Gemma 4 26B A4B
by Google · google/gemma-4-26b-a4b-it
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
- Input / 1M tokens
- $0.09
- Output / 1M tokens
- $0.30
- Context
- 262K
Specs
| Input price | $0.09 / 1M tokens |
|---|---|
| Output price | $0.30 / 1M tokens |
| Cached input | $0.05 / 1M tokens |
| Context window | 262K tokens |
| Max output | 236K tokens |
| Reads | image, text, video |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Apr 3, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
15 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| PrimeIntellect | bf16 | 262K | 32.8K | $0.03 | $0.09 | $0.015 | 100% | 366 ms | 54 tok/s | Normal | |
| Darkbloom | — | 131K | 32.8K | $0.042 | $0.22 | $0.021 | 100% | 531 ms | 52 tok/s | Normal | |
| AkashML | fp4 | 131K | 118K | $0.07 | $0.24 | $0.046 | 100% | 694 ms | 77 tok/s | Normal | |
| Makora | — | 256K | 128K | $0.07 | $0.24 | $0.046 | 100% | 285 ms | 143 tok/s | Normal | |
| DekaLLM | bf16 | 262K | 236K | $0.06 | $0.33 | $0.04 | 100% | 588 ms | 68 tok/s | Normal | |
| NextBit | bf16 | 262K | 236K | $0.09 | $0.30 | $0.05 | 100% | 293 ms | 61 tok/s | Normal | |
| Cloudflare | — | 256K | 230K | $0.10 | $0.30 | $0.05 | 100% | 882 ms | 51 tok/s | Normal | |
| CoreWeave | bf16 | 262K | 236K | $0.10 | $0.30 | $0.05 | 100% | 315 ms | 61 tok/s | Normal | |
| Io Net | bf16 | 262K | 236K | $0.09 | $0.31 | $0.041 | 100% | 533 ms | 88 tok/s | Normal | |
| DeepInfra | fp8 | 262K | 16.4K | $0.07 | $0.34 | — | 96.7% | 375 ms | 66 tok/s | Normal | |
| Novita | bf16 | 262K | 131K | $0.13 | $0.40 | — | 100% | 1.03 s | 144 tok/s | Normal | |
| Parasail | bf16 | 262K | 236K | $0.13 | $0.40 | $0.05 | 100% | 473 ms | 85 tok/s | Normal | |
| Venice | bf16 | 256K | 8.19K | $0.13 | $0.40 | $0.05 | 100% | 728 ms | 84 tok/s | Normal | |
| SiliconFlow | fp8 | 262K | 236K | $0.14 | $0.40 | $0.05 | 93.3% | 1.15 s | 37 tok/s | Normal | |
| — | 262K | 236K | $0.15 | $0.60 | — | 80.8% | 1.67 s | 23 tok/s | Code -2 |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#49
by tokens, Oct 29, 2026
55.9B
tokens that day · 7 days −19%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- Google
Gemini 3.8 Flash
- Input
- $0.825
- Output
- $4.13
- Context
- 1.05M
- Google
Gemini 4 Argon
- Input
- $2.00
- Output
- $10.00
- Context
- 1.05M
- Google
Gemini 3.1 Flash Lite
- Input
- $0.25
- Output
- $1.50
- Context
- 1.05M
- Google
Gemini 3 Flash Preview
- Input
- $0.50
- Output
- $3.00
- Context
- 1.05M
- Google
Gemma 4 31B
- Input
- $0.20
- Output
- $0.40
- Context
- 262K
- Google
Gemini 4 Argon (batch)
- Input
- $1.00
- Output
- $5.00
- Context
- 1.05M