Qwen3 Coder Plus
Qwen’s specialized software engineering foundation model. Optimized for multi-file repository understanding, automated test synthesis, complex refactoring, and deterministic syntax execution across a 128K-token context window.
Qwen
Alibaba US
Dense Code Transformer
Optimized (~320ms TTFT)
Industry Benchmarks & Evaluations
Autonomous software engineering & real-world GitHub bug resolution.
Single-function code generation and algorithm synthesis.
Contamination-free competitive programming evaluation.
Cross-file dependency and codebase architecture comprehension.
Full codebase retrieval fidelity across 128K tokens.
Pricing
Rates are read live
Pricing for qwen3-coder-plus is fetched from the live catalogue on load, so it is never served from a cache that could outlive a repricing.
Specifications
128.0K
tokens16K
tokenscode
Context window, compared
Bars are scaled to 128K tokens. A model with no published context window reads Unknown, never zero.
Usage on nRouter
Usage is temporarily unavailable
Our aggregate read failed, so we cannot report traffic for this model right now.
Availability
Availability is temporarily unavailable
Our own telemetry read failed, so we cannot report uptime or latency for this model right now. This says nothing about the model itself — it is not an outage, and we would rather show you nothing than a figure we did not measure.
Managed Gateway Routing
Unified single-key access with automatic multi-region fallback, real-time credit enforcement, and sub-millisecond routing latency.