llama-3.1-8b-instant to openai/gpt-oss-20b
Some values not published Checked 2026-10-26.
Price per 1M tokens
| Field | Old | New | Change |
|---|---|---|---|
| Input | Not published | $0.075 | Not published |
| Output | Not published | $0.3 | Not published |
| Cached input | Not published | Not published | Not published |
| Example monthly cost | Not published | $1.35 | Example only |
Context and max output
| Limit | Old | New | Change |
|---|---|---|---|
| Context window | 131,072 | 131,072 | 0% (same) |
| Max output | 131,072 | 65,536 | -50% (lower) |
Capabilities that differ
No differing capability values are published for both models.
Endpoint changes
- The Groq API reference says chat completions are POST https://api.groq.com/openai/v1/chat/completions. The sample only changes the model field. Source
Code
python before
from groq import Groq
client = Groq()
chat_completion = client.chat.completions.create(
messages=[{"role": "user", "content": "Hello"}],
model="llama-3.1-8b-instant",
)
python after
from groq import Groq
client = Groq()
chat_completion = client.chat.completions.create(
messages=[{"role": "user", "content": "Hello"}],
model="openai/gpt-oss-20b",
)
typescript before
import Groq from "groq-sdk";
const groq = new Groq();
const completion = await groq.chat.completions.create({
messages: [{ role: "user", content: "Hello" }],
model: "llama-3.1-8b-instant",
});
typescript after
import Groq from "groq-sdk";
const groq = new Groq();
const completion = await groq.chat.completions.create({
messages: [{ role: "user", content: "Hello" }],
model: "openai/gpt-oss-20b",
});
curl before
curl https://api.groq.com/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model":"llama-3.1-8b-instant","messages":[{"role":"user","content":"Hello"}]}'
curl after
curl https://api.groq.com/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-20b","messages":[{"role":"user","content":"Hello"}]}'
Checklist
- Read the shutdown date for llama-3.1-8b-instant on the linked official page.
- Point your requests at openai/gpt-oss-20b.
- Re-check price, context, and parameters on the provider pages linked here.
- Ship the change before the published shutdown date.