OpenCode error
OpenCode: ProviderModelNotFoundError
ProviderModelNotFoundErrorStatus: By designLast verified 4 documented fixes3 sources
What it means
OpenCode could not resolve the model you referenced to a provider and model it knows about. The official troubleshooting docs say that if you see this error, you have most likely referenced a model incorrectly somewhere.
Causes
- The model is not referenced in the required
<providerId>/<modelId>form (official docs). - An agent or subagent config references a model through a provider you are not signed in to. A maintainer in #916: "You are referencing an anthropic model using anthropic provider and aren't signed in w/ anthropic. You can use anthropic models through github copilot but you need to specify them using github-copilot prefix".
- The model ID is not in OpenCode's model list, which comes from models.dev (#916).
How to fix it
- Fix 1.
Reference models as
<providerId>/<modelId>. Examples from the docs:openai/gpt-4.1,openrouter/google/gemini-2.5-flash,opencode/kimi-k2.Snippetopenai/gpt-4.1 openrouter/google/gemini-2.5-flash opencode/kimi-k2 - Fix 2.
List the models you can actually use, then copy the exact ID into your config or agent definition (official docs, and a maintainer in #916).
Terminalopencode models - Fix 3.
To use a model through GitHub Copilot, use the github-copilot prefix rather than the original vendor's prefix (maintainer, #916).
Snippetgithub-copilot/claude-sonnet-4 - Fix 4.
Look up the correct provider and model IDs on models.dev, which OpenCode uses as its model reference (maintainer, #916). Since v1.14.50 the CLI and typed callers suggest alternatives when a model is missing.
More OpenCode errors
All 17 OpenCode errorsProviderInitErrorStatus: WorkaroundAI_APICallErrorStatus: WorkaroundThis credential is only authorized for use with Claude Code and cannot be used for other API requests.Status: By designAI_APICallError: messages.13: `tool_use` ids were found without `tool_result` blocks immediately after: toolu_01CfJCsh21fK1pAXsXWYJYBA, toolu_01NoqnwsaxoK3AYM2FyrxmjN. Each `tool_use` block must have a corresponding `tool_result` block in the next message.Status: Fixed in releasemessages.3.content.0.type: Expected `thinking` or `redacted_thinking`, but found `tool_use`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`.Status: WorkaroundError: Unexpected error, check log file at [user-home]/.local/share/opencode/log/2025-08-26T215857.log for more detailsStatus: WorkaroundAI_RetryError: Failed after 4 attempts. Last error: Too Many RequestsStatus: Workaroundundefined: The provided model identifier is invalid.Status: Fixed in release
Related reading
- OpenCode Hacked: What the Console Breach Means for Your API KeysOpenCode disclosed a breach of its Console that may have exposed provider keys. Who is affected, what to rotate today, and why hosted key gateways are the real risk.
- OpenCode 2: How to Upgrade From v1 Without Breaking Your SetupOpenCode 2 upgrade from v1: what the migration guide says breaks (plugins, server API, TUI config), what carries over, and a safe checklist before you switch.
- Run Your Coding Agent as an API: OpenCode Server on RailwayOpenCode server on Railway: run opencode serve in a container as a password-protected HTTP API with a persistent volume, reachable from any machine or webhook.
- Give Every Agent PR a Live Preview: Railway Environments for AI Pull RequestsRailway preview environments for agent pull requests: an isolated copy of your whole stack for every PR, so you verify agent changes by running them.
- GPT-6 Astra Release Guide: Benchmarks, $10/$50 Pricing, and How to Run It in Codex and OpenCodeGPT-6 Astra release guide: OpenAI's max-capability model, its $10/$50 pricing and 1.05M context, what the benchmarks do and do not say, and commands to try it.
- Put an AI Reviewer on Every Pull Request: A Webhook Build with OpenCode and RailwayBuild an AI pull request reviewer on Railway: a webhook service runs OpenCode headless on every PR diff and posts findings as a review, never touching the code.
FAQ
What does "ProviderModelNotFoundError" mean in OpenCode?
OpenCode could not resolve the model you referenced to a provider and model it knows about. The official troubleshooting docs say that if you see this error, you have most likely referenced a model incorrectly somewhere.
How do I fix "ProviderModelNotFoundError"?
There are 4 documented fixes. Start with the first: Reference models as <providerId>/<modelId>. Examples from the docs: openai/gpt-4.1, openrouter/google/gemini-2.5-flash, opencode/kimi-k2.
Is this OpenCode error fixed?
Status: By design. Expected behavior, not a bug. The documented fixes change the setup that triggers it. Affected versions: Reported from 0.2.33 (Jul 2025) onward. v1.14.50 improved missing-model errors with suggestions.
Sources
Last verified against 3 sources: official docs, maintainer replies and release notes.
Newsletter
Fixes for the tools you use, weekly
One email per week. New coding agent releases, what broke, and how developers are working around it.