gpt-6.1-terra

Availability93.0%

Available

Samples: 14

Latency5.6 s

OpenAI GPT-6.1 Terra: mid-tier GPT-6.1 model for everyday agentic, coding, computer-use and writing work at half the price of GPT-6.1 Sol, 1.05M context with tiered long-context pricing above 272K tokens.

Total input tokens < 272,000

Input: $1/1M
Output: $5/1M
Cache read: $0.05/1M
Cache write: $1.25/1M

Total input tokens ≥ 272,000

Input: $2/1M
Output: $7.5/1M
Cache read: $0.1/1M
Cache write: $2.5/1M

Route: Default

Roleplay

No matching public benchmark is available for this model.

Not measured

Routes

Score

Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.

Sort by

						Use this model
Default	Total input tokens < 272,000 Input $1/1M Output $5/1M Cache read $0.05/1M Cache write $1.25/1M Total input tokens ≥ 272,000 Input $2/1M Output $7.5/1M Cache read $0.1/1M Cache write $2.5/1M			Not measured	Not measured	Use this model
openai_pro	Total input tokens < 272,000 Input $0.1/1M Output $0.5/1M Cache read $0.005/1M Cache write $0.125/1M Total input tokens ≥ 272,000 Input $0.2/1M Output $0.75/1M Cache read $0.01/1M Cache write $0.25/1M			Not measured	Not measured	Plans and tiers

Quick start

Access and billing

curl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
  -H "Authorization: Bearer $TOKENREPLY_API_KEY" \
  -H 'Content-Type: application/json' \
  --data '{
  "model": "gpt-6.1-terra",
  "messages": [
    {
      "role": "user",
      "content": "Reply with hello."
    }
  ]
}'

TokenReply

gpt-6.1-terra

Routes

Quick start

More OpenAI models