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$0.08 / $0.26
Context256K
ReleasedApr 3, 2026
Providers
13 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.09 | $0.30 | $0.05 | 0.39s | 49 tps | 100% | |
| $0.10 | $0.30 | $0.05 | 0.78s | 38 tps | 100% | |
| $0.11 | $0.32 | $0.04 | 0.67s | 60 tps | 100% | |
| $0.06 | $0.33 | $0.04 | 0.75s | 40 tps | 99.97% | |
 CoreWeavebf16 | $0.10 | $0.30 | $0.05 | 0.32s | 35 tps | 99.97% |
| $0.13 | $0.40 | Variable | 0.64s | 50 tps | 99.97% | |
| $0.13 | $0.40 | $0.05 | 0.97s | 36 tps | 99.92% | |
 Darkbloom | $0.04 | $0.22 | $0.02 | 2.89s | 25 tps | 99.84% |
 DeepInfraus · fp8 | $0.07 | $0.34 | Variable | 0.36s | 45 tps | 99.81% |
| $0.10 | $0.28 | $0.05 | 0.42s | 62 tps | 99.79% | |
| $0.13 | $0.40 | $0.05 | 0.78s | 37 tps | 99.47% | |
 SiliconFlowfp8 | $0.14 | $0.40 | $0.05 | 1.32s | 43 tps | 93.2% |
 Google Vertexglobal | $0.15 | $0.60 | Variable | 0.66s | 21 tps | 84.05% |
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
$0.08
per 1M tokens
Output
$0.26
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.
0.0s100.0s200.0s300.0s400.0s
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
Google Vertex (global) Makora Parasail CoreWeave NovitaAI Cloudflare Venice DeepInfra (us) io.net Darkbloom SiliconFlow NextBit DekaLLM
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 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
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 99.97%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.98%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run Gemma 4 26B A4B, by tokens this week.
Activity
1472.3B 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 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 $0.08 per 1M input tokens and $0.26 per 1M output tokens.
Who built Gemma 4 26B A4B?
Google, in the Gemma family.
Explore
Other models your pass can call.
