# Arize AI Qwen 2 1.5B Instruct

Arize AI Qwen 2 1.5B Instruct is a language model from Togethercomputer with a 32K-token context window. Provider list price is $0.10 per million input tokens and $0.10 per million output; on Allocate you pay $0.11 and $0.11 with the 7% transaction fee. The weights are open, so you can fine-tune it and own the result.

## Pricing

| | Provider list | On Allocate |
| --- | --- | --- |
| Input, per M tokens | $0.10 | $0.11 |
| Output, per M tokens | $0.10 | $0.11 |

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

## Facts

| Field | Value |
| --- | --- |
| Lab | Togethercomputer |
| Modality | Language |
| Context window | 32K tokens |
| License | Not listed |
| Open weights | Yes |
| Fine-tunable | Yes, on your data |
| Catalog id | arize/qwen-2-1.5b-instruct |

## What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.10 + 350 × $0.10 = $155 a month. Billed on Allocate it is $165.85 with the 7% transaction fee.

## Common questions

### How much does Arize AI Qwen 2 1.5B Instruct cost per million tokens?

Provider list price is $0.10 per million input tokens and $0.10 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.11 in and $0.11 out.

### What context window does Arize AI Qwen 2 1.5B Instruct have?

32,768 tokens (32K). At roughly 0.75 words per token, that is about 25k words of English text per request.

### Can I fine-tune Arize AI Qwen 2 1.5B Instruct?

Yes. Arize AI Qwen 2 1.5B Instruct is an open-weights model; check the lab’s model card for the exact license terms. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.

### How do I call Arize AI Qwen 2 1.5B Instruct on Allocate?

Send arize/qwen-2-1.5b-instruct in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.

---

[HTML page](https://allocate.network/models/arize-qwen-2-1-5b-instruct) · [Machine-readable catalog](https://allocate.network/catalog.json)