Currently listed through these providers:
Model details
Qwen3 Coder 480B A35B Instruct (NovitaAI)
Qwen3 Coder 480B A35B Instruct is positioned as an open coding model from Alibaba's Qwen3 family, designed to handle agentic programming, browser automation, and the kinds of day-to-day development tasks where Claude Sonnet has historically been a strong baseline. With 480 billion total parameters and roughly 35 billion active per pass, it follows a Mixture-of-Experts-style routing that lets a relatively small active slice handle each request while the larger pool stays available for difficult code reasoning, long-context refactors, and multi-step tool use. The gateway listing presents it as a general-purpose coding assistant rather than a chat-only model, with advertised support for function calling, structured output, and reasoning, making it a fit for workflows that mix natural-language instructions with real tool calls and code edits.
In practical terms, the model is aimed at developers who want a coding-focused open model that can keep up with long sessions, since the listing exposes a 262K context window and a high max-output allowance for sustained agentic workflows such as multi-file edits, repository-wide reasoning, and browser-driven automation. It is well suited to code generation, refactoring assistance, code review, and tool-augmented pipelines where a step-by-step reasoning trace improves reliability. Teams that already rely on Qwen-family tooling or who want an open-weight alternative for code-centric workloads can treat this variant as a strong candidate for pairing with external developer tools and IDE integrations.
Quick Info
Powered by- Provider
- LLM Gateway
- Model key
- novita/qwen3-coder-480b-a35b-instruct
- Release date
- Apr 1, 2025
- Last updated
- Apr 1, 2025
- Knowledge cutoff
- 2025-04
- Input modalities
- Output modalities
- Capabilities
Cost
- Input token cost
- $0.38
- Output token cost
- $1.55
Limits
- Output tokens
- 65,536 tokens
- Context window
- 262,144 tokens
Transparent token rates
Compare Qwen3 Coder 480B A35B Instruct (NovitaAI) pricing
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
Latest news about Qwen3 Coder 480B A35B Instruct (NovitaAI)
We haven't found any news about Qwen3 Coder 480B A35B Instruct (NovitaAI) yet. New models can take a few days to get coverage, so check back soon or look again now.
