Overview
MedCode V1 is a language model from JD. It accepts text input and returns text, so a request is a written prompt and the response is written output. It is billed per token, with separate rates for input and output and a lower rate for cached input.
It accepts text input and returns text.
Capabilities
MedCode V1 accepts text input and returns text. Its input and output modality is text only.
Cache reads are priced separately from regular input, which lowers the price of requests that repeat a long prompt prefix.
Pricing
MedCode V1 is priced at $0.4286 per 1M input tokens and $3.8571 per 1M output tokens. Cache reads are billed at $0.0857 per 1M tokens.
MedCode V1 is available through RealRelay's OpenAI-compatible API.
Use cases
Use MedCode V1 for text-based tasks that fit a prompt-and-response pattern, such as drafting text, summarizing documents and answering questions in chat-style requests, with the prompt and the reply both in plain text.
Cached input pricing helps when many requests share the same long instructions, such as a fixed system prompt, a policy document or other reference text.
What is MedCode V1?
MedCode V1 is a JD language model that accepts text input and returns text.
How much does MedCode V1 cost?
MedCode V1 is priced at $0.4286 per 1M input tokens and $3.8571 per 1M output tokens. Cache reads are billed at $0.0857 per 1M tokens.
What inputs and outputs does MedCode V1 support?
MedCode V1 accepts text input and returns text.
Does MedCode V1 have a cache-read price?
Yes. MedCode V1 bills cache reads at $0.0857 per 1M tokens, separately from regular input and output.
How do I call MedCode V1 via the API?
Send requests to RealRelay's OpenAI-compatible API with the model ID jd/medcode-v1 to use MedCode V1.