Skip to main content

Qwen2.5 72B Instruct

**This repo contains the instruction-tuned 72B Qwen2.5 model**, which has the following features:

Input / output price
$0.36 / $0.40 per 1M
Context
33K tokens
Released
Sep 19, 2024
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "qwen2.5-72b-instruct".

Read docs

Providers

3 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
DeepInfradeepinfra/qwen-2.5-72b-instruct
$0.36/M$0.40/M
Featherlessfeatherless/qwen-2.5-72b-instruct
$0.37/M$0.40/M
OpenRouteropenrouter/qwen-2.5-72b-instruct
$0.36/M$0.40/M

Is a provider down? OpenRouter status

Pricing

Averaged across 3 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.36 per 1M
Average output
$0.40 per 1M
Average cache read
$1.00 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.37/MFeatherlessLowest$0.36/MDeepInfra and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

13tokens/sacross providers

Faster than 23% of the other 599 models on the gateway

Response latency

Lower is better

1.2sacross providers

Faster than 63% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 6 published scores from 4 sources, each linked to where it was published.

10.0/ 100

Respan Index#173 of 176

176 ranked models. The shaded band is this model's 95% interval, 8.4 to 13.2. GPT-4o mini and Phi-4 fall inside it, so the gap is within the margin of error.
Qwen2.5 72B Instruct by category: Coding 0.9, Agents 1.9, Reasoning 16.6, Knowledge & language 3.0 (estimated), Human preference 32.2
  1. 173Qwen2.5 72B Instruct10.0
  2. 171GPT-4o mini10.7
  3. 174Phi-49.3

Published scores

BenchmarkScore
WeirdMLHåvard Tveit Ihle16%

Compare Qwen2.5 72B Instruct: Qwen2.5 72B Instruct vs Qwen3.8-Max, Qwen2.5 72B Instruct vs Qwen3.8-Flash-Next, Qwen2.5 72B Instruct vs Qwen3.7-Max, Qwen2.5 72B Instruct vs Qwen3.8 27B, Qwen2.5 72B Instruct vs Qwen3.6-Max-Preview, Qwen2.5 72B Instruct vs Qwen3.7-Plus

Apps

Use Qwen2.5 72B Instruct in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Qwen2.5 72B Instruct FAQ

Short answers, built from the data on this page.

Qwen2.5 72B Instruct is a model from Qwen, released on Sep 19, 2024. **This repo contains the instruction-tuned 72B Qwen2.5 model**, which has the following features:.

On the Respan gateway, input starts at $0.36 per 1M tokens on DeepInfra and OpenRouter, and output starts at $0.40 per 1M tokens on every provider, after gateway discounts. Averaged across its 3 providers, it costs $0.36 per 1M input tokens and $0.40 per 1M output tokens.

Qwen2.5 72B Instruct is available through 3 providers: DeepInfra, Featherless, and OpenRouter.

Qwen2.5 72B Instruct accepts up to 33K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen2.5-72b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Qwen2.5 72B Instruct scores 10.0 out of 100 on the Respan Index v1.1, ranking #173 of 176 models. By category: Coding 0.9, Agents 1.9, Reasoning 16.6, Knowledge & language 3.0 (estimated), and Human preference 32.2. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Qwen2.5 72B Instruct has 6 published benchmark scores, including WeirdML 16%, BALROG 16.2%, and GPQA Diamond 49.1%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.