Google: gemma-4-26b-a4b-it-moonlight:free
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.
Inputs used for the providers' own purposes
At least one provider of this model uses your inputs for its own purposes, for example to train AI models. Do not enter personal data of third parties or sensitive data. You can object to this use at any time in your account settings or via "Manage consents" in the chat.
Read the privacy policyPricing
Uptime
Performance
Usage & Ranking
Supported parameters
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | All providers | - |
| include_reasoning | All providers | - |
| logit_bias | Some providers | - |
| logprobs | All providers | - |
| max_tokens | All providers | - |
| min_p | Some providers | - |
| presence_penalty | All providers | - |
| reasoning | All providers | - |
| repetition_penalty | All providers | - |
| response_format | All providers | - |
| seed | All providers | - |
| stop | All providers | - |
| structured_outputs | All providers | - |
| temperature | All providers | 1 |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_k | All providers | 64 |
| top_logprobs | All providers | - |
| top_p | All providers | 0.95 |