Google: Gemma 4 31B
google/gemma-4-31b-itGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output.
Modalities
In / out per 1M$0.09 / $0.34
Context256K
ReleasedApr 2, 2026
Providers
13 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 DeepInfra Turbous · fp4 | $0.09 | $0.34 | $0.05 | 0.45s | 33 tps | 100% |
 CoreWeavefp4 | $0.10 | $0.34 | $0.10 | 0.66s | 52 tps | 100% |
| $0.12 | $0.36 | $0.09 | 0.67s | 34 tps | 100% | |
| DeepInfraus · fp8 | $0.20 | $0.40 | Variable | 1.07s | 27 tps | 100% |
| $0.14 | $0.40 | Variable | 5.24s | 43 tps | 99.87% | |
 ModelRun [by Modular]fp4 | $0.75 | $1.00 | $0.20 | 0.13s | 135 tps | 99.39% |
| $0.15 | $0.40 | $0.06 | 1.62s | 21 tps | 98.56% | |
| $0.36 | $1.09 | $0.18 | 1.06s | 32 tps | 97.19% | |
 SiliconFlowfp8 | $0.75 | $1.00 | $0.25 | 1.04s | 42 tps | 94.83% |
| $0.14 | $0.40 | $0.14 | 0.68s | 18 tps | 94.59% | |
| $0.12 | $0.37 | $0.01 | 2.82s | 16 tps | 90.64% | |
| $0.38 | $1.15 | Variable | 2.11s | 82 tps | 89.82% | |
| $0.14 | $0.40 | Variable | 1.60s | 20 tps | 64.68% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Gemma 4 31B in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Gemma 4 31B costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.09
per 1M tokens
Output
$0.34
per 1M tokens
Cache read
$0.05
per 1M cached tokens
Included in every pass
Gemma 4 31B is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s10.0s20.0s30.0s40.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
SambaNova Crusoe Friendli DeepInfra Turbo (us) SiliconFlow Chutes Venice io.net CoreWeave NovitaAI Parasail ModelRun [by Modular] DeepInfra (us)
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
SambaNova Crusoe Friendli DeepInfra Turbo (us) SiliconFlow Chutes Venice io.net CoreWeave NovitaAI Parasail ModelRun [by Modular] DeepInfra (us)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.9%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.93%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run Gemma 4 31B, by tokens this week.
Activity
1897.9B tokens processed market-wide in the last month.
020.0B40.0B60.0B80.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Gemma 4 31B?
google/gemma-4-31b-it. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Gemma 4 31B hold?
262,144 tokens per request, of which up to 16,384 can be the response.
What can it accept and return?
Input: image, text, video. Output: text.
What does Gemma 4 31B cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.09 per 1M input tokens and $0.34 per 1M output tokens.
Who built Gemma 4 31B?
Google, in the Gemma family.
Explore
Other models your pass can call.
