OpenCode Boosts AI Coding Quota to $100 for $10 Monthly Subscribers

AI coding tool OpenCode has launched Phase 4 of Operation Cheepseek. OpenCode Go subscribers paying $10 a month can now use $100 worth of DeepSeek V4.1 Flash model quota.

The plan has gone through three earlier stages: the quota grew from $30, became permanent in stage two, and stage three removed peak-hour limits as OpenCode reached 100,000 GitHub stars.

DeepSeek V4.1 Flash is a native multimodal mixture-of-experts model released by DeepSeek in September. It has 552B total parameters, supports a context window of about 1 million tokens, and activates only about 8B parameters per input token, keeping inference costs low.

With the larger quota, users can handle more code generation, code review, and long document tasks under the same subscription. Note that the quota is counted by actual model usage, so real limits still depend on request frequency and context length.