GET
/v1/models/opencode/deepseek-v4-pro
Accept:
| rawId | deepseek-v4-pro |
| displayName | DeepSeek V4 Pro |
| id | opencode-deepseek-v4-pro |
| activity | chat |
| schemaEndpointId | inference/openai/v1/chat/completions |
| releasedAt | 1776988800 — Apr 24, 2026 |
| firstSeenAt | 1776988800 — Apr 24, 2026 |
| lastSeenAt | 1795363408 — 14m ago |
| pricing | $1.74 / 1M input · $3.48 / 1M output → open calculator input_tokens (usage) · output_tokens (usage) · cache_read_tokens (usage) |
| contextWindow | 1000000 |
| maxOutput | 384000 |
| modalities | {"input":["text"],"output":["text"]} |
| capabilities | {"tools":true,"reasoning":true,"structured_outputs":true,"vision":false} |
| knowledgeCutoff | "2025-05" |
| openWeights | true |
| requestMap | {"thinking":null,"maxTokensField":null,"developerRole":null,"replayReasoningContent":true,"store":null,"strictTools":null,"sessionAffinity":null,"cacheControl":null,"toolStream":null,"reasoningEffort":null} |
| providerMetadata | {"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"api":"https://opencode.ai/inference/openai/v1"},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"canonical_model_id":"deepseek/deepseek-v4-pro"} |
| weightsUrl | not published by this provider’s list endpoint |
Endpoints & schemas
GET /v1/schemas/opencode →| endpoint | activity |
|---|---|
| inference/openai/v1/chat/completions | chat |
endpoints matching this model — the provider has more, see /v1/schemas/opencode
Use it
shell
$ curl https://modelschemas.com/v1/schemas/opencode/chat/inference/openai/v1/chat/completions # request schema
$ curl -X POST https://modelschemas.com/v1/validate -d '{"provider":"opencode","endpointId":"inference/openai/v1/chat/completions","payload":{…}}'
$ curl -X POST https://modelschemas.com/v1/estimate -d '{"provider":"opencode","model":"deepseek-v4-pro","usage":{"input_tokens":1200,"output_tokens":400}}'