Qwen2.5 72B Instruct
DeepInfra chatQwen2.5 72B Instruct is a DeepInfra chat model.It supports a 32,768-token context windowwith up to 32,768 output tokens.Input is priced at $0.360/M tokens and output at $0.400/M tokens. Capabilities include function calling. Route Qwen2.5 72B Instruct via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate Qwen2.5 72B Instruct spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $0.3600/M input · $0.4000/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.
Pricing
Per-token rates, expressed in USD per 1M tokens. Verified Oct 22, 2026.
| Input | $0.360/M | |
| Output | $0.400/M | |
| Blended (3:1 in:out) | $0.370/M Cross-model comparable price |
Context & limits
- Context window
- 32,768 tokens
- Max input
- 32,768 tokens
- Max output
- 32,768 tokens
- Modalities
- text
Capabilities
- Function calling ✓ supported
- Parallel tool calls — not advertised
- Vision input — not advertised
- Audio input — not advertised
- Audio output — not advertised
- PDF input — not advertised
- Streaming ✓ supported
- Structured output — not advertised
- Prompt caching — not advertised
- Reasoning — not advertised
Strengths & caveats — when to pick Qwen2.5 72B Instruct
Data-driven from Qwen2.5 72B Instruct's percentile within chat peers.
Where it's strong
- +agentic workflows that depend on reliable tool calls
Watch out for
- !limited context — 32,768-token window is in the bottom quartile; not ideal for long documents or large RAG
- !strict structured output — no JSON-schema enforcement, expect retry loops
Benchmarks pending
We haven't logged public benchmark scores for Qwen2.5 72B Instruct yet. Have one to contribute? Submit a source — citations help us prioritise.
Call Qwen2.5 72B Instruct via Agent Command Center
One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.
agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.# Qwen2.5 72B Instruct via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC
client = AgentCC(
api_key=os.environ["AGENTCC_API_KEY"], # from app.futureagi.com → Settings → API Keys
base_url="https://gateway.futureagi.com/v1",
)
resp = client.chat.completions.create(
model="deepinfra/qwen-qwen2-5-72b-instruct",
messages=[{"role": "user", "content": "Hello, Qwen2.5 72B Instruct!"}],
)
print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")
# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
model="deepinfra/qwen-qwen2-5-72b-instruct",
messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost: ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache: ", raw.headers.get("x-agentcc-cache"))AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗Same model on other providers
qwen-qwen2-5-72b-instruct is also available via 3 other routes. Pricing, regions, and capabilities can differ — compare before routing production traffic.
| Provider | Input / 1M | Output / 1M | Verified |
|---|---|---|---|
| Nebius | $0.130/M | $0.400/M | Oct 22, 2026 |
| Hyperbolic | $0.120/M | $0.300/M | Oct 22, 2026 |
| Together AI | $1.20/M | $1.20/M | Oct 22, 2026 |
Explore similar models
Qwen2.5 72B Instruct doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark. Side-by-side links appear where a comparison page exists; otherwise, open the model profile.
- DeepSeek V4.1 FlashDeepInfra · $0.140/M in · $0.420/M out · 1,048,576 ctxView model →
- DeepSeek V4.1 Flash 1017DeepInfra · $0.140/M in · $0.420/M out · 1,048,576 ctxView model →
- MiniMax M3DeepInfra · $0.280/M in · $1.10/M out · 524,288 ctxView model →
- Thinkingmachines InklingDeepInfra · $0.950/M in · $4.05/M out · 524,288 ctxView model →
FAQ
How much does Qwen2.5 72B Instruct cost?
Input is priced at $0.360 per 1M tokens and output at $0.400 per 1M tokens (DeepInfra, last verified Oct 22, 2026).
What is the context window of Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct supports a 32,768-token context window with up to 32,768 output tokens.
Does Qwen2.5 72B Instruct support function calling?
Yes — Qwen2.5 72B Instruct supports function (tool) calling.
Is Qwen2.5 72B Instruct good for production?
Qwen2.5 72B Instruct is well-suited for agentic workflows that depend on reliable tool calls. Consider alternatives if you need limited context — 32,768-token window is in the bottom quartile; not ideal for long documents or large RAG.
How can I route to Qwen2.5 72B Instruct with fallback?
Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.
Useful links for Qwen2.5 72B Instruct
Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.
Third-party evals — verify the marketing.
Cross-check our number against the rest of the ecosystem.