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 a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.
Model card on Hugging Face- Input / output price
- $0.00 / $0.00 per 1M
- Context
- 262K tokens
- Released
- Apr 2, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
13 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Google Gemini AI google_gemini_ai/gemma-4-26b-a4b-it | $0.00/M | $0.00/M |
EmpirioLabs empiriolabs/gemma-4-26b-a4b-it | $0.05/M | $0.29/M |
DeepInfra deepinfra/gemma-4-26b-a4b-it | $0.07/M | $0.34/M |
Featherless featherless/gemma-4-26b-a4b-it | $0.07/M | $0.34/M |
Makora makora/gemma-4-26b-a4b-it | $0.09/M | $0.28/M |
Nextbit256 nextbit256/gemma-4-26b-a4b-it | $0.09/M | $0.30/M |
IO.net ionet/gemma-4-26b-a4b-it | $0.0993/M | $0.315/M |
Concentrate concentrate/gemma-4-26b | $0.10/M | $0.30/M |
Prime Intellect prime_intellect/google/gemma-4-26b-a4b-it | $0.10/M | $0.30/M |
NovitaRetiring novita/gemma-4-26b-a4b-it | $0.13/M | $0.40/M |
Parasail parasail/gemma-4-26b-a4b-it | $0.13/M | $0.40/M |
Tera tera/gemma-4-26b-a4b-it | $0.15/M | $0.60/M |
OpenRouter openrouter/gemma-4-26b-a4b-it | $0.0765/M | $0.255/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 13 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.09 per 1M
- Average output
- $0.32 per 1M
- Average cache read
- $0.08 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better111tokens/sacross providers
Time to first token
Lower is better1.2sacross providers
Response latency
Lower is better6.3sacross providers
Benchmarks
The Respan Index plus 12 published scores from 4 sources, each linked to where it was published.
18.5/ 100
Respan Index#141 of 176
- 141Gemma 4 26B A4B18.5
- 141Qwen3 235B-A22B Thinking 250718.5
- 141Gemini 2.5 Flash18.5
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBench v6Google | 77.1% | Apr 2, 2026 | |
| WeirdMLHåvard Tveit Ihle | 35.2% | Håvard Tveit Ihle | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondGoogle | 82.3% | Apr 2, 2026 | |
| GPQA DiamondEpoch AI | 73.2% | Epoch AI | Oct 5, 2026 |
| Humanity's Last Exam (no tools)Google | 8.7% | Apr 2, 2026 | |
| Chess PuzzlesEpoch AI | 6% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2026 (no tools)Google | 88.3% | Apr 2, 2026 | |
| OTIS Mock AIME 2024-2025Epoch AI | 82.2% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1438 Elo · #80 of 191 | LMArena | Nov 19, 2026 |
| LMArena WebDevLMArena | 1358 Elo · #101 of 124 | LMArena | Nov 20, 2026 |
| LMArena VisionLMArena | 1241 Elo · #53 of 91 | LMArena | Nov 19, 2026 |
Compare Gemma 4 26B A4B IT: Gemma 4 26B A4B vs Gemma 4 31B, Gemma 4 26B A4B vs Gemini 4 Neon, Gemma 4 26B A4B vs Gemini 4 Carbon, Gemma 4 26B A4B vs Gemini 4 Hydrogen, Gemma 4 26B A4B vs Gemini 4 Argon, Gemma 4 26B A4B vs Gemini 3.8 Flash
Apps
Use Gemma 4 26B A4B IT in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Gemma 4 26B A4B IT FAQ
Short answers, built from the data on this page.
Gemma 4 26B A4B IT is a model from Google Gemini AI, released on Apr 2, 2026. 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 a fraction of the compute cost. Supports multimodal input including text, images, and video (up to 60s at 1fps). Features a 256K token context window, native function calling, configurable thinking/reasoning mode, and structured output support. Released under Apache 2.0.
On the Respan gateway, Gemma 4 26B A4B IT costs from $0.00 per 1M input tokens and $0.00 per 1M output tokens on Google Gemini AI, after gateway discounts. Averaged across its 13 providers, it costs $0.09 per 1M input tokens and $0.32 per 1M output tokens.
Gemma 4 26B A4B IT is available through 13 providers: Google Gemini AI, EmpirioLabs, DeepInfra, Featherless, Makora, Nextbit256, and 7 more.
Gemma 4 26B A4B IT accepts up to 262K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "google_gemini_ai/gemma-4-26b-a4b-it". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Gemma 4 26B A4B IT scores 18.5 out of 100 on the Respan Index v1.1, ranking #141 of 176 models. By category: Coding 4.1, Agents 13.3 (estimated), Reasoning 20.4, Knowledge & language 15.2, and Human preference 50.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Gemma 4 26B A4B IT has 12 published benchmark scores, including LiveCodeBench v6 77.1%, GPQA Diamond 82.3%, and AIME 2026 (no tools) 88.3%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.