Gemma 4 26B A4B Instruct
Gemma 4 26B A4B Instruct is Google's language model with a 262K context window and up to 131K output tokens, available from 2 providers, starting at $0.080 / 1M input and $0.350 / 1M output. Instruction-tuned Gemma 4 MoE model with 26B total parameters and ~4B active per token, supporting vision, tool use, and file input with a 256K context window.
Google's language model with a 262K context window and up to 131K output tokens, available from 2 providers, starting at $0.080 / 1M input and $0.350 / 1M output. Instruction-tuned Gemma 4 MoE model with 26B total parameters and ~4B active per token, supporting vision, tool use, and file input with a 256K context window.Capabilities
Input4/5
✓
✓
·
✓
✓
Output1/5
✓
·
·
·
·
Capabilities2/13
✓
·
✓
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
 OpenRouter | $0.080 | $0.350 | $0.010 |
 Vercel AI Gateway | $0.130 | $0.400 | N/A |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Gemma 4 26B A4B Instruct | 262K | $0.080 | $0.350 | Current | |
| Gemma 4 31B Instruct | 262K | $0.130 | $0.380 | Available | |
| Gemma 4 31B IT | 262K | — | — | Available |
HuggingFace
726 likes2,562,020 downloads/month2,563,768 total downloads