impulse

Gemini 4 Neon

Frontier lab

Gemini 4 Neon is a fast, mid-priced model in the Gemini 4 family from Google, built for coding and agentic work.

API id gemini-4-neonReleased 18 Nov 2026 (yesterday)
Input / 1M
$3.00
at Google AI Studio
Output / 1M
$15.00
at Google AI Studio
Context window
1M
tokens
Max output
1M
tokens per reply
Hosts
2
3 listings
Released
yesterday
18 Nov 2026

Pricing

List prices at Google AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$3.00$15.00
Cached input
95% off input
$0.15
Batch
50% off
$1.50$7.50
Flex
50% off
$1.50$7.50
Priority
80% more
$5.40$27.00
Web search
$14.00 per 1,000 searches

What it costs a month

At Google AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,769
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,296
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$2,106
  • Overnight batch20,000 requests a day, 4K in / 0.4K out, batch$5,400
Use your own numbers

Where to run it

2 hosts serve Gemini 4 Neon. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
gemini-4-neon
$3.00 / $15.00
gemini-4-neon
$3.00 / $15.00
GitHub CopilotSubscription
gemini-4-neon
In the subscription

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
AudioImagesTextVideoPDFs
Produces
Text
Effort settings the source lists
xhigh
Features
Audio inputComputer useParallel tool callsPDF inputPrompt cachingURL contextVideo inputBuilt-in web search

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

No host sells it for less than Google AI Studio.

Smaller Google models

  • Gemini 4 Carbon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    33% less
  • Gemini 4 Argon
    Google · on Google AI Studio
    $2.00 / $10.00
    Has every key capability
    33% less
  • Gemini 4 Hydrogen
    Google · on Google AI Studio
    $1.50 / $7.50
    Has every key capability
    50% less

Other frontier labs

  • GPT-5.3 Codex
    OpenAI · on OpenAI
    $1.75 / $14.00
    Has every key capability
    20% less
  • Claude Sonnet 5.5
    Anthropic · on Anthropic
    $2.00 / $10.00
    Has every key capability
    33% less
  • Grok 4.7
    xAI · on xAI
    $2.00 / $6.00
    Has every key capability
    50% less
  • GPT-6.2 Sol
    OpenAI · on OpenAI
    $2.00 / $10.00
    Has every key capability
    33% less

Open-weight picks

  • Kimi K3.1 Pro
    Moonshot AI · on Databricks
    $2.00 / $10.00
    Has every key capability
    33% less
  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    64% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    71% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    91% less

Call it

Using Google AI Studio's API.

Python
from google import genai

client = genai.Client()  # reads GEMINI_API_KEY

response = client.models.generate_content(model="gemini-4-neon", contents="Hello")
print(response.text)

Quick answers

How much does Gemini 4 Neon cost?

On Google AI Studio, Gemini 4 Neon costs $3.00 per million input tokens and $15.00 per million output tokens. Cached input costs $0.15 per million tokens.

Which APIs offer Gemini 4 Neon?

Gemini 4 Neon runs on 2 APIs: Google AI Studio and Vertex AI.

What is Gemini 4 Neon's context window?

1M tokens, with up to 1M tokens in one reply.

Is Gemini 4 Neon being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Gemini 4 Neon?

Models that cost less and keep most of what it can do: Gemini 4 Carbon on Google AI Studio (33% less), GPT-5.3 Codex on OpenAI (20% less), Claude Sonnet 5.5 on Anthropic (33% less) and Kimi K3.1 Pro on Databricks (33% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Gemini 4 Neon released?

Google released it on 18 Nov 2026.

What is Gemini 4 Neon's API model id?

Use gemini-4-neon with Google AI Studio.

Sources

Raw catalog entry for gemini-4-neon on Google AI Studio
{
  "cache_read_input_token_cost": 1.5e-7,
  "cache_read_input_token_cost_batches": 7.5e-8,
  "cache_read_input_token_cost_flex": 7.5e-8,
  "cache_read_input_token_cost_priority": 2.7e-7,
  "google_maps_grounding_cost_per_query": 0.014,
  "input_cost_per_token": 0.000003,
  "input_cost_per_token_batches": 0.0000015,
  "input_cost_per_token_flex": 0.0000015,
  "input_cost_per_token_priority": 0.0000054,
  "litellm_provider": "gemini",
  "max_input_tokens": 1048576,
  "max_output_tokens": 1048576,
  "mode": "chat",
  "output_cost_per_reasoning_token": 0.000015,
  "output_cost_per_token": 0.000015,
  "output_cost_per_token_batches": 0.0000075,
  "output_cost_per_token_flex": 0.0000075,
  "output_cost_per_token_priority": 0.000027,
  "prompt_cache_min_tokens": 4096,
  "rpm": 2000,
  "search_context_cost_per_query": {
    "search_context_size_low": 0.014,
    "search_context_size_medium": 0.014,
    "search_context_size_high": 0.014
  },
  "search_free_requests": {
    "count": 5000,
    "period": "month",
    "shared_group": "gemini-3"
  },
  "source": "https://aistudio.google.com/docs/pricing#gemini-4-neon",
  "supported_endpoints": [
    "/v1/chat/completions",
    "/v1/completions"
  ],
  "supported_modalities": [
    "text",
    "image",
    "audio",
    "video"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_audio_input": true,
  "supports_audio_output": false,
  "supports_computer_use": true,
  "supports_continuation": true,
  "supports_function_calling": true,
  "supports_minimal_reasoning_effort": false,
  "supports_native_streaming": true,
  "supports_parallel_function_calling": true,
  "supports_pdf_input": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_system_messages": true,
  "supports_tool_choice": true,
  "supports_url_context": true,
  "supports_video_input": true,
  "supports_vision": true,
  "supports_web_search": true,
  "supports_xhigh_reasoning_effort": true,
  "tpm": 800000,
  "web_search_billing_unit": "per_query"
}