Gemini 4 Carbon (batch)
by Google · google/gemini-4-carbon:batch · #299 cheapest of 457 paid models
Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly
Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$1.00
per 1M tokens
Output
$5.00
per 1M tokens
Blended (3:1)
$2.00
3 input : 1 output
Cache read
$0.05
per 1M cached tokens
Cache write
$0.188
per 1M tokens
Cache & batch economics
Effective prices for Gemini 4 Carbon (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $2.00 | $0.107 | — |
| 50% | $1.64 | $0.0595 | −44% |
| 90% | $1.36 | $0.0215 | −80% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.002 | $2.00 |
| Document summary | 8,000 | 1,000 | $0.013 | $13.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.04 | $40.00 |
| Long-context analysis | 150,000 | 5,000 | $0.175 | $175.00 |
Performance
Intelligence Index
60
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,311 |
| Mobile apps | 1,292 |
| UI components | 1,345 |
| SVG | 1,400 |
| 3D | 1,424 |
| Game dev | 1,332 |
| Code categories | 1,341 |
| codetovideo | 1,287 |
| 1,305 | |
| spreadsheet | 1,220 |
Specs
Context window
1.05M
tokens
Max output
944K
tokens
Input modalities
audio, file, image, text, video
Tokenizer
Gemini