Sulat.com
AI models
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Clarifai logo

Model details

Qwen3 Coder 30B A3B Instruct

Qwen3 Coder 30B A3B Instruct is a streamlined member of the Qwen3-Coder family, positioned for advanced code generation and agentic software tasks. Its mixture-of-experts architecture combines 30.5 billion parameters with 128 experts while activating 8 for each forward pass, aiming to balance broad coding capability with more efficient computation than activating the full parameter set.

The model is especially suited to coding workflows that require work across substantial repositories, including interpreting code, generating implementations, and interacting with tools. A community-distributed Q4 K XL build demonstrates local use in coding tools such as Claude Code and OpenCode, while OpenRouter describes an intended role in repository-scale understanding and agentic tool use. Exact context and pricing claims are not included here because the supplied evidence reports differing service-specific values.

Clarifaiqwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instructqwen

Quick Info

Powered by
Provider
Clarifai
Model key
qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct
Release date
Jul 31, 2025
Last updated
Feb 12, 2026
Knowledge cutoff
2025-04
Input modalities
Output modalities
Capabilities

Cost

Input token cost
$0.11458
Output token cost
$0.74812

Limits

Output tokens
65,536 tokens
Context window
262,144 tokens

Transparent token rates

Compare Qwen3 Coder 30B A3B Instruct pricing

Rates are shown per one million tokens. Combined means one million input plus one million output tokens.

Browse this family

Latest news about Qwen3 Coder 30B A3B Instruct

Clarifai

CoverageBenchmark

OpenRouter lists Qwen3 Coder 30B A3B Instruct as a 30.5-billion-parameter Mixture-of-Experts coding model with 128 experts and eight active per forward pass. The supplied excerpt says it targets advanced code generation, repository-scale understanding, and agentic tool use, including function calls, browser use, and st The model supports a native 256K-token context, with Yarn extension up to one million tokens, and works with OpenAI-compatible tool-use formats without thinking mode. OpenRouter lists a 262K context and released the model on July 31, 2025; its listed price is $0.07 per million input tokens and $0.27 per million output

Videos about Qwen3 Coder 30B A3B Instruct

More models around Qwen3 Coder 30B A3B Instruct