SunsetDiff

Replacement for google/gemma-3-1b-it: what changes when you switch

The official replacement is google/gemma-4-26B-A4B-it. google/gemma-3-1b-it shut down on 2026-07-29 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.

google/gemma-3-1b-it model page · Together AI

Official replacement. Full diff page

google/gemma-3-1b-it to google/gemma-4-26B-A4B-it

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

  • 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="google/gemma-3-1b-it",
    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="google/gemma-4-26B-A4B-it",
    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: "google/gemma-3-1b-it",
  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: "google/gemma-4-26B-A4B-it",
  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":"google/gemma-3-1b-it","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":"google/gemma-4-26B-A4B-it","messages":[{"role":"user","content":"Hello"}]}'

Checklist

  1. Read the shutdown date for google/gemma-3-1b-it on the linked official page.
  2. This row is the fine-tuning service, not serverless inference.
  3. These models can no longer be used as a base model for a fine-tuning job.
  4. Point your requests at google/gemma-4-26B-A4B-it and test before you send traffic.

Related models

Questions

What is the replacement for google/gemma-3-1b-it?

The official replacement is google/gemma-4-26B-A4B-it. google/gemma-3-1b-it shut down on 2026-07-29 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 google/gemma-4-26B-A4B-it cheaper than google/gemma-3-1b-it?

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

Does google/gemma-4-26B-A4B-it have a bigger context window than google/gemma-3-1b-it?

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

Sources

Deprecation alerts

We email you before models shut down. Unsubscribe anytime.

Deprecation alert signup
Providers (optional)