FrogNano-4B-2609

microsoft/frognano-4b-2609

Microsoft repository-level coding agent derived from Qwen3.5-4B and trained with reinforcement learning using the Leaf harness. Intended and evaluated modalities are text input and text/tool-call output; inherited image/video components are unsupported. Evaluated configuration uses approximately 131K combined context and up to 8,192 generated tokens per turn; these are configuration-specific, not a model-wide output limit.

Compare

Context window: -
Input: Text
Output: Text
Released: 2026-09-22

Weights: Open
License: Apache-2.0

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance

No evaluation results available.

Providers

No providers found

ModelRegistry · Catalog updated 2026-11-12