per 1M tokens
Google: Gemma 4 26B A4B
google/gemma-4-26b-a4b-it
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...
Price
per 1M tokens
Cheaper on PrimeIntellect (−82.9%) versus the lab price
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| PrimeIntellect | primeintellect/bf16 | bf16 | $0.03/1M | $0.09/1M | 262K | 100% | Live | openrouter-endpoints |
| Darkbloom | darkbloom | — | $0.042/1M | $0.22/1M | 131K | 100% | Live | openrouter-endpoints |
| AkashML | akashml/fp4 | fp4 | $0.07/1M | $0.24/1M | 131K | 100% | Live | openrouter-endpoints |
| Makora | makora | — | $0.07/1M | $0.24/1M | 256K | 100% | Live | openrouter-endpoints |
| DekaLLM | dekallm/bf16 | bf16 | $0.06/1M | $0.33/1M | 262K | 100% | Live | openrouter-endpoints |
| DeepInfra | — | — | $0.07/1M | $0.34/1M | 262K | — | Listed | deepinfra |
| DeepInfra | deepinfra/fp8 | fp8 | $0.07/1M | $0.34/1M | 262K | 100% | Live | openrouter-endpoints |
| NextBit | nextbit/bf16 | bf16 | $0.09/1M | $0.3/1M | 262K | 100% | Live | openrouter-endpoints |
| Io Net Price differs from the host list |
io-net/bf16 | bf16 | $0.09/1M | $0.31/1M | 262K | 100% | Live | openrouter-endpoints |
| Cloudflare | — | — | $0.1/1M | $0.3/1M | — | — | Listed | cloudflare-pricing |
| Cloudflare | cloudflare | — | $0.1/1M | $0.3/1M | 256K | 100% | Live | openrouter-endpoints |
| CoreWeave | coreweave/bf16 | bf16 | $0.1/1M | $0.3/1M | 262K | 97% | Live | openrouter-endpoints |
| Io Net Price differs from OpenRouter |
— | bf16 | $0.106/1M | $0.328/1M | 262K | — | Listed | ionet |
| Novita | — | — | $0.13/1M | $0.4/1M | 262K | — | Listed | novita |
| Novita | novita/bf16 | bf16 | $0.13/1M | $0.4/1M | 262K | 100% | Live | openrouter-endpoints |
| Parasail | parasail/bf16 | bf16 | $0.13/1M | $0.4/1M | 262K | 100% | Live | openrouter-endpoints |
| Venice | venice/bf16 | bf16 | $0.13/1M | $0.4/1M | 256K | 100% | Live | openrouter-endpoints |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.14/1M | $0.4/1M | 262K | 100% | Live | openrouter-endpoints |
| google-vertex/global | — | $0.15/1M | $0.6/1M | 262K | 100% | Live | openrouter-endpoints | |
| Together | — | — | Not published— | Not published— | 262K | — | Listed | together |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.33 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.0765/1M | $0.255/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.09 | $0.3 | Not published— |
| 2026-09-16 | token | $0.09 | $0.3 | Not published— |
| 2026-09-17 | token | $0.09 | $0.3 | Not published— |
| 2026-09-18 | token | $0.09 | $0.3 | Not published— |
| 2026-09-19 | token | $0.09 | $0.3 | Not published— |
| 2026-09-20 | token | $0.09 | $0.3 | Not published— |
| 2026-09-21 | token | $0.09 | $0.3 | Not published— |
| 2026-09-22 | token | $0.09 | $0.3 | Not published— |
| 2026-09-23 | token | $0.09 | $0.3 | Not published— |
| 2026-09-24 | token | $0.09 | $0.3 | Not published— |
| 2026-09-25 | token | $0.0675 | $0.225 | Not published— |
| 2026-09-26 | token | $0.0675 | $0.225 | Not published— |
| 2026-09-27 | token | $0.0675 | $0.225 | Not published— |
| 2026-09-28 | token | $0.09 | $0.3 | Not published— |
| 2026-09-29 | token | $0.09 | $0.3 | Not published— |
| 2026-09-30 | token | $0.09 | $0.3 | Not published— |
| 2026-10-01 | token | $0.09 | $0.3 | Not published— |
| 2026-10-02 | token | $0.09 | $0.3 | Not published— |
| 2026-10-03 | token | $0.0675 | $0.225 | Not published— |
| 2026-10-04 | token | $0.0675 | $0.225 | Not published— |
| 2026-10-05 | token | $0.09 | $0.3 | Not published— |
| 2026-10-06 | token | $0.09 | $0.3 | Not published— |
| 2026-10-07 | token | $0.09 | $0.3 | Not published— |
| 2026-10-08 | token | $0.0765 | $0.255 | Not published— |
| 2026-10-09 | token | $0.09 | $0.3 | Not published— |
| 2026-10-10 | token | $0.0675 | $0.225 | Not published— |
| 2026-10-11 | token | $0.0675 | $0.225 | Not published— |
| 2026-10-12 | token | $0.09 | $0.3 | Not published— |
| 2026-10-13 | token | $0.09 | $0.3 | Not published— |
| 2026-10-14 | token | $0.09 | $0.3 | Not published— |
| 2026-10-15 | token | $0.09 | $0.3 | Not published— |
| 2026-10-16 | token | $0.09 | $0.3 | Not published— |
| 2026-10-17 | token | $0.0675 | $0.225 | Not published— |
| 2026-10-18 | token | $0.0675 | $0.225 | Not published— |
| 2026-10-19 | token | $0.09 | $0.3 | Not published— |
| 2026-10-20 | token | $0.09 | $0.3 | Not published— |
| 2026-10-21 | token | $0.09 | $0.3 | Not published— |
| 2026-10-22 | token | $0.09 | $0.3 | Not published— |
| 2026-10-23 | token | $0.09 | $0.3 | Not published— |
| 2026-10-24 | token | $0.0675 | $0.225 | Not published— |
| 2026-10-25 | token | $0.0675 | $0.225 | Not published— |
| 2026-10-26 | token | $0.09 | $0.3 | Not published— |
| 2026-10-27 | token | $0.09 | $0.3 | Not published— |
| 2026-10-28 | token | $0.09 | $0.3 | Not published— |
| 2026-10-29 | token | $0.09 | $0.3 | Not published— |
| 2026-10-30 | token | $0.0765 | $0.255 | Not published— |
Alternatives
- ByteDance Seed: Seed 1.6 Flash$0.075/1M · Compare
- Ling 3.0 Flash VL$0.075/1M · Compare
- Mistral: Mistral Small 3.2 24B$0.075/1M · Compare
- mistralai/Mistral-Small-3.2-24B-Instruct-2506$0.075/1M · Compare
- Nex AGI: Nex-N2.5-Pro$0.075/1M · Compare
- OpenAI: GPT-4o-mini (batch)$0.075/1M · Compare
Parameters (20)
Call this model
OpenRouter id google/gemma-4-26b-a4b-it. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"google/gemma-4-26b-a4b-it","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "google/gemma-4-26b-a4b-it",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "google/gemma-4-26b-a4b-it", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())