Skip to content

Qwen2.5 72B Instruct

text → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.296

at DeepInfra

Input / output
$0.288 / $0.32
Providers
1
Spread
1.25×
7 days
−20.0%
30 days
−20.0%
Context
32K
Prices per 1M tokens, blended: DeepInfra (fp8/flex) $0.296, DeepInfra $0.37.

Providers

  • DeepInfraCheapest
    fp8/flex
    $0.296
    $0.288 in · $0.32 out
    ref vs ref
    32K ctx100% uptimefp8
  • $0.37
    $0.36 in · $0.40 out
    +25% vs ref
    32K ctx97.9% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.296 = median of cheapest 20%.

Price history

USD per 1M tokens · each step is a price change

Prices in USD / 1M tokens.

No provider has changed its price since tracking began on Oct 3, 2026.

Changes

  • Now served,
    Listed
  • No longer served,
    Delisted

About

The cheapest provider for Qwen2.5 72B Instruct is DeepInfra at $0.296 per 1M tokens (blended), charging $0.288 per 1M input and $0.32 per 1M output tokens. It is served by a single provider. Its best price fell 20.0% over the last 30 days. Context window: 32K tokens. Prices tracked since Oct 3, 2026.

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...
Released
Sep 19, 2024
First tracked
Oct 3, 2026
Canonical slug
qwen/qwen-2.5-72b-instruct
Weights
Qwen/Qwen2.5-72B-Instruct