Skip to contentК содержанию
LLMcode
ModelsМоделиPricingЦеныInstructionsИнструкцииDocsДокументацияNewsНовости
ENRU
EnglishРусский
Sign inВойтиCreate accountСоздать аккаунтAccountАккаунт
MenuМеню
ModelsМоделиPricingЦеныInstructionsИнструкцииDocsДокументацияNewsНовостиCreate accountСоздать аккаунт
LLMcode

Model names in the API are LLMcode profiles with their own routing. They do not mean direct access to the same-named models of OpenAI LLC or Anthropic PBC. Trademarks belong to their owners. The service is independent and is not affiliated with OpenAI or Anthropic.Названия моделей в API — профили LLMcode с собственной маршрутизацией. Они не означают прямой доступ к одноимённым моделям OpenAI LLC или Anthropic PBC. Товарные знаки принадлежат их правообладателям. Сервис независим и не аффилирован с OpenAI/Anthropic.

CatalogКаталог

ModelsМоделиPricingЦеныInstructionsИнструкцииDocsДокументацияKey checkПроверка ключа

LegalДокументы

OfferОфертаPrivacyКонфиденциальностьConsentСогласиеAcceptable useДопустимое использованиеRefundВозврат

LearnМатериалы

GuidesГайдыComparisonsСравненияAlternativesАльтернативыIntegrationsИнтеграцииUse casesСценарииGlossaryГлоссарийNewsНовостиRSSTelegramTelegram-канал
HomeГлавнаяModelsМоделиPricingЦеныSign inВойтиAccountАккаунт
LLMcode/Integrations/opencode with an LLMcode provider

Integration

opencode with an LLMcode provider

opencode keeps providers in opencode.json. The LLMcode entry is a standard OpenAI-compatible provider with a models map you control.

Updated 2026-11-18

The provider entry

Add a provider named llmcode with the @ai-sdk/openai-compatible package, the base URL https://llmcode.io/v1 and the key read from LLMCODE_API_KEY. The models map lists every published slug you want to offer.

Each profile in the map becomes a selectable model. A token without a model allowlist may use all published profiles; a token with one is limited to that list, and anything else returns 403.

Autocomplete versus chat

opencode uses the same provider for chat and inline completion. Pointing completion at a fast, cheap profile and chat at a larger one keeps latency down without splitting the billing: both go through one balance.

  • baseURL: https://llmcode.io/v1
  • apiKey: {env:LLMCODE_API_KEY}
  • models: published slugs from /models

When the provider does not appear

Validate the JSON first — a trailing comma hides the whole file. Then reload the editor window so the engine rereads the provider list; the config is parsed at startup.

If the model list is empty, run GET /v1/models with the same key. An empty answer means the key is restricted, not that the config is wrong.

Connect

opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "llmcode": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "LLMcode",
      "options": {
        "baseURL": "https://llmcode.io/v1",
        "apiKey": "{env:LLMCODE_API_KEY}"
      },
      "models": {
        "claude-sonnet-5-5": {},
        "deepseek-flash": {}
      }
    }
  }
}
Smoke test
curl https://llmcode.io/v1/models \
  -H "Authorization: Bearer $LLMCODE_API_KEY"

Published model prices

USD per 1M tokens. The numbers come from the public catalog on every page rebuild — this is the sale price, not an estimate.

ModelInputOutputCache
Claude Opus 5.5$2.70$8.00$0.14
DeepSeek Flash$0.50$2.00$0.01
Claude Sonnet 5.5$1.33$6.67$0.07
DeepSeek V4 Pro$2.20$6.60$0.07

Top-up from $10, balance in USD. 1 USD = 1,000,000 UT. No subscription and no auto-charge.

Questions

Where does opencode.json live?

In ~/.config/opencode/opencode.json for a global setup, or in the project directory for a per-repository configuration.

Which package name should the provider use?

@ai-sdk/openai-compatible — the provider is OpenAI-compatible, so opencode needs no custom adapter.

Can several profiles share one key?

Yes. The model is chosen per request; the key is not bound to a single profile unless you set an allowlist.

Does streaming work in opencode?

Chat completions stream over SSE. The /v1/responses endpoint does not stream in this version and returns 400 with stream: true.

See also

All setup instructionsModels and pricesAPI docs

One key for every model

OpenAI- and Anthropic-compatible endpoints, balance in USD, top-up from $10.

Create accountPricing
Base URL
https://llmcode.io/v1
Key format
sk-llmcode-…