Qwen2.5 VL 72B Instruct API pricing

5 providers serve Qwen2.5 VL 72B Instruct. Qwen2.5 VL 72B Instruct is a proprietary API model, up to 131K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-08-23 · list prices from provider APIs
Input floor $0.130/1M at Nebius Output floor $0.400/1M at Nebius Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
Nebius $0.130 $0.400output floor - 131K Use
Novita AI $0.800 $0.800 - 33K Use
OpenRouter marketplace quote $0.800 $1.00 $0.400 128K Use
Fireworks AI $0.900 $0.900 - 128K Use
OVHcloud $0.910 $0.910 - 32K Use

The cheapest way to run Qwen2.5 VL 72B Instruct

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $21.10/month, at Nebius. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
Qwen2p5-Coder-32b $0.060 $0.200 5
Qwen2p5-72b $0.120 $0.300 4
Qwen2.5-Coder-7B $0.010 $0.030 4
Qwen2.5-7B-Instruct $0.040 $0.070 3

FAQ

What is the cheapest API for Qwen2.5 VL 72B Instruct?

As of 2026-08-23, the lowest input price for Qwen2.5 VL 72B Instruct is Nebius at $0.130 per 1M input tokens. The lowest output price is Nebius at $0.400 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is Novita AI at $0.800, a 515% difference.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON