Chat Completions

OpenAI-compatible chat completions endpoint.

Supports any HuggingFace causal language model.

post/v1/chat/completions

Request

The document declares no server URL.
Auth
none declared
TypeScript
https://skmtc.dev/llama-farm/apis/llamafarm-edge-runtime/docs/v1/chat/completions/post.ts
A function with typed inputs. Its response is checked against the schema.

modelstring required

temperaturenumber nullable

top_pnumber nullable

max_tokensinteger nullable

streamboolean nullable

logprobsboolean nullable

top_logprobsinteger nullable

presence_penaltynumber nullable

frequency_penaltynumber nullable

userstring nullable

n_ctxinteger nullable

n_batchinteger nullable

n_gpu_layersinteger nullable

n_threadsinteger nullable

flash_attnboolean nullable

use_mmapboolean nullable

use_mlockboolean nullable

cache_type_kstring nullable

cache_type_vstring nullable

extra_bodyobject nullable

thinkboolean nullable

thinking_budgetinteger nullable

cache_keystring nullable

return_cache_keyboolean nullable

auto_truncateboolean nullable

truncation_strategystring nullable

Successful Response

unknown required

No recorded changes to this operation across all 1 revision of this API.