Gemini 4 Carbon API pricing and cost calculator
Short answer: Gemini 4 Carbon costs $2 per 1M input tokens and $10 per 1M output tokens on Google's standard tier (checked 2026-11-15), with cached input at $0.1. A 2,000-input / 500-output chat call costs $0.0090, so 1,000 calls cost $9.00. Output is 5.0× the input price, which is why long answers dominate a bill.
Nearest-priced models, this workload
Showing the 9 models closest in price; change any input to rank every model.
| Model | Per call | Per 1K calls |
|---|---|---|
| GPT-6.1 Sol | $0.0090 | $9.00 |
| GPT-6 Sol | $0.0090 | $9.00 |
| Claude Sonnet 5.5 | $0.0090 | $9.00 |
| Claude Sonnet 5 | $0.0090 | $9.00 |
| Gemini 4 Carbon | $0.0090 | $9.00 |
| Gemini 4 Argon | $0.0090 | $9.00 |
| GPT-5.6 Terra | $0.0100 | $10.00 |
| Gemini 3.1 Pro Preview | $0.0100 | $10.00 |
| GPT-5.4 | $0.0125 | $12.50 |
o4-mini is shut down; its last published list rate is kept for comparing old invoices, not as a model you can call today — the model page names its replacement.
At a glance
| API model ID | gemini-4-carbon |
| Context window | 1,048,576 tokens |
| Max output | 65,536 tokens; up to 1,048,576 with long decode |
| Inputs | Text, Image, Video, Audio, and PDF |
| Gemini API free tier | No — paid tier only |
Every price tier
| Tier | Price per 1M tokens |
|---|---|
| Standard input | $2 |
| Cached input (cache read) | $0.1 — implicit caching only |
| Output (incl. reasoning tokens) | $10 |
| Batch API input / output | $1 / $5 (50% off) |
Source: Google pricing and the Gemini 4 Carbon model page, checked 2026-11-15.
Rises to $4/$20 on 2026-12-01
Worked examples
| Workload | Per call | Per 1K calls | Per 1K, Batch |
|---|---|---|---|
| Chat reply · 1K in / 500 out | $0.0070 | $7.00 | $3.50 |
| RAG answer · 10K in / 1K out | $0.0300 | $30.00 | $15.00 |
| RAG with 80% cached prefix | $0.0148 | $14.80 | $7.40 |
| Long document · 100K in / 2K out | $0.2200 | $220 | $110 |
| Whole-codebase prompt · 400K in / 4K out | $0.8400 | $840 | $420 |
Does prompt caching pay off?
There is no separate cache-write charge listed for this model, so every cache hit on a 20K-token prefix saves $0.0380 versus the normal input price ($38.00 per 1,000 calls). Cached reads cost 5% of the normal input price on this model.
When to pick it
- Google describes it as: “Gemini 4 Carbon (gemini-4-carbon) is our most capable reasoning model, built for complex software engineering, mathematical and scientific problem solving, high factual accuracy, autonomous multi-step agents, and long decode up to 1M tokens.”
- Cheapest current model from another provider with at least a 1,048,576 context window: GPT-6 Luna at $1.50 per 1,000 RAG calls.
- Output costs 5× input here, so long answers and reasoning dominate the bill — cap max output tokens.
- Background jobs (classification, nightly summaries, evals) can go through the Batch API for 50% off.
Where it sits in the Google lineup
Among the 10 Google models we track, Gemini 4 Carbon ranks #8 from cheapest at a 10K-in / 1K-out workload ($30.00 per 1,000 calls). The next cheaper option is Gemini 2.5 Pro at $22.50 (0.75× the cost, 1,048,576 context). Stepping up to Gemini 4 Argon costs $30.00 (1×). The cheapest in the lineup, Gemini 2.5 Flash-Lite, is 21.4× cheaper.
Related
- All Google models and prices
- Benchmarks: price vs performance
- Best LLM for coding in 2026
- Find a model for your use case
- Gemini cost calculator
- Prompt caching guide
- Batch API guide
- How to price an AI SaaS from measured usage
- Reasoning tokens: why thinking models cost more
Ready to build? Create an API key in the official Google console.
Questions
How much does Gemini 4 Carbon cost per 1M tokens?
$2 for input, $10 for output and $0.1 for cached input on the standard tier. Source: the official Google pricing page, checked 2026-11-15.
How much do 1,000 Gemini 4 Carbon API calls cost?
At 2,000 input and 500 output tokens per call, one call costs $0.0090 and 1,000 calls cost $9.00 at list price. Batch and caching are not included; both lower the total.
Is Gemini 4 Carbon expensive compared with other models?
On a 2,000-input / 500-output chat call it ranks #34 of 55 verified models by cost. The cheapest is Ministral 3 3B at $0.00025 per call.
Does Gemini 4 Carbon publish a cached-input rate or a batch discount?
Its official pricing page lists a cached-input rate of $0.1 per 1M tokens and a Batch API multiplier of 0.5, a 50% discount. Caching pays off when a system prompt or document prefix repeats across calls; batch applies only to asynchronous jobs nobody is waiting on. Both are priced on top of the standard rates above, never instead of them.
Next step → Estimate cost per user with Gemini 4 Carbon
Price data last checked 2026-11-18 against official sources · how we verify
Price-change alerts
One short email when a provider changes a price or a promo ends. No spam, unsubscribe any time.
Tools, skills & plugins that use this model
Matched to this model's profile: cheaper models are paired with workflow and agent tools, million-token-context models with frameworks and open-source projects, and reasoning models with coding agents. Each entry links to its token-cost page or official site, and the per-task price is calculated on this model from the tool data rather than copied from another model.
- LangChain agent — Open-source agent framework that rebuilds prompt context on every step. ($0.0568 per task, Estimated)
- Dify — Open-source LLM app platform with per-node workflow token logs. ($0.0534 per task, Estimated)
- Aider — Open-source pair-programming CLI with published benchmark token counts. ($0.0437 per task, Measured)
- OpenHands — Open-source AI coding agent platform that runs locally with any model. (Resource)