Gemma 4 31B
by Google · google/gemma-4-31b-it · #60 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.12
per 1M tokens
Output
$0.37
per 1M tokens
Blended (3:1)
$0.182
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Gemma 4 31B (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.182 | $0.0126 | — |
| 50% | $0.182 | $0.0126 | −0% |
| 90% | $0.182 | $0.0126 | −0% |
*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 | $0.000171 | $0.171 |
| Document summary | 8,000 | 1,000 | $0.00133 | $1.33 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00434 | $4.34 |
| Long-context analysis | 150,000 | 5,000 | $0.0198 | $19.85 |
Performance
Intelligence Index
29.4
AA composite quality
Coding Index
43.4
Math Index
—
Agentic Index
14.4
Output speed
35 tok/s
median
Time to first token
0.98s
median
Time to first answer
50.29s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 85.7% |
| Humanity's Last Exam | 22.7% |
| SciCode | 43.4% |
| IFBench | 75.6% |
| AA-LCR (Long Context Reasoning) | 62.0% |
| Terminal-Bench Hard | 36.4% |
| Terminal-Bench 2.1 | 43.4% |
| τ²-Bench (Telecom) | 59.9% |
| τ³-Bench Banking | 15.1% |
Specs
Context window
262K
tokens
Max output
16K
tokens
Input modalities
image, text, video
Tokenizer
Gemma