per 1M tokens
Google: Gemma 4 31B
google/gemma-4-31b-it
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...
Price
per 1M tokens
Cheaper on CoreWeave (−36%) versus the OpenRouter list 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 |
|---|---|---|---|---|---|---|---|---|
| CoreWeave | coreweave/fp4 | fp4 | $0.1/1M | $0.34/1M | 262K | 100% | Live | openrouter-endpoints |
| Venice | venice/fp4 | fp4 | $0.12/1M | $0.36/1M | 256K | 100% | Live | openrouter-endpoints |
| Chutes | chutes/fp4 | fp4 | $0.12/1M | $0.37/1M | 131K | 100% | Live | openrouter-endpoints |
| DeepInfra Price differs from the host list |
deepinfra/fp8/flex | fp8 | $0.16/1M | $0.32/1M | 262K | 100% | Live | openrouter-endpoints |
| Crusoe | crusoe/bf16 | bf16 | $0.14/1M | $0.4/1M | 262K | 100% | Live | openrouter-endpoints |
| DekaLLM | dekallm | — | $0.14/1M | $0.4/1M | 262K | 100% | Live | openrouter-endpoints |
| Friendli | — | — | $0.14/1M | $0.4/1M | 262K | — | Listed | friendli |
| Friendli | friendli | — | $0.14/1M | $0.4/1M | 262K | 100% | Live | openrouter-endpoints |
| Novita | — | — | $0.14/1M | $0.4/1M | 262K | — | Listed | novita |
| Novita | novita/bf16 | bf16 | $0.14/1M | $0.4/1M | 262K | 93% | Live | openrouter-endpoints |
| Parasail | parasail/fp8 | fp8 | $0.15/1M | $0.4/1M | 262K | 100% | Live | openrouter-endpoints |
| Phala | — | — | $0.15/1M | $0.46/1M | 262K | — | Listed | phala |
| DeepInfra Price differs from the host list |
deepinfra/turbo | fp4 | $0.135/1M | $0.51/1M | 262K | 100% | Live | openrouter-endpoints |
| DeepInfra | — | — | $0.2/1M | $0.4/1M | 262K | — | Listed | deepinfra |
| DeepInfra | deepinfra/fp8 | fp8 | $0.2/1M | $0.4/1M | 262K | 100% | Live | openrouter-endpoints |
| DeepInfra Price differs from the host list |
deepinfra/fp8/priority | fp8 | $0.3/1M | $0.6/1M | 262K | 100% | Live | openrouter-endpoints |
| Io Net Price differs from OpenRouter |
— | — | $0.301/1M | $0.68/1M | 262K | — | Listed | ionet |
| Sarvam | — | — | $0.3674/1M | $0.9447/1M | — | — | Listed | sarvam-docs |
| Together | — | — | $0.39/1M | $0.97/1M | 262K | — | Listed | together |
| Io Net Price differs from the host list |
io-net | — | $0.361/1M | $1.093/1M | 262K | 100% | Live | openrouter-endpoints |
| SambaNova | — | — | $0.38/1M | $1.15/1M | 131K | — | Listed | sambanova |
| ModelRun | modelrun/fp4 | fp4 | $0.75/1M | $1/1M | 262K | 100% | Live | openrouter-endpoints |
| SiliconFlow | siliconflow/fp8 | fp8 | $0.75/1M | $1/1M | 262K | 100% | Live | openrouter-endpoints |
| SambaNova | sambanova | — | $0.38/1M | $1.15/1M | 131K | 86% | Down | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.60 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.2/1M | $0.4/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.09 | $0.34 | Not published— |
| 2026-09-16 | token | $0.09 | $0.34 | Not published— |
| 2026-09-17 | token | $0.09 | $0.34 | Not published— |
| 2026-09-18 | token | $0.09 | $0.34 | Not published— |
| 2026-09-19 | token | $0.09 | $0.34 | Not published— |
| 2026-09-20 | token | $0.09 | $0.34 | Not published— |
| 2026-09-21 | token | $0.09 | $0.34 | Not published— |
| 2026-09-22 | token | $0.09 | $0.34 | Not published— |
| 2026-09-23 | token | $0.09 | $0.34 | Not published— |
| 2026-09-24 | token | $0.09 | $0.34 | Not published— |
| 2026-09-25 | token | $0.09 | $0.34 | Not published— |
| 2026-09-26 | token | $0.09 | $0.34 | Not published— |
| 2026-09-27 | token | $0.09 | $0.34 | Not published— |
| 2026-09-28 | token | $0.09 | $0.34 | Not published— |
| 2026-09-29 | token | $0.09 | $0.34 | Not published— |
| 2026-09-30 | token | $0.09 | $0.34 | Not published— |
| 2026-10-01 | token | $0.09 | $0.34 | Not published— |
| 2026-10-02 | token | $0.09 | $0.34 | Not published— |
| 2026-10-03 | token | $0.09 | $0.34 | Not published— |
| 2026-10-04 | token | $0.09 | $0.34 | Not published— |
| 2026-10-05 | token | $0.09 | $0.34 | Not published— |
| 2026-10-06 | token | $0.09 | $0.34 | Not published— |
| 2026-10-07 | token | $0.09 | $0.34 | Not published— |
| 2026-10-08 | token | $0.09 | $0.34 | Not published— |
| 2026-10-09 | token | $0.09 | $0.34 | Not published— |
| 2026-10-10 | token | $0.09 | $0.34 | Not published— |
| 2026-10-11 | token | $0.09 | $0.34 | Not published— |
| 2026-10-12 | token | $0.09 | $0.34 | Not published— |
| 2026-10-13 | token | $0.09 | $0.34 | Not published— |
| 2026-10-14 | token | $0.09 | $0.34 | Not published— |
| 2026-10-15 | token | $0.2 | $0.4 | Not published— |
| 2026-10-16 | token | $0.2 | $0.4 | Not published— |
| 2026-10-17 | token | $0.2 | $0.4 | Not published— |
| 2026-10-18 | token | $0.2 | $0.4 | Not published— |
| 2026-10-19 | token | $0.2 | $0.4 | Not published— |
| 2026-10-20 | token | $0.2 | $0.4 | Not published— |
| 2026-10-21 | token | $0.2 | $0.4 | Not published— |
| 2026-10-22 | token | $0.2 | $0.4 | Not published— |
| 2026-10-23 | token | $0.2 | $0.4 | Not published— |
| 2026-10-24 | token | $0.2 | $0.4 | Not published— |
| 2026-10-25 | token | $0.2 | $0.4 | Not published— |
| 2026-10-26 | token | $0.2 | $0.4 | Not published— |
| 2026-10-27 | token | $0.2 | $0.4 | Not published— |
| 2026-10-28 | token | $0.2 | $0.4 | Not published— |
| 2026-10-29 | token | $0.2 | $0.4 | Not published— |
| 2026-10-30 | token | $0.2 | $0.4 | Not published— |
Alternatives
- deepseek-ai/DeepSeek-V4.1-Flash$0.2/1M · Compare
- deepseek-ai/DeepSeek-V4.1-Flash-1017$0.2/1M · Compare
- Doubao Seed Character$0.2/1M · Compare
- google/gemma-4-31B-it$0.2/1M · Compare
- Google: Gemini Embedding 2$0.2/1M · Compare
- Google: Gemini Embedding 2 Preview$0.2/1M · Compare
Parameters (19)
Call this model
OpenRouter id google/gemma-4-31b-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-4-31b-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-4-31b-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-4-31b-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())