Qwen: Qwen3 Coder Next
qwen/qwen3-coder-next
120th smartest of 182Cheaper than 81% of paidToolsJSON
Intelligence
21.1
120th of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.120
63rd cheapest
Context
262K
262K max out
How it compares
Smarter than34%
of all ranked models
Cheaper than81%
of all ranked models
Overview
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...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis63th percentile
Intelligence Index
21.1
Coding Index
36.2
GPQA Diamond
74%
Humanity's Last Exam
9%
SciCode
32%
Tau²-Bench (agentic)
80%
Providers & pricing (5)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Ionstreamfp8 | $0.110 | $0.800 | 262K | 96.2% |
| Parasailbf16 | $0.120 | $0.800 | 262K | 100% |
| StreamLake | $0.180 | $0.900 | 256K | 99.6% |
| Novitafp8 | $0.200 | $1.50 | 262K | — |
| Alibaba | $0.300 | $1.50 | 262K | 99.6% |
Specifications
Context window262K
Max output262K
Knowledge cutoff—
Input modalitiestext
Output modalitiestext
Prompt caching—
Cache read price$0.070/M
ModeratedNo
Open weightsQwen/Qwen3-Coder-Next ↗
Qwen3 Coder Next FAQ
How much does Qwen3 Coder Next cost?
Qwen3 Coder Next costs $0.120 per million input tokens and $0.800 per million output tokens via OpenRouter, making it 63rd cheapest of 332 paid models.
How smart is Qwen3 Coder Next?
Qwen3 Coder Next scores 21.1 on the Artificial Analysis Intelligence Index, ranking 120th of 182 benchmarked models, with a GPQA Diamond score of 74%.
What is Qwen3 Coder Next's context window?
Qwen3 Coder Next supports a 262K-token context window and can output up to 262K tokens. It accepts text input.