API pricing per million tokens
gemma-4-26b-a4b-it Open weightsChecked 7h ago
- Input
- $0.042
- per 1M, Darkbloom
- Output
- $0.22
- per 1M tokens
- Cached input
- n/a
- no batch tier listed
- Context
- 262K
- 236K max output
Where to buy it (12)
- Darkbloomdefault region$0.042 / $0.22$0.086 blended
- DekaLLMbf16, bf16$0.06 / $0.33$0.128 blended
DeepInfrafp8, fp8$0.07 / $0.34$0.138 blended
- NextBitbf16, bf16$0.09 / $0.3cached $0.05
Cloudflare Workers AIdefault region$0.1 / $0.3$0.15 blended
CoreWeavebf16, bf16$0.1 / $0.3cached $0.05
- Makoradefault region$0.1 / $0.34cached $0.034
Novita AIbf16, bf16$0.13 / $0.4$0.198 blended
Parasailbf16, bf16$0.13 / $0.4cached $0.05
Venicebf16, bf16$0.13 / $0.4cached $0.05
SiliconFlowfp8, fp8$0.14 / $0.4cached $0.05
Google Vertex AIglobal$0.15 / $0.6$0.262 blended
Through a gateway
Your own numbers100M input and 20M output tokens a month: $8.60 direct.
Helicone$8.60+0%
Kong AI Gateway$8.60+0%
LiteLLM$8.60+0%
Vercel AI Gateway$8.60+0%
AWS Bedrock$8.60+0%
Azure AI Foundry$8.60+0%
Google Vertex AI$8.60+0%
Databricks Mosaic AI$8.60+0%
Hugging Face Inference$8.60+0%
Cloudflare AI Gateway$9.03+5%
Requesty$9.03+5%
Eden AI$9.07+5.5%
OpenRouter$9.07+5.5%
Snowflake Cortex AI$10.32+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
BigQuery MLn/a
Cloudflare Workers AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
Gemini 3.7 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MAug 13, 2026
Gemini 3.5 Flash LiteGoogle Gemini API · 1M$0.3 / $2.5in / out per 1M$0.3$2.5$0.031MJul 21, 2026
Gemini 3.6 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MJul 21, 2026
Muse Spark 1.3 ContributorMeta · 1M$0.1 / $0.2in / out per 1M$0.1$0.2$0.0021MSep 2, 2026
GLM 5.3 FlashZ.ai · via InferenceNet (fp4) · 1.31M$0.045 / $0.14in / out per 1M$0.045$0.14$0.011.31MAug 26, 2026
Muse Spark 1.2 ContributorMeta · 1M$0.1 / $0.2in / out per 1M$0.1$0.2$0.0021MAug 21, 2026
DeepSeek V4 Flash 0731DeepSeek · via StreamLake (fp8) · 1.31M$0.053 / $0.158in / out per 1M$0.053$0.158$0.00171.31MJul 31, 2026
About Gemma 4 26B A4B
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind.
Takes image, text, video in and returns text. First listed Sep 23, 2026. Blended price $0.086 per 1M tokens at 3 input to 1 output.
Questions
How much does Gemma 4 26B A4B cost?
$0.042 per million input tokens and $0.22 per million output tokens.
What is the context window of Gemma 4 26B A4B?
262K tokens, with up to 236K tokens of output.
Where is Gemma 4 26B A4B cheapest?
Of 12 routes tracked, Darkbloom is cheapest at $0.042 input and $0.22 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.