Claude models and GPT-5.6 Luna are now available to accounts that have topped up at least once. Top up any amount to unlock them — bonus credits can pay for them too. All other models are unaffected.Top up
OpenAI

GPT-5.6 Terra

Save 90%Official

openai/gpt-5.6-terra

Balanced GPT-5.6 quality and cost for production workloads.

Context window
1.1M
Max output
128K
Input modalities
text · image
Output modalities
text
Capabilities
Vision · Reasoning · Tool calling · Coding · Prompt cache · Paid cache writes · Strip Responses Summary Input
Upstream release
2026-07-09
RouteMux name
openai/gpt-5.6-terra
Live model playground

Try GPT-5.6 Terra here

Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.

streamchat
1Configure input
0 / 20,000
Add images

Sign in first to upload images to this vision model.

Maximum estimated cost
2Live result

Your result will appear here

Enter an input on the left. The same RouteMux Playground execution and billing path powers this embedded test.

conversation

What is GPT-5.6 Terra

GPT-5.6 Terra is the middle of the GPT-5.6 line, and for most production traffic it is the one that should be running. It keeps everything structural about Sol — the 1.05M-token context window, vision input, tool calling, configurable reasoning, persisted reasoning, prompt caching — and asks $0.20 / $1.20 per 1M tokens against Sol's $0.40 / $2.00.

Through RouteMux that works out to $0.20 per 1M input tokens against OpenAI's $2, and $1.20 against $12 on output. Three protocols are available: OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages.

The practical way to use the family is to default to Terra and escalate. Because all three models share the same context window and the same request shape, escalation is a one-line change, and you find out quickly whether a task actually needed Sol or just needed a better prompt.

GPT-5.6 Terra API pricing

Source: openai_x0.10 · Verified 2026-08-24

InputOfficial $2 / M tokens
$0.2/ M tokensSave 90%
OutputOfficial $12 / M tokens
$1.2/ M tokensSave 90%

Fast $0.4 / $2.4 /M

Cache read $0.02/M · Cache write $0.25/M

TierInputCache readCache writeOutput
Standard ≤272K$0.2$2−90%$0.02$0.2−90%$0.25$2.5−90%$1.2$12−90%
Standard >272K$0.4$4−90%$0.04$0.4−90%$0.5$5−90%$1.8$18−90%
Priority ≤272K$0.4$4−90%$0.04$0.4−90%$0.5$5−90%$2.4$24−90%

Estimate cost

Estimated cost$0.0032

Limited time20% extra Credits on your first top-up — up to 200 bonus Credits

Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.

Sign up and claimNo subscription. Pay for what you use.

Key capabilities

Same structure as Sol

1.05M context, vision, tools, reasoning controls and caching are identical — only price and depth differ.

Built for steady production load

Priced so that a high-traffic assistant or coding agent can run on it continuously rather than as a treat.

Escalation is one line

Moving a hard request up to Sol means changing the model string, nothing else.

Three protocols

OpenAI Chat, OpenAI Responses, and Anthropic Messages all route here.

Interface and protocols

OpenAI Chat CompletionsStreamingOpenAI ResponsesStreamingAnthropic MessagesStreaming

Use any of these IDs to call this model via the API.

RouteMux nameopenai/gpt-5.6-terra

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

from openai import OpenAI

client = OpenAI(
    base_url="https://api.routemux.com/v1",
    api_key="<ROUTEMUX_KEY>",
)

completion = client.chat.completions.create(
    model="openai/gpt-5.6-terra",
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)
base_url: https://api.routemux.com/v1

Performance (last 30 days)

GPT-5.6 Terra FAQ

What is GPT-5.6 Terra?

Balanced GPT-5.6 quality and cost for production workloads.

How large is the context window of GPT-5.6 Terra?

GPT-5.6 Terra supports a context window of up to 1.1M tokens, with up to 128K output tokens per request.

How much does the GPT-5.6 Terra API cost?

Through RouteMux, GPT-5.6 Terra costs $0.2 for input and $1.2 for output (USD per 1M tokens), below the official list price.

How do I call GPT-5.6 Terra via API?

GPT-5.6 Terra is OpenAI-compatible: point your base URL at RouteMux and set the model field to openai/gpt-5.6-terra — no code changes needed.

Which input and output modalities does GPT-5.6 Terra support?

GPT-5.6 Terra accepts text, image as input and produces text as output.

When was GPT-5.6 Terra released?

GPT-5.6 Terra was released on July 9, 2026.

When should I use Sol instead of Terra?

When the task is failing on Terra for reasoning reasons rather than prompt reasons. Both have the same context and tools, so context pressure is not the differentiator.

Is the context window really the same as Sol's?

Yes — 1.05M tokens on both, with 128K max output.

Sources