← All models
Flagship — best answers, highest costOpen Weights
Qwen3 235B A22B Instruct 2507 Pricing
Qwen · qwen-qwen3-235b-a22b-2507
Input / 1M tokens
$0.090
Output / 1M tokens
$0.550
Context window
262,144 tokens
≈ 350 pages of text
Max output
16,384 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0003
1,000 requests / month$0.328/mo10,000 requests / month$3.28/mo100,000 requests / month$32.80/moEstimate your own workloadOpens the calculator with Qwen3 235B A22B Instruct 2507 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 multilingual, coding, and long-context tasks with 256k token context support.
The business tradeoff
Open-weights release requires self-hosting or third-party inference, creating variable latency and infrastructure costs.
Head-to-head
Vendor list rates, as of Jul 12, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.