GET
/v1/models/opencode-go/hy4-flash-free
Accept:
| rawId | hy4-flash-free |
| displayName | Hy4 flash Free |
| id | opencode-go-hy4-flash-free |
| activity | chat |
| schemaEndpointId | inference/go/openai/v1/chat/completions |
| releasedAt | 1794787200 — Nov 16, 2026 |
| firstSeenAt | 1794787200 — Nov 16, 2026 |
| lastSeenAt | 1795360029 — 7m ago |
| pricing | not published by this provider’s list endpoint |
| contextWindow | 1048576 |
| maxOutput | 65536 |
| modalities | {"input":["text","image"],"output":["text"]} |
| capabilities | {"tools":true,"reasoning":true,"vision":true} |
| openWeights | false |
| providerMetadata | {"attachment":true,"canonical_model_id":"tencent/hy4-flash","cost":{"cache_read":0,"input":0,"output":0},"description":"Tencent's lower-cost Hy4 tier for everyday agent and productivity tasks, with image understanding and a 1M-token context window.","family":"hy-flash-free","id":"hy4-flash-free","last_updated":"2026-11-16","limit":{"context":1048576,"input":983040,"output":65536},"modalities":{"input":["text","image"],"output":["text"]},"name":"Hy4 flash Free","open_weights":false,"provider":{"api":"https://opencode.ai/inference/go/openai/v1"},"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"release_date":"2026-11-16","temperature":true,"tool_call":true} |
| knowledgeCutoff · weightsUrl · requestMap | not published by this provider’s list endpoint |
Endpoints & schemas
GET /v1/schemas/opencode-go →| endpoint | activity |
|---|---|
| inference/go/openai/v1/chat/completions | chat |
endpoints matching this model — the provider has more, see /v1/schemas/opencode-go
Use it
shell
$ curl https://modelschemas.com/v1/schemas/opencode-go/chat/inference/go/openai/v1/chat/completions # request schema
$ curl -X POST https://modelschemas.com/v1/validate -d '{"provider":"opencode-go","endpointId":"inference/go/openai/v1/chat/completions","payload":{…}}'
$ curl -X POST https://modelschemas.com/v1/estimate -d '{"provider":"opencode-go","model":"hy4-flash-free","usage":{"input_tokens":1200,"output_tokens":400}}'