Question 1

What is Qwen3 Coder 30B A3B Instruct?

Accepted Answer

Qwen3 Coder 30B A3B Instruct is a model from Qwen, released on Jul 31, 2025. Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the Qwen3 architecture, it supports a native context length of 256K tokens (extendable to 1M with Yarn) and performs strongly in tasks involving function calls, browser use, and structured code completion. This model is optimized for instruction-following without “thinking mode”, and integrates well with OpenAI-compatible tool-use formats.

Question 2

How much does Qwen3 Coder 30B A3B Instruct cost?

Accepted Answer

On the Respan gateway, input starts at $0.06 per 1M tokens on Novita, and output starts at $0.24 per 1M tokens on Novita, after gateway discounts. Averaged across 2 providers, it costs $0.07 per 1M input tokens and $0.26 per 1M output tokens.

Question 3

Which providers serve Qwen3 Coder 30B A3B Instruct on Respan?

Accepted Answer

2 providers serve Qwen3 Coder 30B A3B Instruct: Novita and OpenRouter.

Question 4

What is Qwen3 Coder 30B A3B Instruct's context window?

Accepted Answer

Qwen3 Coder 30B A3B Instruct accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Qwen3 Coder 30B A3B Instruct with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "qwen3-coder-30b-a3b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Qwen3 Coder 30B A3B Instruct?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 11 tokens per second, and the lowest response latency was 1.2 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Qwen3 Coder 30B A3B Instruct score on benchmarks?

Accepted Answer

Qwen3 Coder 30B A3B Instruct has 13 published benchmark scores, including SWE-bench Verified (w/ OpenHands, 500 turns) 51.6%, BFCL-v3 62.2%, and TAU-Bench Retail 68.7%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output	Capabilities
NovitaSave 10%`novita/qwen/qwen3-coder-30b-a3b-instruct`	160K	$0.06/M	$0.24/M
OpenRouter`openrouter/qwen/qwen3-coder-30b-a3b-instruct`	262K	$0.07/M	$0.28/M

Qwen3 Coder 30B A3B Instruct

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Coding7

Agents1

Other5

Apps