← All models
Flash — fastest and cheapest, lighter reasoningOpen Weights
Qwen2.5 7B Instruct Pricing
Qwen · qwen-qwen-2-5-7b-instruct
Input / 1M tokens
$0.100
Output / 1M tokens
$0.200
Context window
32,768 tokens
≈ 44 pages of text
Max output
32,768 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0002
1,000 requests / month$0.2/mo10,000 requests / month$2.00/mo100,000 requests / month$20.00/moEstimate your own workloadOpens the calculator with Qwen2.5 7B 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 instruction following, coding, and math performance for a 7B model. Low inference cost with 128k context support.
The business tradeoff
Reasoning depth and consistency lag behind 32B+ models in the same series. Output quality varies with hosting and quantization choices.
Head-to-head
Vendor list rates, as of Jul 30, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.