Models/Qwen/Qwen2.5 72B Instruct

Qwen2.5 72B Instruct

Name: Qwen2.5 72B Instruct API access
Brand: Qwen

Qwen · Open weights · Released Sep 19, 2024 · qwen/qwen-2.5-72b-instruct

Best $0.36 in / $0.40 out via DeepInfra · fp8

Compare Estimate cost

33K contextToolsStructured outputOpen weights

Available from 2 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 2 DAYS AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
DeepInfra	$0.36	$0.40	—	33K	fp8	2.2s	30 tok/s	91.5%
Novita	$0.38	$0.40	—	32K	bf16	✕	✕	83.5%

TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 2 days ago

SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →

About

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

Specifications

Context window32,768

Max output16,384

Modalities intext

Modalities outtext

LicenseOpen weights

ReleasedSep 19, 2024

Knowledge cutoff2024-06-30

TokenizerQwen

WeightsHugging Face ↗

Open weights

Hugging FaceQwen/Qwen2.5-72B-Instruct ↗

Downloads287K

Likes1K

Licenseother

safetensors

Qwen3.8 Max Prime$4.00 / $12.00 Qwen3.8 Omni Flash$0.15 / $0.47 Qwen3.8 Max (0902)$2.00 / $6.00 Qwen3.8 Flash$0.15 / $0.47

Embed badge

Qwen2.5 72B Instruct price and speed badge

[![Qwen2.5 72B Instruct](https://modelindex.ai/badge/qwen/qwen-2.5-72b-instruct)](https://modelindex.ai/models/qwen/qwen-2.5-72b-instruct)

Sources

OpenRouter API23 minutes ago

AGGREGATOR

Hugging Face23 minutes ago

COMMUNITY

ModelIndex benchmarks2 days ago

MEASURED

Verified 23 minutes ago · list prices, not negotiated rates.