aiapicostcalcUnit economicsPricesBrandsCompareBenchmarksSkills & PluginsFind my modelGuidesChanges

GPT-6.1 Terra API pricing and cost calculator

Short answer: GPT-6.1 Terra costs $1 per 1M input tokens and $5 per 1M output tokens on OpenAI's standard tier (checked 2026-11-15), with cached input at $0.05. A 2,000-input / 500-output chat call costs $0.0045, so 1,000 calls cost $4.50. Output is 5.0× the input price, which is why long answers dominate a bill.

Last verified 2026-11-18 · Sources: OpenAI pricing page, checked 2026-11-15 · Report an error

By Shangyi Duan · Reviewed against OpenAI pricing page

Source URL: https://platform.openai.com/docs/pricing · Verified: · Rate row: src/prices.json

1
2
Presets

Preset token counts are starting assumptions; replace them with your logged averages.

Cost per call$0.0045
Per 1,000 calls$4.50

$1 in · $5 out per 1M

Nearest-priced models, this workload

Showing the 9 models closest in price; change any input to rank every model.

ModelPer callPer 1K calls
Gemini 3.6 Flash$0.00337$3.38
GPT-5.4 mini$0.00375$3.75
Grok 4.3$0.00375$3.75
o4-mini (shut down 2026-10-23)$0.0044$4.40
GPT-6.1 Terra$0.0045$4.50
Claude Haiku 4.5$0.0045$4.50
DeepSeek V4 Pro$0.00462$4.62
Grok 4.7$0.0070$7.00
Gemini 2.5 Pro$0.0075$7.50

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 IDgpt-6.1-terra
Context window1.05M tokens (max input 922K)
Max output128K tokens
Knowledge cutoffJun 01, 2026

Every price tier

TierPrice per 1M tokens
Standard input$1
Cached input (cache read)$0.05
Cache write$1.25 (30-min retention)
Output (incl. reasoning tokens)$5
Batch API input / output$0.5 / $2.5 (50% off)
Long-context tier (prompt over 272K)$2 in · $0.1 cached · $7.5 out — applies to the whole request

Source: OpenAI pricing and the GPT-6.1 Terra model page, checked 2026-11-15.

≤272K input; long context $2/$7.5

Worked examples

WorkloadPer callPer 1K callsPer 1K, Batch
Chat reply · 1K in / 500 out$0.0035$3.50$1.75
RAG answer · 10K in / 1K out$0.0150$15.00$7.50
RAG with 80% cached prefix$0.0074$7.40$3.70
Long document · 100K in / 2K out$0.1100$110$55.00
Whole-codebase prompt · 400K in / 4K out$0.8300$830$415

Rows above 272K input use the official long-context rate for the entire request, which is why the last rows jump more than the token count alone suggests.

Does prompt caching pay off?

Writing a 20K-token prefix to the cache costs $0.0050 more than sending it normally; every later hit saves $0.0190. The cache pays for itself after 1 reuse within the retention window. Cached reads cost 5% of the normal input price on this model.

When to pick it

Where it sits in the OpenAI lineup

Among the 21 OpenAI models we track, GPT-6.1 Terra ranks #7 from cheapest at a 10K-in / 1K-out workload ($15.00 per 1,000 calls). The next cheaper option is GPT-5.4 mini at $12.00 (0.8× the cost, 400K context). Stepping up to o4-mini costs $15.40 (1×). The cheapest in the lineup, GPT-6 Luna, is 10× cheaper.

Performance benchmarks

Measured scores copied from the dated leaderboard pages linked in the table: SWE-bench Verified, LiveCodeBench, AIME, Humanity's Last Exam, MMMU-Pro, Output speed. A benchmark this model does not publish is left out rather than estimated, and scores from different benchmarks are never mixed into one number.

On SWE-bench Verified, GPT-6.1 Terra ranks #6 of the 16 OpenAI models we track that publish this benchmark.

BenchmarkScoreRank in the OpenAI lineupCost per quality pointSource, checked
SWE-bench Verified65.6%#6 of 16$0.0305 / pointtrustthebench.com ·
LiveCodeBench69%#6 of 16$0.0290 / pointtrustthebench.com ·
AIME78.2%#7 of 16$0.0256 / pointtrustthebench.com ·
Humanity's Last Exam46.2%#5 of 8$0.0433 / pointartificialanalysis.ai ·
MMMU-Pro84.7%#3 of 8$0.0236 / pointartificialanalysis.ai ·
Output speed109 tok/s#5 of 10–benchleader.com ·

MMMU-Pro/HLE from Artificial Analysis entry 'GPT-6.1 Terra (Max)'.

Cost per quality point = blended standard price (3 input tokens : 1 output token per 1 million) ÷ the benchmark score: what one point of measured quality costs at list price, not a task cost. Ranks compare only models from the same provider on the same benchmark. All benchmarks ranked by price and performance · Best LLM for coding · Compare two models

Related

Ready to build? Create an API key in the official OpenAI console.

Questions

How much does GPT-6.1 Terra cost per 1M tokens?

$1 for input, $5 for output and $0.05 for cached input on the standard tier. Source: the official OpenAI pricing page, checked 2026-11-15.

How much do 1,000 GPT-6.1 Terra API calls cost?

At 2,000 input and 500 output tokens per call, one call costs $0.0045 and 1,000 calls cost $4.50 at list price. Batch and caching are not included; both lower the total.

Is GPT-6.1 Terra expensive compared with other models?

On a 2,000-input / 500-output chat call it ranks #24 of 55 verified models by cost. The cheapest is Ministral 3 3B at $0.00025 per call.

Does GPT-6.1 Terra publish a cached-input rate or a batch discount?

Its official pricing page lists a cached-input rate of $0.05 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 GPT-6.1 Terra

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.

More paths from this model