MODELS / GOOGLE

Gemini 4 Neon

Gemini 4 Neon is Google's fast multimodal reasoning model for coding, agentic workflows, and complex tasks, delivering high-quality results with low latency. It accepts text, images, video, and documents, with tool calling and structured outputs for building responsive…

TEXTREASONINGFILE-INPUTVISIONTOOL-USEWEB-SEARCHIMPLICIT-CACHINGVIDEO-INPUTSTRUCTURED-OUTPUT
1M
CONTEXT WINDOW
-
MAX OUTPUT TOKENS
$3
INPUT PRICE / 1M TOKENS
$15
OUTPUT PRICE / 1M TOKENS
QUICKSTART
PROTOCOL:
OPENAI COMPATIBLE
STREAMING:
SUPPORTED

Call it in one request.

OpenAI-compatible: change the base URL, and the setup is complete.

curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/google/gemini-4-neon",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
SPECIFICATIONS
CONTEXT:
1M
PROVIDER:
GOOGLE
TYPE:
TEXT

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything Gemini 4 Neon supports, in one table.

MODEL ID
blackboxai/google/gemini-4-neon
DEVELOPED BY
Google
MODEL TYPE
Text
RELEASED
Nov 18, 2026
CONTEXT WINDOW
1M
MAX OUTPUT TOKENS
-
INPUT MODALITIES
text, image, pdf, video
OUTPUT MODALITIES
text
INPUT PRICE
$3 / 1M tokens
OUTPUT PRICE
$15 / 1M tokens
CACHE READ
$0.15 / 1M tokens
REASONING
Supported
DATA RETENTION
Standard retention
DEDICATED DEPLOYMENT
Not available (closed-weight model)
SUPPORTED PARAMETERS
max_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs