Context
33K
Max output
33K
Serving providers
1
Cheapest input
$0.90 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
EvalComputeProxy62.7default
GPQA Diamond37%default
Humanity's Last Exam4%default
LiveCodeBench16%default
MMLU-Pro62%default
SciCode23%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Fireworks AICheapest$0.90$0.901
ComponentUnitStandardBatchCached
Text input/1M tok$0.9000
Text output/1M tok$0.9000

Price history

input + output $/1M since we started tracking
Input Output
Input down 61% since first tracked
$0.000$0.500$1.00Jul 15Aug 22Jun 22$0.400$0.350

Cost calculator

estimate your monthly spend on this model
$252
estimated / month

Model IDs

copy the exact identifier for your platform
fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct

Frequently asked questions

Qwen2 72B Instruct pricing, context and availability

How much does Qwen2 72B Instruct cost?

Qwen2 72B Instruct costs $0.90 per 1M input tokens and $0.90 per 1M output tokens at its cheapest provider via Fireworks AI.

What is the context window of Qwen2 72B Instruct?

Qwen2 72B Instruct accepts up to 33K tokens of context and can return up to 33K output tokens.

What can Qwen2 72B Instruct do?

Qwen2 72B Instruct supports structured output.

Other Alibaba models

compare pricing across the Alibaba lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI