← All models
Balanced — strong quality at a mid priceOpen Weights
Qwen3 Coder 30B A3B Instruct Pricing
Qwen · qwen-qwen3-coder-30b-a3b-instruct
Input / 1M tokens
$0.070
Output / 1M tokens
$0.280
Context window
262,144 tokens
≈ 350 pages of text
Max output
235,929 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0002
1,000 requests / month$0.196/mo10,000 requests / month$1.96/mo100,000 requests / month$19.60/moEstimate your own workloadOpens the calculator with Qwen3 Coder 30B A3B Instruct preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Strong results on code generation, completion, and repository-level tasks. Competitive accuracy at low per-token cost for a 30B-scale model.
The business tradeoff
Requires self-hosting with associated deployment and latency overhead. Output token price is nearly four times the input rate.
Head-to-head
Vendor list rates, as of Aug 10, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.