Gemini 4 Argon vs Gemini 4 Carbon
Which one, when
These two Google models share one rate card and one set of limits: $2 input, $10 output and $0.1 cache reads per million tokens, a 1048576-token context, 65536 max output, and text, image, audio and video input. The split is how hard they think: Google says gemini-4-carbon spends more thinking tokens per turn than gemini-4-argon to explore and verify its work, and thinking is billed as output, so the same task costs more and takes longer. Keep gemini-4-argon as the default and send the hardest coding, finance, legal or science work to gemini-4-carbon.
Benchmarks
12 measured on both.
Vendor-published: Google
Pricing
| Gemini 4 Argon | Gemini 4 Carbon | Δ | |
|---|---|---|---|
| Input / 1M tokens | $2 | $2 | = |
| Output / 1M tokens | $10 | $10 | = |
| Cache read / 1M tokens | $0.1 | $0.1 | = |
Rates from the live catalogue at build time; each model page carries the current rate card.
Where they sit · input price per 1M tokens across all 86 chat models on this billing unit (log scale)
Capabilities
| Gemini 4 Argon | Gemini 4 Carbon | |
|---|---|---|
| Tool calling | yes | yes |
| Thinking control | yes (vendor dial not published) | always on |
| Structured output | yes | yes |
| Prompt caching | implicit (automatic) | implicit (automatic) |
| Cache lifetime | not published | not published |
| Minimum cached prefix | 4,096 tokens | 4,096 tokens |
Specs
| Gemini 4 Argon | Gemini 4 Carbon | |
|---|---|---|
| Input modalities | text image audio video | text image audio video |
| Output modalities | text | text |
| Released | 2026-10-13 | 2026-11-10 |
| Knowledge cutoff | 2026-03 | 2026-03 |
| Context window | 1,048,576 | 1,048,576 |
| Max output | 65,536 | 65,536 |
| Thinking parameter | - | thinking_level |
| Accepted values | - | thinking_level
"minimal" and thinking_budget return 400 |
| Default | - | medium |
Specs are transcribed from each vendor’s documentation; a row a vendor does not publish is left out rather than inferred. Full sources: Gemini 4 Argon · Gemini 4 Carbon
One prompt, both models, measured through the gateway
Gemini 4 Argon passed · 3 sentences
Enabling the reasoning feature forces the AI to generate an extensive, hidden "chain of thought" to solve complex problems before delivering the final answer. Because LLM providers bill us per token generated, we are now paying for thousands of these invisible "thinking" words on top of the standard visible output. While this doubles our raw usage costs per query, it represents an investment in significantly higher accuracy and drastically reduced error rates for our most critical tasks.
out 91 tok latency 4.7 s
Gemini 4 Carbon passed · 3 sentences
Enabling reasoning instructs the AI to generate a lengthy, behind-the-scenes "thought process" to verify its logic before delivering a final answer. Because our vendor bills us based on total output volume, we are charged for all of that invisible scratchpad work in addition to the visible response, effectively doubling the compute consumed per query. Moving forward, we can control this cost by restricting reasoning strictly to complex, high-stakes workflows where higher accuracy justifies the premium, while routing routine tasks back to standard, lower-cost models.
out 908 tok (+799 thinking) latency 18.0 s
Instruction following (exactly three sentences, so countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.
Gemini 4 Argon passed · 8/8 cases
```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` The bug occurs because the original function counts the number of matching adjacent *pairs* rather than the actual number of *elements* in a run, causing all non-empty results to be off by one. Because a single element constitutes a valid run of length 1, initializing and resetting `cur` and `best` to `0` instead of `1` means the first element of any sequence is never counted; this causes single-element lists (where the loop doesn't run) to wrongly return `0` and makes it seem like runs at the end are missed because a pair of matching elements only increments `cur` to `1` instead of `2`. […]
out 286 tok latency 7.5 s
Gemini 4 Carbon passed · 8/8 cases
```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` The original function counts the number of matching adjacent *transitions* rather than the number of *elements* in a run because `best` and `cur` are initialized and reset to `0` instead of `1`. Because a single item on its own already forms a run of length `1`, starting at `0` causes every non-empty result to be short by one: single-element lists (where the loop never executes) and lists with no duplicates return `0` instead of `1`, and any run of $k$ equal items—including one ending at the last index—only increments `cur` $k - 1$ times, making it appear as though the final element of the run was missed. […]
out 1411 tok (+1131 thinking) latency 32.7 s
Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.
Gemini 4 Argon passed · 5/5 fields, guidance "withheld pending the Q4 close"
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": null, "growth_pct": "eleven and change", "guidance": "withheld pending the Q4 close" } ```
out 68 tok latency 5.8 s
Gemini 4 Carbon passed · 5/5 fields, guidance null
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": null, "growth_pct": null, "guidance": null } ```
out 3338 tok (+3281 thinking) latency 61.6 s
Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.
Gemini 4 Argon passed · 120 words, 0 banned, 1 question
Are you paying twice for the exact same AI responses? Today, we are introducing Cross-Provider Prompt Caching for our API gateway, a new feature designed to reduce your artificial intelligence infrastructure costs and latency. When your applications send identical prompts to different large language models, our gateway now intercepts the request and serves a verified, cached response in milliseconds. It works across OpenAI, Anthropic, and open-source models simultaneously. If your primary provider experiences an outage, your fallback model still benefits from the shared cache Layer, preventing expensive redundant computations. Engineering teams can configure custom time-to-live settings, set similarity thresholds, and monitor cache hit rates directly from the dashboard. Activate Cross-Provider Prompt Caching in your gateway settings today and start saving.
out 156 tok latency 6.3 s
Gemini 4 Carbon passed · 120 words, 0 banned, 1 question
Are your engineering teams paying multiple AI vendors to generate identical responses? Today, we are introducing Universal Prompt Caching for our flagship API Gateway. When applications route traffic across providers like OpenAI, Anthropic, and Mistral, duplicate queries drain budgets and degrade user experiences. Our new unified caching layer intercepts incoming prompts directly at the network edge. If an identical request was previously fulfilled by any connected model, the gateway delivers the stored response in milliseconds, completely bypassing external API calls. This practical upgrade cuts monthly token expenses substantially while accelerating overall application speed. Best of all, deployment requires zero complex code changes. Simply activate this capability inside your gateway configuration dashboard today to start reducing latency and infrastructure costs immediately.
out 2620 tok (+2480 thinking) latency 31.1 s
Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.
Switch between them with one line
Both ids are in every tab below; the highlighted pair of lines is the only edit. Same endpoint, same key, same request shape.
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="gemini-4-argon",
# model="gemini-4-carbon", # uncomment this line, comment the one above
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "gemini-4-argon",
// model: "gemini-4-carbon", // uncomment this line, comment the one above
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-argon",
# "model": "gemini-4-carbon", # uncomment this line, comment the one above
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "gemini-4-argon",
// Model: "gemini-4-carbon", // uncomment this line, comment the one above
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("gemini-4-argon")
// .model("gemini-4-carbon") // uncomment this line, comment the one above
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));FAQ
Which is cheaper, Gemini 4 Argon or Gemini 4 Carbon?
Both list $2 for “Input / 1M tokens”. Other rates and the number of units used can still change the total cost.
Can I A/B test Gemini 4 Argon against Gemini 4 Carbon without two integrations?
Yes. Both are served through the same OpenAI-compatible endpoint with one API key. Switching is a one-line change to the model id, so you can route a fraction of traffic to each and compare bills directly.
Do Gemini 4 Argon and Gemini 4 Carbon support prompt caching?
Yes. Both bill cache reads below their input rate, so warm-prefix workloads cost less than the list rates suggest. The exact cache-read rows are in the pricing table above.