GLM-5.3 Flash
Abliterated API.

One account. Another model.

Oathbreaker Flash gives developers access to GLM-5.3 Flash Abliterated through an OpenAI-compatible Chat Completions API. It supports text conversations, streaming responses, and function calling for agents that run tools in your own environment.

Oathbreaker is operated by Formacha LLC. We provide the API gateway, account, keys, and usage accounting. The model family comes from Z.ai; inference providers supply the modified checkpoints. Oathbreaker does not train the underlying model.

Set model to oathbreaker-glm-5.3-flash and use https://oathbreaker.ai/v1 as your base URL. Flash is an explicit choice; it does not replace the flagship GLM-5.3 Abliterated default.

Flash pricing vs. flagship

Pay for confirmed token usage from your prepaid balance. Both models use the same account and API key.

For example, 100,000 uncached input tokens plus 10,000 output tokens on Flash cost $0.065. This is a token-cost illustration, not a benchmark or a promise about how many tokens an agent task will use.

Try Flash when token cost matters, then compare both models on a small task you can evaluate: a code change with tests, a document summary, or a tool workflow with a known result. Quality and response time depend on your task, history, and reasoning effort.

Add credit starting at $5. There is no subscription or automatic refill. Cached input is charged once at its discounted rate when the provider reports a cache hit; repeated prompts do not guarantee one. See billing details and pricing.

Capabilities & current limits

These are the limits exposed by Oathbreaker. A supplier’s larger advertised context window or additional features do not change this API’s limits.

Reasoning and final text share the output budget and output-token price. This is a text API: image input, audio, embeddings, and the Responses API are not supported. Validate model output and tool arguments in your application; strict tool-schema enforcement is not supported.

Conversation history and tool schemas use context. If a request is too large, shorten its history, reduce tool definitions, or lower the requested output budget. Account rate limits are shared across models. Review rate limits.

Your first Flash request

Create an account, add prepaid credit, and create an API key in your console. Store it as OATHBREAKER_API_KEY in your terminal or server environment. Running these examples uses credit.

curl --fail-with-body --silent --show-error --max-time 650 \
  https://oathbreaker.ai/v1/chat/completions \
  -H "Authorization: Bearer $OATHBREAKER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "oathbreaker-glm-5.3-flash",
    "messages": [{"role": "user", "content": "Suggest three tests for a CSV import tool."}],
    "max_tokens": 2048,
    "reasoning_effort": "low",
    "stream": false
  }'

Using the OpenAI Python SDK

Install the openai package in your Python environment, then run:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://oathbreaker.ai/v1",
    api_key=os.environ["OATHBREAKER_API_KEY"],
    timeout=650.0,
    max_retries=0,
)

response = client.chat.completions.create(
    model="oathbreaker-glm-5.3-flash",
    messages=[{"role": "user", "content": "Suggest three tests for a CSV import tool."}],
    max_tokens=2048,
    reasoning_effort="low",
)
print(response.choices[0].message.content)
print(response.usage)

These examples send one request and do not retry automatically. The output budget includes reasoning, so it may be used up before a final answer. Check the response’s finish_reason and your console usage before repeating a request.

For streaming, set stream: true and consume the SSE events. For tools, supply function definitions, validate returned arguments, and send the tool results back with the conversation. Follow the streaming guide and tool-calling guide for the complete request flow.

Connect Flash to Hermes or another agent

Follow the Hermes setup guide using your Oathbreaker key and https://oathbreaker.ai/v1. When selecting a model, choose oathbreaker-glm-5.3-flash. Start a new conversation so the new model selection takes effect.

For OpenCode, OpenWork, or Pi, use the other agent setup guides with the same base URL and Flash model identifier. Use a custom OpenAI-compatible connection where required.

Start with a small, reviewable task in a folder you choose. Your agent manages its tools and permissions; Oathbreaker provides model responses. You can inspect requests and token costs in your console’s Usage tab.

Common questions

Read the abliterated-model guide for a fuller explanation, hosted-versus-local tradeoffs, and a recorded Flash example.

What does “abliterated” mean?

It describes a model modified to reduce learned refusal behavior. These models are sometimes called uncensored. That does not guarantee an answer to every prompt, correct output, or suitability for every task. Human judgment and responsibility still matter.

Where does the model come from?

Oathbreaker Flash serves a hosted abliterated variant of GLM-5.3 Flash. The underlying model authors retain attribution. Hosted checkpoints and performance can differ. Oathbreaker uses the selected abliterated model and keeps its customer-facing model name, limits, and retail rates when routing to an approved backup.

Can I switch without a new key or deposit?

Yes. Select the Flash model identifier in your request or agent configuration. It uses the same Oathbreaker account balance and API key as the flagship model.

Who can help with setup?

Email support@oathbreaker.ai with the error message and request ID, without your API key. The API reference, privacy policy, and terms cover request behavior and service policies.