LLM Comparison
Gemma 4 26B A4B vs Mistral Small 4
Side-by-side specs, pricing & capabilities · Updated April 2026
Add to comparison
2/6 modelsSame tier:
M Mistral Small 4 | ||
|---|---|---|
| Organization | Mistral AI | |
| OpenTools Score | ||
| Family | Gemma | Mistral |
| Status | Current | Current |
| Release Date | Apr 2026 | Mar 2026 |
| Context Window | 262K tokens | 262K tokens |
| Input Price | — | $0.15/M tokens |
| Output Price | — | $0.60/M tokens |
| Pricing Notes | Free tier available on OpenRouter with rate limits | Cache read: $0.0150/M tokens |
| Capabilities | textvisionvideocode | textvisioncodetool-use |
| Max Output | 33K tokens | — |
| API Identifier | google/gemma-4-26b-a4b-it:free | mistralai/mistral-small-2603 |
| Benchmarks | ||
| MMLU | — | 76.5 |
| View Gemma 4 26B A4B | View Mistral Small 4 | |
Gemma 4 26B A4B
Gemma 4 26B A4B is a multimodal llm from Google. Supports up to 262,144 token context window. Available free with rate limits on OpenRouter.
Mistral AI
Mistral Small 4
Mistral Small 4 is a multimodal llm from Mistral AI. Supports up to 262,144 token context window. Achieves 76.5% on MMLU. Available from $0.15/M input tokens.
More Comparisons
Looking for more AI models?
Browse All LLMs