SunsetDiff

Replacement for DeepSeek-R1: what changes when you switch

The official replacement is DeepSeek-R1-0528. DeepSeek-R1 does not have a published shutdown date per Together AI's deprecation page (checked 2026-11-12). Price, context window, and max output were left blank because the official pages we checked did not publish them.

This is the canonical diff. Model page · Replacement page · Together AI

DeepSeek-R1 to DeepSeek-R1-0528

Some values not published Checked 2026-11-12.

Price per 1M tokens

Price comparison. Example monthly cost for 10M input tokens and 2M output tokens. Labeled example, not a bill.
FieldOldNewChange
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

Token limits
LimitOldNewChange
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

API changes

Code

python before
from openai import OpenAI
client = OpenAI(base_url="https://api.together.ai/v1")
response = client.chat.completions.create(
    model="DeepSeek-R1",
    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="DeepSeek-R1-0528",
    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: "DeepSeek-R1",
  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: "DeepSeek-R1-0528",
  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":"DeepSeek-R1","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":"DeepSeek-R1-0528","messages":[{"role":"user","content":"Hello"}]}'

Checklist

  1. Read the deprecations page for DeepSeek-R1. It does not publish a shutdown date.
  2. Requests to the original model ID are automatically routed to the upgraded version.
  3. The old version remains available via dedicated endpoints.
  4. Point your requests at DeepSeek-R1-0528 and test before you send traffic.

Questions

What is the replacement for DeepSeek-R1?

The official replacement is DeepSeek-R1-0528. DeepSeek-R1 does not have a published shutdown date per Together AI's deprecation page (checked 2026-11-12). Price, context window, and max output were left blank because the official pages we checked did not publish them.

Is DeepSeek-R1-0528 cheaper than DeepSeek-R1?

A full price comparison is not published. One or both prices are missing from the official pages we checked.

Does DeepSeek-R1-0528 have a bigger context window than DeepSeek-R1?

Context window sizes are not both published on the official pages we checked.