Back to model catalog

Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

Gemini 4 NeonChat with this model
AttributeGemini 4 Neongemini/gemini-4-neon
Specs
Context window1M
Max output66K
Input modalitiesTextImageAudioVideo
Output modalitiesText
Capabilities
StreamingSupported
Tool callingSupported
Structured output (JSON)Supported
Image inputSupported
Thinking modeSupported
Price / 1M tokens
Input$ 3.00
Output$ 15.00
Cache read$ 0.15
Cache write$ 3.00
What it is good at
Best for
  • Repository-level agentic coding
  • Analytical knowledge work
  • Science and quantitative work
  • Secure coding and vulnerability patching
Published benchmarks
Agents' Last Exam v1.1score
  • 75.8%effort xhigh · Antigravity-CLI (agy) 1.4.8(setup not fully disclosed)
SWE-sweepscore
  • 39%effort xhigh · Antigravity-CLI (agy) 1.5.9(setup not fully disclosed)
GraphWalks BFS 256K to 1Mf1
  • 95.2%effort xhigh(setup not fully disclosed)
Chartography (no tools)score
  • 73.5%effort xhigh(setup not fully disclosed)
Terminal-Bench-Science 0.1accuracy
  • 70.5%effort xhigh · mini-swe-agent (vision) · 5 runs(setup not fully disclosed)
LVBench (static)accuracy
  • 89%effort xhigh(setup not fully disclosed)