Long context

GPT-5.6 Terra API pricing

OpenAI's GPT series — broad general capability, wide ecosystem, and the native models behind Codex CLI.

Model IDopenai/gpt-5.6-terra

ChatStreamingTool callingVision

Get API Key Run your first request

Call summary

Input

$2.50$0.25/ 1M tokens

Cache write $0.25

Cache read $0.125

Output

$15.00$1.50/ 1M tokens

Applies to request input ≤ 272,000 tokens · See pricing tiers

Context Window

1.05M

API Endpoints

GPT-5.6 Terra API endpoints

One API key — call this model through any of the 2 endpoints below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model

Chat Completions reference

POST/v1/responsesResponses API · Native for Codex CLI

Responses API reference

GPT-5.6 Terra pricing tiers

Pricing is tiered by total input length per request (cache included); once a threshold is crossed, the whole request is billed at that tier. All prices are per 1M tokens.

Tier

Standard≤ 272K

Input

$2.50$0.25Cache write: $0.25Cache read: $0.125

Output

$15.00$1.50

Tier

Long context> 272K

Input

$5.00$0.50Cache write: $0.50Cache read: $0.25

Output

$22.50$2.25

Tier	Input	Output
Standard≤ 272K	$2.50$0.25Cache write: $0.25Cache read: $0.125	$15.00$1.50
Long context> 272K	$5.00$0.50Cache write: $0.50Cache read: $0.25	$22.50$2.25

Call GPT-5.6 Terra from your code

The same API key works across all 2 endpoints below.

Endpoint

/v1/chat/completions

Model ID

openai/gpt-5.6-terra

Request example

bash

curl -X POST \
  https://api.router.one/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-5.6-terra",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Get API Key

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Successful response share

98.81%

Success 2xx

98.81%

Rate limit 429

0.00%

Server 5xx

1.19%

TPS

103.28

tokens/s

Avg. time to first token

23.2 s

Avg. latency

18.15 s

Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.

Updated Oct 25, 2026, 2:12 AM UTC

More GPT models on Router One

15 other GPT models on the same gateway and API key — each page lists endpoints, posted price, and context window.

Codex Auto Review$0.50 in / $3.00 out per 1M1.05M context GPT-5.6 Sol$0.50 in / $4.00 out per 1M1.05M context GPT-6.1 Sol$0.40 in / $2.00 out per 1M1.05M context GPT-6 Astra$2.00 in / $10.00 out per 1M1.05M context GPT-6 Sol$0.40 in / $2.00 out per 1M1.05M context GPT Image 2$0.50 per image GPT Image 2.5 Flare$0.50 per image GPT Image 2.5 Sunburst$0.50 per image

7 channel versions

GPT-5.5 · Azure$3.75 in / $22.50 out per 1M1.05M context GPT-5.6 Luna · Azure$0.15 in / $0.90 out per 1M1.05M context GPT-5.6 Sol · Azure$3.00 in / $15.00 out per 1M1.05M context GPT-5.6 Terra · Azure$1.50 in / $9.00 out per 1M1.05M context GPT-6.1 Sol · Azure$1.50 in / $7.50 out per 1M1.05M context GPT-6 Astra · Azure$7.50 in / $37.50 out per 1M1.05M context GPT-6 Sol · Azure$1.50 in / $7.50 out per 1M1.05M context

GPT-5.6 Terra compared with other models

Spec and price matchups against peer models.

GPT-5.6 Sol vs GPT-5.6 Terra Grok 4.6 vs GPT-5.6 Terra GPT-5.6 Terra vs Claude Sonnet 5 Gemini 3.8 Flash vs GPT-5.6 Terra

GPT-5.6 Terra at a glance

GPT-5.6 Terra (model ID openai/gpt-5.6-terra) is a GPT-series text model on Router One. GPT-5.6 Terra is priced in whole-request tiers. Request input ≤ 272,000 tokens: Input $0.25 / 1M tokens, Output $1.50 / 1M tokens, Cache write $0.25 / 1M tokens, Cached input $0.125 / 1M tokens; request input > 272,000 tokens: Input $0.50 / 1M tokens, Output $2.25 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.25 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold. Router One subscriptions include GPT-5.6 Terra in the Mid-tier models allowance: Pro 1,200, Max 4,500, Ultra 15,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Within a plan allowance, a request above 272,000 / 512,000 input tokens counts as 2 / 4 requests. Context window: 1.05M tokens. Accepts text, image; returns text. Endpoints: POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path).

GPT-5.6 Terra FAQ

How much does GPT-5.6 Terra cost on Router One?

GPT-5.6 Terra is priced in whole-request tiers. Request input ≤ 272,000 tokens: Input $0.25 / 1M tokens, Output $1.50 / 1M tokens, Cache write $0.25 / 1M tokens, Cached input $0.125 / 1M tokens; request input > 272,000 tokens: Input $0.50 / 1M tokens, Output $2.25 / 1M tokens, Cache write $0.50 / 1M tokens, Cached input $0.25 / 1M tokens. The total input tokens in each request select the tier; its rates apply to the whole request, not only tokens above the threshold.

Is GPT-5.6 Terra included in Router One subscriptions?

Router One subscriptions include GPT-5.6 Terra in the Mid-tier models allowance: Pro 1,200, Max 4,500, Ultra 15,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Within a plan allowance, a request above 272,000 / 512,000 input tokens counts as 2 / 4 requests.

Which endpoints serve GPT-5.6 Terra?

GPT-5.6 Terra is served on 2 endpoints — POST /v1/chat/completions (OpenAI-compatible), POST /v1/responses (Responses API, the Codex CLI path). The same Router One API key works on each.

What is GPT-5.6 Terra's context window?

GPT-5.6 Terra accepts up to 1.05M tokens of context per request on Router One.

Start using GPT-5.6 Terra

Create an API key and call GPT-5.6 Terra at $0.25 in / $1.50 out per 1M tokens (request input ≤ 272,000 tokens) on Router One — pay as you go, with per-request cost and latency visibility.

Get API Key Plans & pay-as-you-go pricing Compare models side by side Quickstart guide GPT API access