Last refreshed 2026-06-29. Next refresh: weekly.
Why use Gemma 4 26B A4B IT on Vercel AI Gateway?
Vercel AI Gateway offers Gemma 4 26B A4B IT with pay-as-you-go pricing at $0.13/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Gemma 4 26B A4B IT across 9 providers to find the best fit for your use caseInput / 1M
$0.13
Output / 1M
$0.40
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AI_GATEWAY_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],Model ID
google/gemma-4-26b-a4b-itRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="google/gemma-4-26b-a4b-it",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "google/gemma-4-26b-a4b-it", not the LLMReference slug "gemma-4-26b-a4b-it".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Gemma 4 26B A4B IT Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | $0.10 | $0.30 |
| Google AI Studio | — | — |
| GCP Vertex AI | $0.15 | $0.60 |
| OpenRouter | $0.06 | $0.33 |
| Together AI | — | — |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.13 |
| Output tokens | $0.40 |
Capabilities
VisionMultimodalJSON / Tool useStructured Outputs
About Gemma 4 26B A4B IT
Instruction-tuned MoE variant with 26B parameters (4B active). Optimized for instruction-following with advanced reasoning and multimodal capabilities.
Get Started
Model Specs
Released2026-03-31
Parameters26B
Context256k
Knowledge cutoff2025-01