025-09
Release: 2026-02-03
Updated: 2026-02-03
Weights: Open
Input: text
Output: text
Capabilities: Tools, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

17 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Amazon Bedrock	qwen.qwen3-coder-next	262,144	65,536	$0.50 / $1.20	No	Yes	Yes	View
Cortecs	qwen3-coder-next	256,000	256,000	$0.167 / $0.891	No	Yes	Yes	View
Eden AI	qwen/qwen3-coder-next	262,144	65,536	$0.30 / $1.50	No	Yes	Yes	View
Eden AI	qwen/qwen3-coder-next@eu	262,144	65,536	$0.30 / $1.50	No	Yes	Yes	View
Kilo Gateway	qwen/qwen3-coder-next	262,144	235,929	$0.30 / $1.50	No	Yes	Yes	View
LLM Gateway	embercloud/qwen3-coder-next	262,144	262,144	$0.108 / $0.675	No	Yes	No	View
Merge Gateway	qwen/qwen3-coder-next	262,144	65,536	$0.15 / $0.80	No	No	No	View
NanoGPT	qwen/qwen3-coder-next	262,144	65,536	$0.20 / $1.50	No	Yes	Yes	View
Ofox	bailian/qwen3-coder-next	262,144	65,536	$0.20 / $1.50	No	Yes	Yes	View
Ofox	qwen/qwen3-coder-next	256,000	64,000	$0.20 / $1.50	No	Yes	Yes	View
Alibabavia OpenRouter	qwen/qwen3-coder-next unknown	262,144	65,536	$0.30 / $1.50	No	Yes	No	View
Novitavia OpenRouter	qwen/qwen3-coder-next fp8	262,144	65,536	$0.20 / $1.50	No	Yes	No	View
Parasailvia OpenRouter	qwen/qwen3-coder-next bf16	262,144	235,929	$0.12 / $0.80	No	Yes	Yes	View
PrimeIntellectvia OpenRouter	qwen/qwen3-coder-next unknown	262,144	235,929	$0.30 / $1.50	No	Yes	No	View
StreamLakevia OpenRouter	qwen/qwen3-coder-next unknown	256,000	64,000	$0.18 / $0.90	No	Yes	No	View
Opper	qwen3-coder-next	262,144	65,536	$0.5811 / $2.3244	No	Yes	Yes	View
Vercel AI Gateway	alibaba/qwen3-coder-next	256,000	256,000	$0.50 / $1.20	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.108Per 1M input tokens

Output from$0.675Per 1M output tokens

Available offers17Across 11 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 5 lowest-priced configurations

InputOutput

Parasailparasail/bf16

$0.12$0.80

StreamLakestreamlake

$0.18$0.90

Novitanovita/fp8

$0.20$1.50

Alibabaalibaba

$0.30$1.50

PrimeIntellectprimeintellect

$0.30$1.50

qwen/qwen3-coder-nextObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.12
Output: $0.80
Cache read: $0.07

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Alibabaalibaba	$0.30	$1.50	—	—
Novitanovita/fp8	$0.20	$1.50	—	—
Parasailparasail/bf16	$0.12	$0.80	$0.07	—
PrimeIntellectprimeintellect	$0.30	$1.50	—	—
StreamLakestreamlake	$0.18	$0.90	$0.036	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 5 endpoints

P50P75P90P99

Alibabaalibaba

946–25,953.8 ms

Novitanovita/fp8

1,959–11,585.42 ms

Parasailparasail/bf16

735.5–1,969 ms

PrimeIntellectprimeintellect

2,758.5–31,633.26 ms

StreamLakestreamlake

1,207–5,956.53 ms

All latency percentiles 5 endpoints

Endpoint	P50	P75	P90	P99
Alibabaalibaba	946 ms	1,582 ms	3,674.2 ms	25,953.8 ms
Novitanovita/fp8	1,959 ms	3,020 ms	4,266.2 ms	11,585.42 ms
Parasailparasail/bf16	735.5 ms	954 ms	1,213 ms	1,969 ms
PrimeIntellectprimeintellect	2,758.5 ms	12,119.75 ms	12,692.9 ms	31,633.26 ms
StreamLakestreamlake	1,207 ms	1,882.25 ms	2,727.4 ms	5,956.53 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 5 endpoints

P50P75P90P99

Alibabaalibaba

69–187.84 t/s

Novitanovita/fp8

32–189.4 t/s

Parasailparasail/bf16

44–68 t/s

PrimeIntellectprimeintellect

26–180.08 t/s

StreamLakestreamlake

59–201.88 t/s

All throughput percentiles 5 endpoints

Endpoint	P50	P75	P90	P99
Alibabaalibaba	69 t/s	143 t/s	168.4 t/s	187.84 t/s
Novitanovita/fp8	32 t/s	66 t/s	156.4 t/s	189.4 t/s
Parasailparasail/bf16	44 t/s	54 t/s	60 t/s	68 t/s
PrimeIntellectprimeintellect	26 t/s	149 t/s	162.8 t/s	180.08 t/s
StreamLakestreamlake	59 t/s	85 t/s	118.2 t/s	201.88 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 5 endpoints

Endpoint5 minutes30 minutes24 hours

AlibabaalibabaObserved Oct 4, 2026, 11:31 AM UTC

—

99.42%

Novitanovita/fp8Observed Oct 4, 2026, 11:31 AM UTC

—

99.74%

Parasailparasail/bf16Observed Oct 4, 2026, 11:31 AM UTC

100%

99.98%

PrimeIntellectprimeintellectObserved Oct 4, 2026, 11:31 AM UTC

—

99.81%

StreamLakestreamlakeObserved Oct 4, 2026, 11:31 AM UTC

98.31%

99.82%

99.59%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

qwen/qwen3-coder-nextObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 40

Coding

36.2

Agentic

0.9

Intelligence

9.2

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

tau bench verified airlineQwen: Qwen3 Coder Next

54.963%

gpqa diamondQwen: Qwen3 Coder Next

74.579%

Evaluation	Configuration	Source	Results	Details
tau bench verified airline	Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next-2025-02-03	OpenRouter	54.963%	Details
gpqa diamond	Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next-2025-02-03	OpenRouter	74.579%	Details
Composite indices	Qwen3 Coder Nextqwen/qwen3-coder-next-2025-02-03	Artificial Analysis	Intelligence 9.2 · Coding 36.2 · Agentic 0.9	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Sep 27, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	qwen/qwen3-coder-next-2025-02-03	2–9 turns	$0.006511	Details
Claude Code	qwen/qwen3-coder-next-2025-02-03	2–9 turns	$0.010508	Details
Hermes Agent	qwen/qwen3-coder-next-2025-02-03	10–49 turns	$0.07113	Details

Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

qwen/qwen3-coder-nextObserved Oct 4, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 235,929
Tokenizer: Qwen
Input: text
Output: text
Moderation: No
Added to OpenRouter: 2026-02-04

Base URLhttps://openrouter.ai/api/v1

Model IDqwen/qwen3-coder-next

Version IDqwen/qwen3-coder-next-2025-02-03

Weights IDQwen/Qwen3-Coder-Next

Supported parameters

frequency_penalty
logit_bias
logprobs
max_tokens
presence_penalty
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

Default parameters

top p: 0.95
temperature: 1

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Qwen3 Coder Next cost?

Listed rates start at $0.108 per million input tokens and $0.675 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Qwen3 Coder Next?

There are 17 cataloged offers across 11 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 8a29bd927f14
Sep 12, 2026 · d203c4c85849