Gemini 4 Carbon vs GPT-6.1 Terra

vs

Which one, when

For prompts up to 272000 input tokens, gemini-4-carbon accepts audio and video and supports search grounding. Choose gpt-6.1-terra for lower input and output rates, a larger output ceiling and the option to turn reasoning off.

Benchmarks

GPT-6.1 Terra: 9 published, but no benchmark it shares with enough other models to compare.

Above averageNo peer higherGemini 4 Carbon12 / 1210 / 12
Gemini 4 Carbon GPT-6.1 Terra other models measured peer average ★ no peer scored higher
FrontierSWE 2 Proximal leaderboard, Carbon report
61.2%
N/A
OSWorld 2.1 82 offline tasks, partial score. Gemini: best of 3. Peers: published evaluations
81.5%
N/A
AutomationBench (Zapier) Zapier private set
no peer scored higher 53.9%
N/A
GraphWalks BFS (F1) 256k to 1M tokens, 200 tasks, Google evaluation
no peer scored higher 96.2%
N/A
Blueprint-Bench 2 Similarity score, Andon Labs leaderboard
no peer scored higher 58.6%
N/A
Vending-Bench 2 (USD) Andon Labs leaderboard, Carbon report · 5422-16484
no peer scored higher 16484
N/A
Chartography No tools, Carbon report
no peer scored higher 72.5%
N/A

Vendor-published: Google Google

Pricing

Gemini 4 Carbon GPT-6.1 Terra Δ
Input / 1M tokens $2 $1 2×
Output / 1M tokens $10 $5 2×
Cache read / 1M tokens $0.1 $0.05 2×
Cache write - 1.25x (30m) / 2.5x (12h) -

Rates from the live catalogue at build time; each model page carries the current rate card. The main table shows base rates. Prompt length can change the rate for the entire request. See each model’s full rate card.

GPT-6.1 Terra · Rates by prompt length

The whole request uses the rate for its input-length tier. Prices are USD per million tokens.

Input tokensInputOutput
0 - 272,000 $1 $5
272,001 - 1,050,000 $2 $7.5

Where they sit · input price per 1M tokens across all 86 chat models on this billing unit (log scale)

Capabilities

Gemini 4 Carbon GPT-6.1 Terra
Tool calling yes yes
Thinking control always on configurable
Structured output yes yes
Prompt caching implicit (automatic) implicit + explicit
Cache lifetime not published at least 30m by default, 12h option on the Responses API
Minimum cached prefix 4,096 tokens 1,024 tokens

Specs

Gemini 4 Carbon GPT-6.1 Terra
Input modalities text image audio video text image
Output modalities text text
Released 2026-11-10 2026-10-26
Knowledge cutoff 2026-03 2026-06
Context window 1,048,576 1,050,000
Max output 65,536 128,000
Thinking parameter thinking_level reasoning.effort
Accepted values
thinking_level
  • low
  • medium
  • high

"minimal" and thinking_budget return 400

reasoning.effort
  • none
  • low
  • medium
  • high
  • xhigh
  • max
Default medium 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 Carbon · GPT-6.1 Terra

One prompt, both models, measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

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

GPT-6.1 Terra passed · 3 sentences

Enabling reasoning caused the model to process additional internal tokens before producing each answer, even though those tokens are not visible to users. Those tokens are generally billable, increasing the cost per request and potentially doubling the bill even if usage stayed the same. To confirm the cause, compare request counts, model pricing, and token usage—including reasoning tokens—before and after the change.

out 196 tok (+115 thinking) latency 4.6 s

Instruction following (exactly three sentences, so countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

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

GPT-6.1 Terra passed · 8/8 cases

```python def longest_run(xs): if len(xs) == 0: return 0 best = cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 else: cur = 1 best = max(best, cur) return best ``` The original code counted matching *adjacent pairs* rather than items, so every nonempty run was undercounted by one, including a single-element input. It did update `best` for matches at the last index, but still undercounted those runs. The fix starts each run at length one and updates `best` as the run grows.

out 331 tok (+172 thinking) latency 6.3 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

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

GPT-6.1 Terra passed · 5/5 fields, guidance "Withheld pending the Q4 close"

{ "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": null, "growth_pct": null, "guidance": "Withheld pending the Q4 close" }

out 317 tok (+261 thinking) latency 6.9 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

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

GPT-6.1 Terra passed · 120 words, 0 banned, 1 question

Meet Prompt Cache, a new API gateway feature that stores reusable prompts across providers, helping teams reduce latency and control costs without changing how they build. When a request matches a cached prompt, the gateway retrieves the stored result instead of sending the same work again. Need to route traffic between models or vendors? Prompt Cache works across supported providers, giving your applications a consistent caching layer as your stack evolves. Set expiration policies, monitor cache performance, and choose which requests qualify through familiar gateway controls. Your team can spend less time repeating requests and more time improving the experiences customers rely on. Start using Prompt Cache today and make every request work harder for your application and your budget.

out 579 tok (+440 thinking) latency 9.1 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-carbon",
    # model="gpt-6.1-terra",  # uncomment this line, comment the one above
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

Get your API key →

FAQ

Which is cheaper, Gemini 4 Carbon or GPT-6.1 Terra?

The main table shows base rates. Prompt length can change the rate for the entire request. See each model’s full rate card.

Can I A/B test Gemini 4 Carbon against GPT-6.1 Terra 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 Carbon and GPT-6.1 Terra 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.

Related comparisons

From our measured studies