Google: Gemma 4 26B A4B
google/gemma-4-26b-a4b-itGemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Modalities
In / out per 1M$0.07 / $0.23
Context256K
ReleasedApr 3, 2026
Providers
13 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.06 | $0.33 | $0.04 | 0.67s | 54 tps | 100% | |
| $0.09 | $0.30 | $0.05 | 0.49s | 42 tps | 100% | |
| $0.09 | $0.31 | $0.04 | 0.56s | 72 tps | 100% | |
| $0.10 | $0.30 | $0.05 | 0.87s | 39 tps | 100% | |
 Darkbloom | $0.04 | $0.22 | $0.02 | 0.75s | 60 tps | 99.97% |
 CoreWeavebf16 | $0.10 | $0.30 | $0.05 | 0.24s | 29 tps | 99.97% |
| $0.13 | $0.40 | Variable | 0.78s | 67 tps | 99.91% | |
| $0.13 | $0.40 | $0.05 | 0.96s | 46 tps | 99.88% | |
| $0.13 | $0.40 | $0.05 | 0.89s | 61 tps | 99.83% | |
 DeepInfraus · fp8 | $0.07 | $0.34 | Variable | 0.58s | 47 tps | 99.8% |
| $0.10 | $0.18 | $0.05 | 0.54s | 67 tps | 99.62% | |
 SiliconFlowfp8 | $0.14 | $0.40 | $0.05 | 1.22s | 25 tps | 97.45% |
 Google Vertexglobal | $0.15 | $0.60 | Variable | 1.53s | 25 tps | 94.2% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Gemma 4 26B A4B in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Gemma 4 26B A4B costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.07
per 1M tokens
Output
$0.23
per 1M tokens
Cache read
$0.04
per 1M cached tokens
Included in every pass
Gemma 4 26B A4B 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.
0.0s5.0s10.0s15.0s20.0s
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
Google Vertex (global) Makora Parasail CoreWeave NovitaAI Cloudflare Venice DeepInfra (us) io.net Darkbloom SiliconFlow NextBit DekaLLM
0 tok/s250 tok/s500 tok/s750 tok/s1000 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
Google Vertex (global) Makora Parasail CoreWeave NovitaAI Cloudflare Venice DeepInfra (us) io.net Darkbloom SiliconFlow NextBit DekaLLM
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.96%
Oct 16, 9:00 AMNow
Availability over the last 24 hoursAvailability 99.95%
100% 98% 97% 95%
Oct 18, 9:50 AMNow
Apps
Tools that most often run Gemma 4 26B A4B, by tokens this week.
Activity
1494.3B tokens processed market-wide in the last month.
020.0B40.0B60.0B80.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens
FAQ
Which model id do I use for Gemma 4 26B A4B?
google/gemma-4-26b-a4b-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 26B A4B hold?
262,144 tokens per request, of which up to 235,929 can be the response.
What can it accept and return?
Input: image, text, video. Output: text.
What does Gemma 4 26B A4B cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.07 per 1M input tokens and $0.23 per 1M output tokens.
Who built Gemma 4 26B A4B?
Google, in the Gemma family.
Explore
Other models your pass can call.
