Gemma 4 26B A4B
by Google · google/gemma-4-26b-a4b-it · #59 cheapest of 457 paid models
Prices updated Nov 18, 2026, 8:44 AM UTC · refreshed nightly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.076
per 1M tokens
Output
$0.255
per 1M tokens
Blended (3:1)
$0.121
3 input : 1 output
Cache read
$0.042
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Gemma 4 26B A4B with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.121 | $0.008058 | — |
| 50% | $0.108 | $0.006358 | −21% |
| 90% | $0.098 | $0.004998 | −38% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.000115 | $0.1147 |
| Document summary | 8,000 | 1,000 | $0.000867 | $0.867 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.002805 | $2.80 |
| Long-context analysis | 150,000 | 5,000 | $0.0127 | $12.75 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
39.3
Math Index
—
Agentic Index
2.9
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Specs
Context window
262K
tokens
Max output
236K
tokens
Input modalities
image, text, video
Tokenizer
Gemma