llama.cpp (llama-server)
partially verifiedlocal · inference_host · confidence 60% · doc_fetch · last verified 2026-07-18
Subject record
| Base URLs | http://127.0.0.1:8080/v1 openai-compatible |
|---|---|
| API key required | no |
| Credit card | no |
| Phone verification | no |
| May train on prompts | no |
| Quota | local [—] |
| Signup friction | steps unknown · ~0m to first key |
| Env var | none — anonymous access |
| Notes | Open-source project (ggml-org), no company HQ. Server README (fetched 2026-07-18) confirms OpenAI-compatible /v1/chat/completions, /v1/completions, /v1/embeddings, /v1/models with streaming; OpenAI-style function calling requires the --jinja flag. /v1/responses not listed — 'unknown'. Serves whichever GGUF model(s) the user loads, so no model records are cataloged. |
Models (0)
| model | capabilities | context | free | limits |
|---|
Provenance
| source_llamacpp_server_docs | official_docs | trust: high | checked 2026-07-18 |