Pricing
| Provider | Input / 1M | Cached / 1M | Output / 1M |
|---|---|---|---|
| Sail Research | $0.30 | $0.15 | $2.00 |
USD, as of November 5, 2026. Live prices
Gemma 4 12B API
- 16.4KContext
- 16.4KMax output
- $0.30/ $2.00From, per 1M in / out
- 1Provider
Providers
Cost
| Workload | Sail Research |
|---|---|
| 1,000 chat replies2K in, 500 out each | $1.60 |
| 1,000 agent tasks50K in, 5K out each | $25.00 |
| Monthly batch job500M in, 50M out | $250.00 |
Gemma 4 versions
| Model | Released | Context | Lowest input | Lowest output | Providers |
|---|---|---|---|---|---|
| Gemma 4 12BThis pagegoogle/gemma-4-12b-it | May 23, 2026 | 16.4K | $0.30 | $2.00 | 1 |
| Gemma 4 31Bgoogle/gemma-4-31b-it | April 2, 2026 | 262K | $0.12 | $0.35 | 4 |
| Gemma 4 31B NVFP4google/gemma-4-31b-it-nvfp4 | April 2, 2026 | 262K | $0.12 | $0.37 | 2 |
Lowest listed price, USD per 1M tokens, as of November 5, 2026.
Quickstart
curl https://api.routerplus.com/v1/chat/completions \
-H "Authorization: Bearer $ROUTERPLUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-4-12b-it",
"messages": [{ "role": "user", "content": "Hello" }]
}'Compare
FAQ
How much does the Gemma 4 12B API cost?
On RouterPlus, Gemma 4 12B costs $0.30 per million input tokens and $2.00 per million output tokens at Sail Research, the lowest listed prices and the provider where routing starts. Prices as of November 5, 2026.
Which providers serve Gemma 4 12B?
Sail Research serves Gemma 4 12B on RouterPlus today.
What is the Gemma 4 12B model ID?
Use "google/gemma-4-12b-it" as the model with the OpenAI-compatible endpoint at https://api.routerplus.com/v1. The same key also accepts the Anthropic API format.
What is the Gemma 4 12B context window?
16.4K tokens of context and up to 16.4K output tokens, per the RouterPlus catalog. A provider can list a lower limit; the console shows each one.
Is Gemma 4 12B open weights?
Yes. Google publishes Gemma 4 12B as an open-weight model, which is why several independent providers can host it.
Do any Gemma 4 12B providers retain prompts?
None of the 1 providers serving Gemma 4 12B on RouterPlus list prompt retention.
Can I reserve capacity for Gemma 4 12B?
Yes. Tell us the model, the throughput you need and the region with "I need inference", and RouterPlus lines up reserved capacity for it.