Checked against the OpenRouter public models feed. Prices are copied, not estimated.

The Best Model ForWhich AI model to use, from ten labs.

Gemini Embedding 2 vs Gemini 4 Neon

Short answer

Gemini Embedding 2 ($0.20 in / $0 out); Gemini 4 Neon ($3.00 in / $15.00 out). Lowest listed input price: Gemini Embedding 2. Longest listed context: Gemini 4 Neon at 1,048,576 tokens. A lower price is not a quality ranking.

Side-by-side facts. The third-party index is copied when the feed has one. Unknown means it did not.
FactGemini Embedding 2Gemini 4 Neon
LabGoogle (Gemini)Google (Gemini)
KindEmbeddingsChat
Listed20 May 202618 Nov 2026
Context8,1921,048,576
Input / million$0.20$3.00
Output / million$0$15.00
Batch input$0.10$1.50
Batch output$0$7.50
Inputsaudio, file, image, text, videoaudio, file, image, text, video
Outputsembeddingstext
ToolsNot listedYes
Open weightsNo public weights id listedNo public weights id listed
Knowledge cutoffUnknownUnknown
Third-party indexUnknown61.4
GuideNew, not yet reviewedReviewed

Input and output prices are USD per million tokens, from pricing.prompt and pricing.completion. The index is not our benchmark.

Gemini Embedding 2

New, not yet reviewed. No guide note yet.

Gemini Embedding 2 is listed at $0.20 input and $0 output per million tokens, with a 8,192-token context window.

Gemini 4 Neon

Gemini 4 Neon is the newest Gemini 4 model on the feed. OpenRouter describes it as a fast, mid-priced model for coding and agentic work. The practical reason to pick it is the input list: text, images, audio, video, and files, in one model.

Gemini 4 Neon is listed at $3.00 input and $15.00 output per million tokens, with a 1,048,576-token context window.

Choose models

Popular comparisons