opencode

We track 24 canonical opencode models plus 11 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.

Muse Spark 1.3 is currently the lowest-priced opencode model, at $1.25 per 1M input tokens and $4.25 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.

Muse Spark 1.3 leads at 1.05M tokens. This is the total of prompt + completion.

Multiple opencode models support tool calling, with Muse Spark 1.3 being a popular pick. The capability column in the table above marks every model with opencode tool-calling support.

Muse Spark 1.3 accepts image input. Other vision-capable opencode models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.