Gemma 4 26B A4B IT
VertexOpen weights
Gemma 4 26B A4B IT by Vertex costs $0.15 per 1M input tokens and $0.60 per 1M output tokens, with a 262K-token context window.
Pricing
Input (per 1M tokens)
$0.15
Output (per 1M tokens)
$0.60
Cached input (per 1M)
$0.02
Specifications
- Provider
- Vertex
- Context window
- 262K tokens
- Parameters
- —
- Released
- Apr 2026
- Open weights
- Yes
- Frontier model
- No
Benchmarks
- GPQA Diamond
- 73.2
Speed & latency
Time to first token
0.93s
Output speed
64 tok/s
Fastest host: novita (via vercel-ai-gateway).
Compare Gemma 4 26B A4B IT with…
Gemma 4 26B A4B IT vs Gemini Flash Latest$2.50/1MGemma 4 26B A4B IT vs Claude Haiku 3.5$4.00/1MGemma 4 26B A4B IT vs Gemini Flash-Lite Latest$0.40/1MGemma 4 26B A4B IT vs Gemini 3.1 Flash Lite Preview$1.50/1MGemma 4 26B A4B IT vs Claude Opus 4.8$25.00/1MGemma 4 26B A4B IT vs Gemini 2.5 Flash TTS$10.00/1M
FAQ
How much does Gemma 4 26B A4B IT cost?
Gemma 4 26B A4B IT is priced at $0.15 per 1M input tokens and $0.60 per 1M output tokens. Output tokens cost more than input.
What is Gemma 4 26B A4B IT's context window?
Gemma 4 26B A4B IT supports a context window of 262K tokens — the maximum prompt plus response length it can handle in a single request.
Is Gemma 4 26B A4B IT open weight?
Yes — Gemma 4 26B A4B IT has openly available weights.
Data as of 2026-10-14. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.