Qwen/Qwen2-1.5B to Qwen/Qwen3.5-2B
Some values not published Checked 2026-11-12.
Price per 1M tokens
| Field | Old | New | Change |
|---|---|---|---|
| Input | Not published | Not published | Not published |
| Output | Not published | Not published | Not published |
| Cached input | Not published | Not published | Not published |
| Example monthly cost | Not published | Not published | Example only |
Context and max output
| Limit | Old | New | Change |
|---|---|---|---|
| Context window | Not published | Not published | Not published |
| Max output | Not published | Not published | Not published |
Capabilities that differ
No differing capability values are published for both models.
Endpoint changes
- The quickstart shows POST https://api.together.ai/v1/chat/completions and an OpenAI client base_url of https://api.together.ai/v1. This sample only changes the model field. Source
API changes
- The deprecations page says these models can no longer be used as a base model for a fine-tuning job. This row is the fine-tuning service, not serverless inference. Source
Code
python before
from openai import OpenAI
client = OpenAI(base_url="https://api.together.ai/v1")
response = client.chat.completions.create(
model="Qwen/Qwen2-1.5B",
messages=[{"role": "user", "content": "Hello"}],
)
python after
from openai import OpenAI
client = OpenAI(base_url="https://api.together.ai/v1")
response = client.chat.completions.create(
model="Qwen/Qwen3.5-2B",
messages=[{"role": "user", "content": "Hello"}],
)
typescript before
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.together.ai/v1" });
const response = await client.chat.completions.create({
model: "Qwen/Qwen2-1.5B",
messages: [{ role: "user", content: "Hello" }],
});
typescript after
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.together.ai/v1" });
const response = await client.chat.completions.create({
model: "Qwen/Qwen3.5-2B",
messages: [{ role: "user", content: "Hello" }],
});
curl before
curl https://api.together.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-d '{"model":"Qwen/Qwen2-1.5B","messages":[{"role":"user","content":"Hello"}]}'
curl after
curl https://api.together.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-d '{"model":"Qwen/Qwen3.5-2B","messages":[{"role":"user","content":"Hello"}]}'
Checklist
- Read the shutdown date for Qwen/Qwen2-1.5B on the linked official page.
- This row is the fine-tuning service, not serverless inference.
- These models can no longer be used as a base model for a fine-tuning job.
- Point your requests at Qwen/Qwen3.5-2B and test before you send traffic.