Qwen2.5 7B Instruct Turbo

$0.3
Input / MTok
$0.3
Output / MTok

Hosted third-party inference; price is Together's serverless rate, not the model originator's first-party API.

API identifier Qwen/Qwen2.5-7B-Instruct-Turbo · Context 32,768 tokens · vendor pricing page

Full price sheet

MetricUSD / million tokens
Input$0.3
Output$0.3

Price history

ObservedMetric Price
2026-08-07 13:03:13 Input $0.3
2026-08-07 13:03:13 Output $0.3

Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.

Changes affecting this model

coverage
Qwen2.5 7B Instruct Turbo added to coverage
2026-08-07

Compare with

Models at a similar price point.

ModelInputOutput
GPT-5 nano $0.05$0.4 compare →
GPT-4.1 nano $0.1$0.4 compare →
Gemini 2.5 Flash-Lite $0.1$0.4 compare →
Devstral Small 2 $0.1$0.3 compare →
DeepSeek V4 Flash $0.14$0.28 compare →
DeepSeek V4 Flash (0731) $0.14$0.28 compare →