Google: Gemma 3 4B
google/gemma-3-4b-itGemma 3 introduces multimodality, supporting vision-language input and text outputs.
Modalities
In / out per 1M$0.05 / $0.10
Context128K
ReleasedMar 13, 2025
Providers
2 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 DeepInfraus · bf16 | $0.05 | $0.10 | Variable | 1.80s | 27 tps | 100% |
| $0.04 | $0.05 | $0.02 | 0.49s | 120 tps | 98.72% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Gemma 3 4B in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Gemma 3 4B costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.05
per 1M tokens
Output
$0.10
per 1M tokens
Cache read
—
not published
Included in every pass
Gemma 3 4B 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.
0.0s1.0s2.0s3.0s4.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepInfra (us) Parasail
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DeepInfra (us) Parasail
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 98.78%
Oct 16, 12:00 PMNow
Availability over the last 24 hoursAvailability 99.4%
100% 95% 90% 85%
Oct 18, 12:10 PMNow
Apps
Tools that most often run Gemma 3 4B, by tokens this week.
Activity
4.6B tokens processed market-wide in the last month.
0100.0M200.0M300.0M400.0M
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens
FAQ
Which model id do I use for Gemma 3 4B?
google/gemma-3-4b-it. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Gemma 3 4B hold?
131,072 tokens per request, of which up to 16,384 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does Gemma 3 4B cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.05 per 1M input tokens and $0.10 per 1M output tokens.
How current is its knowledge?
Training data runs to Aug 2024. Anything later has to come from your prompt or a tool call.
Who built Gemma 3 4B?
Google, in the Gemma family.
Explore
Other models your pass can call.
