Skip to content

Free models · data of 2026-11-06

Xing4.0 29B A4B: free API

Xing4.0 29B A4B is free on OpenRouter as xingchen-agi/xing4.0-29b-a4b:free. Today it ranks #5 of 12 free chat models in our open ranking, with a score of 24/100 (an estimate: it has no published benchmark or Arena scores yet).

Score basis
Estimated from size and adoption (no published scores)
Served by
Phala
Context
262K tokens
Max output
236K tokens
Input
text
Tool calling
Yes
JSON output
Yes
Free limit
20 RPM · 50 RPD

Does it train on your prompts?

The free variant is served by Phala, which does not train on prompts and keeps none of them (zero retention).

From OpenRouter's published provider policies, checked 2026-10-22.

How to call it

Any OpenAI-compatible client works. Create a key at openrouter.ai and use the model id above; the free limit is shared by all free models on your account.

from openai import OpenAI

client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key="sk-or-...")
reply = client.chat.completions.create(
    model="xingchen-agi/xing4.0-29b-a4b:free",
    messages=[{"role": "user", "content": "Hello"}],
    extra_body={"provider": {"data_collection": "deny"}},  # never route to a provider that may train
)
print(reply.choices[0].message.content)

Hit a limit? free-models-per-day, Provider returned error and other errors, explained. Limits and fine print: OpenRouter free models.

Questions

Is Xing4.0 29B A4B free to use?
Yes, as xingchen-agi/xing4.0-29b-a4b:free on OpenRouter. Free models share one allowance per account: 20 RPM · 50 RPD, or 1,000 a day once the account has bought 10 credits.
Does Xing4.0 29B A4B train on my prompts?
The free variant is served by Phala, which does not train on prompts and keeps none of them (zero retention).
What is Xing4.0 29B A4B's context window?
262K tokens of context, with up to 236K tokens of output.
How good is Xing4.0 29B A4B compared with other free models?
It ranks #5 of 12 free chat models today with a score of 24/100 (basis: Estimated from size and adoption (no published scores)).

Ranked next to it

Sources

Data of 2026-11-06, refreshed daily. Free models come and go: when this one leaves the free catalogue, this page goes with it.

Don't want to pick one model and handle its errors? ZeroLimitAI is one OpenAI-compatible endpoint that sends each request to the best free model available, and can run on your own Groq or OpenRouter key.

Stop paying per token.

One endpoint. $0 inference.

Free 7-day API key in a minute · no card. Then $99 once on your own key, or $99 a year.