Loading
Z.ai GLM 4.7 Flash · coder-small
Self-hosted 7B code model for quick single-file coding help - explain a snippet, a regex or an error message, write a small helper or shell one-liner, convert between languages - across 40+ programming languages; code stays inside the deployment. Repository-wide changes, refactors with tests and reviews go to the coding agent.
Published by the vendor; the platform bills at the target's declared price.
Requests per day this target answered on this deployment, with the cost line.
Domains the signal layer detected on requests that ended here.
Hard stops enforced before scoring.
Pin this target with model="coder-small", or send a candidate list and let the router choose and fall back.
curl https://api.opensmartroute.ai/v1/chat/completions \
-H "Authorization: Bearer $OSR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "coder-small", "messages": [{"role": "user", "content": "Explain what this regular expression matches."}]}'from openai import OpenAI
client = OpenAI(base_url="https://api.opensmartroute.ai/v1", api_key="osr_live_...")
resp = client.chat.completions.create(
model="coder-small", # pin this target, or "auto" to let the router choose
messages=[{"role": "user", "content": "Explain what this regular expression matches."}],
extra_body={"models": ["coder-small", "auto"]}, # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)Z.ai z-ai/glm-4.7-flash
As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...
Examples the similarity strategy matches against.