Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Model details →Google: Gemma 4 31B (batch) vs Inception: Mercury 2.5 Preview
Google: Gemma 4 31B (batch) and Inception: Mercury 2.5 Preview are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Model details →Side-by-side comparison
| Capability | Google: Gemma 4 31B (batch) | Inception: Mercury 2.5 Preview | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 262K | 260K | 🏆 Google: Gemma 4 31B (batch) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.39 | $0.04 | 🏆 Inception: Mercury 2.5 Preview |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.97 | $0.15 | 🏆 Inception: Mercury 2.5 Preview |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | Yes | — | 🏆 Google: Gemma 4 31B (batch) |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is Google: Gemma 4 31B (batch) better than Inception: Mercury 2.5 Preview?
Google: Gemma 4 31B (batch) and Inception: Mercury 2.5 Preview are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
What's the price difference between Google: Gemma 4 31B (batch) and Inception: Mercury 2.5 Preview?
Input: $0.39 vs $0.04 per 1M tokens. Output: $0.97 vs $0.15 per 1M tokens.
What context windows do Google: Gemma 4 31B (batch) and Inception: Mercury 2.5 Preview support?
Google: Gemma 4 31B (batch) supports up to 262K tokens. Inception: Mercury 2.5 Preview supports up to 260K tokens.
Do both Google: Gemma 4 31B (batch) and Inception: Mercury 2.5 Preview support tool calling?
Google: Gemma 4 31B (batch): yes. Inception: Mercury 2.5 Preview: yes.