GPT-5.6 Luna vs Qwen3-Coder 30B-A3B Instruct

OpenAIActive

GPT-5.6 Luna

$0.06 / $0.37 · 1,050,000 ctx · 37 providers

AlibabaActive

Qwen3-Coder 30B-A3B Instruct

$0.06 / $0.24 · 262,144 ctx · 20 providers

01Differences

At a glance

Computed automatically from tracked data.

• GPT-5.6 Luna's output price is 34% lower than Qwen3-Coder 30B-A3B Instruct's ($0.37 vs $0.24 per 1M).

• GPT-5.6 Luna has a 4× larger context window (1,050,000 vs 262,144 tokens).

• They differ in reasoning (GPT-5.6 Luna: Yes, Qwen3-Coder 30B-A3B Instruct: No) and open weights (GPT-5.6 Luna: No, Qwen3-Coder 30B-A3B Instruct: Yes).

02Specs

Side by side

	GPT-5.6 Luna	Qwen3-Coder 30B-A3B Instruct
Input / 1M	$0.06	$0.06
Output / 1M	$0.37	$0.24
Context	1,050,000	262,144
Max output	128,000	262,144
Providers	37	20
Released	2026-07-09	2025-04

03Prices

Common providers

Provider	GPT-5.6 Luna	Qwen3-Coder 30B-A3B Instruct
cortecs	$0.22 / $1.32	$0.07 / $0.24
edenai	$0.20 / $1.20	$0.45 / $2.25
kilo	$0.20 / $1.20	$0.29 / $1.46
llmgateway	$0.20 / $1.20	$0.07 / $0.27
llmgateway-providers	$0.22 / $1.32	$0.07 / $0.27
nano-gpt	$0.20 / $1.20	$0.10 / $0.40
openrouter	$0.20 / $1.20	$0.07 / $0.28

04History

Recent changes

GPT-5.6 Luna

2026-09-10 — Added amazon-bedrock

2026-09-10 — Added bothub

2026-09-08 — Added 302ai

2026-09-08 — Added amazon-bedrock

2026-09-06 — Status azure

Qwen3-Coder 30B-A3B Instruct

2026-09-02 — Context cortecs

2026-08-25 — Context kilo

2026-08-25 — Context openrouter

2026-08-20 — Added llmgateway-providers

2026-08-14 — Added edenai