Pricing compared · checked 22 Oct – 2 Nov 2026

GPT-6.1 Terra vs Claude Sonnet 5.5

Price your workload on both + Add a model to this comparison

GPT-6.1 Terra costs $1.00 / $5.00 and Claude Sonnet 5.5 costs $2.00 / $10.00 per million input / output tokens. At a typical 3:1 mix, GPT-6.1 Terra is 2.0× cheaper than Claude Sonnet 5.5.

GPT-6.1 Terra

OpenAI · Source

2.0× cheaper

Input

$1.00

per 1M

Output

$5.00

per 1M

Cached

$0.050

1.05M context

Claude Sonnet 5.5

Anthropic · Source

Input

$2.00

per 1M

Output

$10.00

per 1M

Cached

$0.10

1M context

Side by side

✓ marks the cheaper price, larger context window, bigger discount or higher score.

GPT-6.1 Terra and Claude Sonnet 5.5: prices and limits
Detail	GPT-6.1 Terra	Claude Sonnet 5.5
Price per 1M tokens
Input	$1.00Lowest	$2.00
Output	$5.00Lowest	$10.00
Blended (3 in : 1 out)	$2.00Lowest	$4.00
Cached input	$0.050Lowest	$0.10
Batch or off-peak discount	50% (batch)	50% (batch)
Long prompts	Over 272K: 2× in, 1.5× out	Same rate at any length
Limits and model
Context window	1.05MLargest	1M
Capability score Epoch AI index	168	167
Released	26 Oct 2026	28 Sep 2026
Open weights	No	No
Status	Current	Current
Checked
Price checked	2 Nov 2026 OpenAI pricing	22 Oct 2026 Anthropic pricing

Monthly cost on three workloads

List prices, no batch discount. The cached share applies where a model has a cache rate.

Workload	GPT-6.1 Terra	Claude Sonnet 5.5	Difference
Customer chat assistant50,000 conversations a month, about 2,000 tokens in and 400 out each; 50% cachedPrice this workload in the calculator	$153Lower	$305	$153
Document Q&A (RAG)20,000 questions a month over retrieved documents, 12,000 in and 600 out; 30% cachedPrice this workload in the calculator	$232Lower	$463	$232
Coding agent400 tasks a month, 40 steps each with a growing context; 85% cachedPrice this workload in the calculator	$184Lower	$369	$184

How they differ

GPT-6.1 Terra is cheaper on input ($1 vs $2).
GPT-6.1 Terra is cheaper on output ($5 vs $10), which matters most for long answers and reasoning models.
GPT-6.1 Terra accepts longer prompts (1.05M vs 1M tokens).
Cached input is cheaper on GPT-6.1 Terra ($0.05 vs $0.10), which favours agents and chat apps that resend the same context.
On Epoch AI’s Capabilities Index, GPT-6.1 Terra scores 168 and Claude Sonnet 5.5 167, within each other’s margin of error, so treat them as level on general benchmarks. GPT-6.1 Terra is 2.0× cheaper for a similar score.

Add a third model to this comparison

Recent changes

All changes

26 Oct 2026OpenAI launched GPT-6.1 Terra at $1 / $5 per 1M tokens, with cached input at $0.05: half the price of GPT-6.1 Sol.
7 Oct 2026Anthropic halved Claude Sonnet 5.5's cache-read price from $0.20 to $0.10 per 1M tokens; Anthropic says this cuts most agent workloads by about 20%.
29 Sep 2026GPT-6.1 Sol replaced GPT-6 Sol at the same $2 / $10 per 1M tokens, with cached input cut from $0.20 to $0.10.
28 Sep 2026Claude Sonnet 5.5 replaced Sonnet 5 at the same $2 / $10 per 1M tokens, with cache reads at $0.20.
22 Sep 2026OpenAI launched GPT-6 Sol at $2 / $10 and GPT-6 Luna at $0.10 / $0.50.

Related comparisons

Compare up to four