Gemma 4 26B A4B
google.gemma-4-26b-a4bPricing
List prices at Amazon Bedrock, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.13 | $0.40 | |
| Batch 50% off | $0.065 | $0.20 | 50% off |
| Flex 50% off | $0.065 | $0.20 | 50% off |
| Priority 75% more | $0.228 | $0.70 | 75% more |
What it costs a month
At Amazon Bedrock list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$69.00
- RAG over documents2,000 requests a day, 8K in / 0.6K out$76.80
- Coding agent1,000 requests a day, 40K in / 2K out$180
- Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$204
Where to run it
2 hosts serve Gemma 4 26B A4B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
EmpirioLabs AICloud gemma-4-26b-a4b | $0.05 / $0.29 −44% vs headline | gemma-4-26b-a4b | |
| $0.13 / $0.40 | google.gemma-4-26b-a4b |
Show 2 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| us-gov-west-1 · Mantle google.gemma-4-26b-a4b | $0.156 / $0.48 +20% vs headline | google.gemma-4-26b-a4b | |||||
| eu-central-1 · Mantle google.gemma-4-26b-a4b | $0.156 / $0.48 +20% vs headline | google.gemma-4-26b-a4b | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
- Open weights
- License: Gemma LicenseRuntimes: Ollama, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
- EmpirioLabs AI44% lessgemma-4-26b-a4b$0.05 / $0.29
Smaller Google models
No cheaper Google model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 9% less
- 9% less
- 19% less
- 28% less
Call it
Using Amazon Bedrock's API.
from litellm import completion
response = completion(
model="bedrock/google.gemma-4-26b-a4b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Gemma 4 26B A4B cost?
On Amazon Bedrock, Gemma 4 26B A4B costs $0.13 per million input tokens and $0.40 per million output tokens. The cheapest host is EmpirioLabs AI, at $0.05 per million input tokens and $0.29 per million output tokens.
Which APIs offer Gemma 4 26B A4B?
Gemma 4 26B A4B runs on 2 APIs: EmpirioLabs AI and Amazon Bedrock.
What is Gemma 4 26B A4B's context window?
256K tokens, with up to 256K tokens in one reply.
Is Gemma 4 26B A4B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Gemma 4 26B A4B?
Models that cost less and keep most of what it can do: Qwen3.8 Flash on AIHubMix (9% less). Gemma 4 26B A4B itself costs 44% less on EmpirioLabs AI. Savings are on a mix of 3 input tokens to 1 output token.
What is Gemma 4 26B A4B's API model id?
Use google.gemma-4-26b-a4b with Amazon Bedrock. Other hosts use their own ids: gemma-4-26b-a4b on EmpirioLabs AI.
Sources
Raw catalog entry for google.gemma-4-26b-a4b on Amazon Bedrock
{
"input_cost_per_token": 1.3e-7,
"input_cost_per_token_batches": 6.5e-8,
"input_cost_per_token_flex": 6.5e-8,
"input_cost_per_token_priority": 2.275e-7,
"output_cost_per_token": 4e-7,
"output_cost_per_token_flex": 2e-7,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"mode": "chat",
"output_cost_per_token_batches": 2e-7,
"output_cost_per_token_priority": 7e-7,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_parallel_function_calling": false,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
}