modelgrep
Q

Qwen: Qwen3 Coder Next

qwen/qwen3-coder-next

85th smartest of 179Cheaper than 79% of paidToolsJSON
Use via OpenRouter ↗
Intelligence
28.3
85th of 179
Design Elo
Speed
84
85th fastest
Latency
565ms
first token
Input price
$0.110
64th cheapest
Context
262K
262K max out

How it compares

Smarter than53%
of all ranked models
Faster than72%
of all ranked models
Cheaper than79%
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 · via OpenRouter
Artificial Analysis50th percentile
Intelligence Index
28.3
Coding Index
22.9
Agentic Index
42.1
GPQA Diamond
74%
Humanity's Last Exam
9%
SciCode
32%
Tau²-Bench (agentic)
80%

Providers & pricing (5)

ProviderIn $/MOut $/MUptime
Ionstreamfp8$0.110$0.800100%
Parasailbf16$0.120$0.800100%
StreamLake$0.180$0.900
AtlasCloudfp8$0.180$1.35
Novitafp8$0.200$1.50

Specifications

Context window262K
Max output262K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.070/M
ModeratedNo

Qwen3 Coder Next FAQ

How much does Qwen3 Coder Next cost?

Qwen3 Coder Next costs $0.110 per million input tokens and $0.800 per million output tokens via OpenRouter, making it 64th cheapest of 298 paid models.

How smart is Qwen3 Coder Next?

Qwen3 Coder Next scores 28.3 on the Artificial Analysis Intelligence Index, ranking 85th of 179 benchmarked models, with a GPQA Diamond score of 74%.

How fast is Qwen3 Coder Next?

Qwen3 Coder Next generates around 84 tokens per second with 565ms time-to-first-token (p50), the 85th fastest tracked model.

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.

Compare head-to-head