GET
/v1/models/neon/meta-llama-3-1-8b-instruct
Accept:
| rawId | meta-llama-3-1-8b-instruct |
| displayName | Meta Llama 3.1 8B Instruct |
| id | neon-meta-llama-3-1-8b-instruct |
| activity | chat |
| schemaEndpointId | no bound generation route |
| releasedAt | 1721692800 — Jul 23, 2024 |
| firstSeenAt | 1721692800 — Jul 23, 2024 |
| lastSeenAt | 1795366123 — 10m ago |
| pricing | $0.15 / 1M input · $0.45 / 1M output → open calculator input_tokens (usage) · output_tokens (usage) |
| contextWindow | 131072 |
| maxOutput | 8192 |
| modalities | {"input":["text"],"output":["text"]} |
| capabilities | {"tools":true,"structured_outputs":true,"temperature":true} |
| knowledgeCutoff | "2023-12-31" |
| openWeights | true |
| weightsUrl · requestMap · providerMetadata | not published by this provider’s list endpoint |
Endpoints & schemas
GET /v1/schemas/neon →| endpoint | activity |
|---|---|
| v1/chat/completions | chat |
| v1/embeddings | embeddings |
Use it
shell
$ curl https://modelschemas.com/v1/schemas/neon/chat/v1/chat/completions # request schema
$ curl -X POST https://modelschemas.com/v1/validate -d '{"provider":"neon","endpointId":"v1/chat/completions","payload":{…}}'
$ curl -X POST https://modelschemas.com/v1/estimate -d '{"provider":"neon","model":"meta-llama-3-1-8b-instruct","usage":{"input_tokens":1200,"output_tokens":400}}'