Skip to main content

Gemini 4 Neon

Google Gemini 4 frontier model for complex software engineering, knowledge work and science workflows with fast end-to-end task completion. Shared 1048576-token input, thinking and output context; 65536-token synchronous output limit.

Input / output price
$3.00 / $15.00 per 1M
Context
1M tokens
Released
Nov 18, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "google_gemini_ai/gemini-4-neon".

Read docs

Providers

3 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/gemini-4-neon
$3.00/M$15.00/M
Google Gemini AIgoogle_gemini_ai/gemini-4-neon
$3.00/M$15.00/M
OpenRouteropenrouter/google/gemini-4-neon
$3.00/M$15.00/M

Is a provider down? OpenRouter status

Pricing

Averaged across 3 providers, in USD per 1M tokens after gateway discounts.

Average input
$3.00 per 1M
Average output
$15.00 per 1M
Average cache read
$0.15 per 1M
Average cache write
$0.08 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$3.00/MConcentrate, Google Gemini AI, and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

117tokens/sacross providers

Faster than 81% of the other 596 models on the gateway

Time to first token

Lower is better

9.8sacross providers

Faster than 9% of the other 153 models on the gateway

Response latency

Lower is better

19sacross providers

Faster than 10% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 22 published scores from 6 sources, each linked to where it was published.

176 ranked models. The shaded band is this model's 95% interval, 70.8 to 84.6. Claude Fable 5.2 and Gemini 4 Carbon fall inside it, so the gap is within the margin of error.
Gemini 4 Neon by category: Coding 78.0 (estimated), Agents 84.5, Reasoning 87.8, Knowledge & language 75.3, Human preference 60.4
  1. 2Gemini 4 Neon79.2
  2. 1Claude Fable 5.280.8
  3. 3Gemini 4 Carbon76.1

Published scores

BenchmarkScore
CursorBench 4.1Google65.4%
Terminal-bench 4.1Google65.2%
FrontierCode 2.0Google46.2%

Compare Gemini 4 Neon: Gemini 4 Neon vs Gemini 4 Carbon, Gemini 4 Neon vs Gemini 4 Hydrogen, Gemini 4 Neon vs Gemini 4 Argon, Gemini 4 Neon vs Gemini 3.8 Flash, Gemini 4 Neon vs Gemini 3.7 Flash, Gemini 4 Neon vs Gemini 3.6 Flash

Apps

Use Gemini 4 Neon in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Gemini 4 Neon FAQ

Short answers, built from the data on this page.

Gemini 4 Neon is a model from Google Gemini AI, released on Nov 18, 2026. Google Gemini 4 frontier model for complex software engineering, knowledge work and science workflows with fast end-to-end task completion. Shared 1048576-token input, thinking and output context; 65536-token synchronous output limit.

On the Respan gateway, Gemini 4 Neon costs $3.00 per 1M input tokens and $15.00 per 1M output tokens on every provider, after gateway discounts.

Gemini 4 Neon is available through 3 providers: Concentrate, Google Gemini AI, and OpenRouter.

Gemini 4 Neon accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "google_gemini_ai/gemini-4-neon". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Gemini 4 Neon scores 79.2 out of 100 on the Respan Index v1.1, ranking #2 of 176 models. By category: Coding 78.0 (estimated), Agents 84.5, Reasoning 87.8, Knowledge & language 75.3, and Human preference 60.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Gemini 4 Neon has 22 published benchmark scores, including CursorBench 4.1 65.4%, APEX-Agents 82.9%, and GPQA Diamond 96.3%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.