Providers and ModelsGoogle

Gemma-4-26B-A4B

Gemma-4-26B-A4B
Google · Text Generation
POST /v1/chat/completions

Gemma 4 26B A4B is a Google open multimodal model with 256K context, text, image, and video input, tools, and structured output.

At a glance

FieldValue
Model idgemma-4-26b-a4b
Input modalitiesText, Image, Video
Output modalitiesText
Context window256K
Weight precisionFP8 weights + FP8 KV
Max output tokens32,768
Featuresreasoning, vision, video, function_calling, structured_output, cache, multimodal, json_mode, logprobs
Native inferenceYes
NewYes
Supported endpointsPOST /v1/chat/completions, POST /v1/responses, POST /v1/messages, POST /v1/completions

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.05 (was $0.15)
Outputper 1M generated tokens$0.29 (was $0.50)
Implicit cache readper 1M cached input tokens$0.025 (was $0.15)

Example request

$curl https://api.empiriolabs.ai/v1/chat/completions \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "gemma-4-26b-a4b", "messages": [{"role":"user","content":"Hello"}]}'

Parameters

ParameterTypeRequiredDefaultDescription
temperaturenumberno1.0Sampling temperature. Lower values are more deterministic. · Range: 0 – 2
top_pnumberno0.95Nucleus sampling probability mass. · Range: 0 – 1
max_tokensintegerno4096Maximum output tokens. · Range: 1 – 32768
stopstringno—One or more stop strings.
reasoning_effortenumno"medium"Reasoning effort. none disables thinking; low, medium, high, and max set bounded thinking budgets. · Allowed: none, low, medium, high, max
enable_thinkingbooleannotrueEnable the model reasoning channel before final output.
thinking_budgetintegerno4096Maximum thinking tokens before the final answer. If max_tokens is lower, the service reserves room for the answer. · Range: 128 – 32768
top_kintegerno20Limit sampling to the top K candidate tokens when supported. · Range: 1 – 200
min_pnumberno0Minimum probability threshold for token sampling. · Range: 0 – 1
presence_penaltynumberno0Penalty for tokens that already appeared in the generated text. · Range: -2 – 2
frequency_penaltynumberno0Penalty based on how often a token has already appeared. · Range: -2 – 2
repetition_penaltynumberno1Penalty used by SGLang to reduce repeated text. · Range: 0.1 – 2
seedintegerno—Optional random seed for reproducible sampling. · Range: 0 – 2147483647
logprobsbooleannofalseReturn token log probabilities when supported.
top_logprobsintegerno—Return up to this many top token log probabilities. · Range: 0 – 20
logit_biasobjectno—Bias token IDs by adding positive or negative values before sampling.
toolsarrayno—OpenAI-compatible function tool definitions.
tool_choiceobjectno—OpenAI-compatible function tool selection.
response_formatobjectno—Structured JSON output instructions.
streambooleannofalseStream response deltas using server-sent events.

Notes

Supports text, image, and video input, streaming, function tools, structured JSON output, seed control, and thinking mode on by default. Use reasoning_effort or thinking_budget for bounded thinking, or enable_thinking=false for direct answers. Automatic cache reads are billed at the cached-input rate when reported by the model service. Explicit cache controls are not supported.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/gemma-4-26b-a4b.