---
title: "Qwen2.5 72B vs DeepSeek R1 Distill Llama 70B API pricing compared"
description: "Qwen2.5 72B vs DeepSeek R1 Distill Llama 70B API price per 1M tokens: USD 0.36 / USD 0.40 vs USD 0.25 / USD 0.75 input/output, from providers' own pricing pages."
url: https://broadrouter.com/llm-api-pricing/compare/qwen2.5-72b-instruct-vs-deepseek-r1-distill-llama-70b/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Qwen2.5 72B vs DeepSeek R1 Distill Llama 70B API pricing

Updated 2026-11-15

Qwen2.5 72B: USD 0.36 input, USD 0.40 output per 1M tokens (DeepInfra). DeepSeek R1 Distill Llama 70B: USD 0.25 input, USD 0.75 output per 1M tokens (GMI Cloud). At 3 input tokens per output token, DeepSeek R1 Distill Llama 70B costs 1.4% more than Qwen2.5 72B (USD 0.375 vs USD 0.37 per 1M).

Picked by the same-tier rule: both are in the second quarter of the indexed models by price (USD 0.1556 to USD 0.4512 per 1M tokens at 3:1) and in the same size class, mid-size (no tier word, 40B to 200B parameters or no size in the name). Qwen2.5 72B is the 2nd-closest-priced model from another maker to DeepSeek R1 Distill Llama 70B in that bucket. **Price only**: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

## How do Qwen2.5 72B and DeepSeek R1 Distill Llama 70B differ on price?

-   Cheapest input price: DeepSeek R1 Distill Llama 70B USD 0.25 against USD 0.36 per 1M tokens, so Qwen2.5 72B costs 1.44× as much (44% more).
-   Cheapest output price: Qwen2.5 72B USD 0.40 against USD 0.75 per 1M tokens, so DeepSeek R1 Distill Llama 70B costs 1.88× as much (88% more).
-   Among the 201 indexed models, Qwen2.5 72B ranks 78th cheapest and DeepSeek R1 Distill Llama 70B 80th on the 3:1 blend.
-   The cheaper model changes at 3.2 input tokens per output token.
-   Only DeepSeek R1 Distill Llama 70B lists a cached-input discount: DeepSeek R1 Distill Llama 70B at 1 standard price of 2, from USD 0.52 (Featherless, 80% below that provider's input price). Qwen2.5 72B's cached tokens bill at the input price.
-   DeepSeek R1 Distill Llama 70B states up to 131,072 tokens of context, 4× the 32,768 of Qwen2.5 72B.
-   Qwen2.5 72B has 3 providers with a standard price, 1 more than DeepSeek R1 Distill Llama 70B; 1 provider sells both (Featherless).
-   On one account, Featherless charges USD 0.3775 for Qwen2.5 72B (1.02× its cheapest price) and USD 2.70 for DeepSeek R1 Distill Llama 70B (7.2× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
-   Shopping around matters more for DeepSeek R1 Distill Llama 70B: its dearest standard price is 7.2× its cheapest, against 1.59× for Qwen2.5 72B.

## Qwen2.5 72B and DeepSeek R1 Distill Llama 70B prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Qwen2.5 72B and DeepSeek R1 Distill Llama 70B API prices compared
| Price | Qwen2.5 72B | DeepSeek R1 Distill Llama 70B |
| --- | --- | --- |
| Model page | [Qwen2.5-72B-Instruct](https://broadrouter.com/llm-api-pricing/qwen2.5-72b-instruct/) · Qwen · 3 providers | [DeepSeek R1 Distill Llama 70B](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-llama-70b/) · DeepSeek · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.37 lower · USD 0.36 in / USD 0.40 out at DeepInfra · [DeepInfra page](https://deepinfra.com/Qwen/Qwen2.5-72B-Instruct) checked 2026-11-14 | USD 0.375 · USD 0.25 in / USD 0.75 out at GMI Cloud · [GMI Cloud page](https://console.gmicloud.ai/model/llm/deepseek-r1-distill-llama-70b/c271c9b8-621b-4f5d-ab1c-7725506bb2c5) checked 2026-11-15 |
| Cheapest input | USD 0.36 · DeepInfra [source](https://deepinfra.com/Qwen/Qwen2.5-72B-Instruct) | USD 0.25 lower · GMI Cloud [source](https://console.gmicloud.ai/model/llm/deepseek-r1-distill-llama-70b/c271c9b8-621b-4f5d-ab1c-7725506bb2c5) |
| Cheapest cached input | No standard price lists a cache price; cached tokens bill at the input price. | USD 0.52 · Featherless [source](https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) |
| Cheapest output | USD 0.40 lower · DeepInfra [source](https://deepinfra.com/Qwen/Qwen2.5-72B-Instruct) | USD 0.75 · GMI Cloud [source](https://console.gmicloud.ai/model/llm/deepseek-r1-distill-llama-70b/c271c9b8-621b-4f5d-ab1c-7725506bb2c5) |
| Maker's own API | Qwen publishes no paid standard price on its own API that we found. | DeepSeek publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.37 / USD 0.40 · input / output, 3 prices | USD 1.425 / USD 1.875 · input / output, 2 prices |
| Context window | 32,768 tokens, largest stated | 131,072 tokens, largest stated; from 32,768 at some providers |
| Providers with a standard price | 3 | 2 |

-   **Lower** marks the lower price on a line; **tie**, equal prices. Other tiers and free rows are on the model pages.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Qwen2.5%2072B%20vs%20DeepSeek%20R1%20Distill%20Llama%2070B%20API%20pricing&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Fllm-api-pricing%2Fcompare%2Fqwen2.5-72b-instruct-vs-deepseek-r1-distill-llama-70b%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link filled in).

## What do Qwen2.5 72B and DeepSeek R1 Distill Llama 70B cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the [cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/?model=qwen2.5-72b-instruct,deepseek-r1-distill-llama-70b); cached input at the cached price where listed).

Monthly cost of three workloads on Qwen2.5 72B and DeepSeek R1 Distill Llama 70B
| Workload | Qwen2.5 72B | DeepSeek R1 Distill Llama 70B | Difference |
| --- | --- | --- | --- |
| **Support chatbot** · 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 39.60 · DeepInfra | USD 36.00 · GMI Cloud | USD 3.60 · DeepSeek R1 Distill Llama 70B lower |
| **RAG over documents** · 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 92.40 · DeepInfra | USD 71.25 · GMI Cloud | USD 21.15 · DeepSeek R1 Distill Llama 70B lower |
| **Coding agent (one developer)** · 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | exceeds context | USD 517.50 · GMI Cloud | — |

DeepSeek R1 Distill Llama 70B is cheaper on 2 workloads. The widest gap is on RAG over documents: the dearer model costs 30% more than the cheaper one.

## Does the cheaper model change with your input:output ratio?

The cheaper model changes with the mix: below 3.2 input tokens per output token, Qwen2.5 72B is cheaper; above 3.2, DeepSeek R1 Distill Llama 70B is cheaper. At the site's 3:1 blend, Qwen2.5 72B is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Price per 1M tokens of Qwen2.5 72B and DeepSeek R1 Distill Llama 70B at different input:output mixes
| Input : output tokens | Qwen2.5 72B | DeepSeek R1 Distill Llama 70B |
| --- | --- | --- |
| **1 : 3** (long answers) | USD 0.39 lower · DeepInfra | USD 0.625 · GMI Cloud |
| **1 : 1** | USD 0.38 lower · DeepInfra | USD 0.50 · GMI Cloud |
| **3 : 1** (the site’s blend) | USD 0.37 lower · DeepInfra | USD 0.375 · GMI Cloud |
| **10 : 1** (retrieval, long prompts) | USD 0.3636 · DeepInfra | USD 0.2955 lower · GMI Cloud |
| **30 : 1** (agents, big contexts) | USD 0.3613 · DeepInfra | USD 0.2661 lower · GMI Cloud |

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

## What do Qwen2.5 72B and DeepSeek R1 Distill Llama 70B cost per character in other languages?

Not measured: the [real cost by language dataset](https://broadrouter.com/data/real-cost-by-language/) covers only tokenizers we could measure from published files, and Qwen2.5 72B and DeepSeek R1 Distill Llama 70B are not among them. Count tokens on your own text with the counters below.

## Check it on your own traffic

-   [Qwen2.5-72B-Instruct API pricing](https://broadrouter.com/llm-api-pricing/qwen2.5-72b-instruct/): all 3 providers and other tiers.
-   [DeepSeek R1 Distill Llama 70B API pricing](https://broadrouter.com/llm-api-pricing/deepseek-r1-distill-llama-70b/): all 2 providers and other tiers.
-   [Cost calculator with Qwen2.5 72B and DeepSeek R1 Distill Llama 70B preloaded](https://broadrouter.com/tools/llm-api-cost-calculator/?model=qwen2.5-72b-instruct,deepseek-r1-distill-llama-70b)
-   [Qwen token counter](https://broadrouter.com/tools/qwen-token-counter/)
-   [DeepSeek token counter](https://broadrouter.com/tools/deepseek-token-counter/)
-   [Prompt caching calculator](https://broadrouter.com/tools/prompt-caching-calculator/)

More comparisons: [Llama 3.3 70B vs Qwen2.5 72B](https://broadrouter.com/llm-api-pricing/compare/llama-3.3-70b-instruct-vs-qwen2.5-72b-instruct/) · [Qwen2.5 72B vs Qwen 2.5 7B](https://broadrouter.com/llm-api-pricing/compare/qwen2.5-72b-instruct-vs-qwen2.5-7b-instruct/) · [every Qwen2.5 72B comparison](https://broadrouter.com/llm-api-pricing/compare/#m-qwen2.5-72b-instruct) · [every DeepSeek R1 Distill Llama 70B comparison](https://broadrouter.com/llm-api-pricing/compare/#m-deepseek-r1-distill-llama-70b) · [all 662 price comparisons](https://broadrouter.com/llm-api-pricing/compare/)

## Questions

### Is Qwen2.5 72B cheaper than DeepSeek R1 Distill Llama 70B?

Yes. On a blend of 3 input tokens to 1 output token, Qwen2.5 72B costs USD 0.37 per 1M tokens and DeepSeek R1 Distill Llama 70B USD 0.375, at each model's cheapest standard price. For input alone, DeepSeek R1 Distill Llama 70B is cheaper (USD 0.25 against USD 0.36 per 1M); for output alone, Qwen2.5 72B is (USD 0.40 against USD 0.75). This compares price only, not quality.

### What do Qwen2.5 72B and DeepSeek R1 Distill Llama 70B cost per 1M tokens?

Qwen2.5 72B: from USD 0.36 input and USD 0.40 output at DeepInfra; median of 3 standard prices USD 0.37 / USD 0.40. DeepSeek R1 Distill Llama 70B: from USD 0.25 input and USD 0.75 output at GMI Cloud; median of 2 standard prices USD 1.425 / USD 1.875. Each price is read from the provider's own pricing page; the source is linked in the table.

### Which providers sell both Qwen2.5 72B and DeepSeek R1 Distill Llama 70B?

1 provider has a standard price for both: Featherless (USD 0.3775 and USD 2.70 at 3:1). Buying each model from its own cheapest provider costs USD 0.37 and USD 0.375.

### At what input:output ratio does the cheaper of Qwen2.5 72B and DeepSeek R1 Distill Llama 70B change?

The cheaper model changes with the mix: below 3.2 input tokens per output token, Qwen2.5 72B is cheaper; above 3.2, DeepSeek R1 Distill Llama 70B is cheaper. At the site's 3:1 blend, Qwen2.5 72B is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

### Do Qwen2.5 72B and DeepSeek R1 Distill Llama 70B have cached input pricing?

Qwen2.5 72B: no standard price lists a cached-input discount. DeepSeek R1 Distill Llama 70B from USD 0.52 per 1M cached input tokens (Featherless; 1 of 2 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

### Which has the larger context window, Qwen2.5 72B or DeepSeek R1 Distill Llama 70B?

DeepSeek R1 Distill Llama 70B: up to 131,072 tokens, against 32,768 for Qwen2.5 72B, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=llm-api-pricing-compare-qwen2.5-72b-instruct-vs-deepseek-r1-distill-llama-70b&utm_content=page-cta) ·

**Sources**

-   [DeepInfra: pricing (checked 2026-11-14)](https://deepinfra.com/Qwen/Qwen2.5-72B-Instruct)
-   [GMI Cloud: pricing (checked 2026-11-15)](https://console.gmicloud.ai/model/llm/deepseek-r1-distill-llama-70b/c271c9b8-621b-4f5d-ab1c-7725506bb2c5)
-   [Featherless: pricing (checked 2026-11-15)](https://featherless.ai/models/deepseek-ai/DeepSeek-R1-Distill-Llama-70B)
-   [Featherless: pricing (checked 2026-11-15)](https://featherless.ai/models/Qwen/Qwen2.5-72B-Instruct)
