feat(openrouter/openai/gpt-5.6-terra): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for openrouter/openai/gpt-5.6-terra.

---

Note

Low Risk
Declarative model metadata only; no runtime, auth, or application logic changes.

Overview
Adds a new OpenRouter provider definition for openai/gpt-5.6-terra at providers/openrouter/openai/gpt-5.6-terra.yaml, following the existing catalog pattern (auto-generated by model-addition-agent).

The entry registers chat mode with thinking enabled, 1.05M context and 128k max output, pdf/image/text inputs, and standard tool features (function calling, JSON/structured output, prompt caching). Pricing includes per-token input/output plus cache read/create costs, with OpenRouter as the source URL.

^{Reviewed by Cursor Bugbot for commit cd9cd5d. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 964f4f4. Configure here.}

[cursor]

Missing long-context tiered pricing

Medium Severity

The costs entry only lists base per-token rates, but gpt-5.6-terra uses cumulative long-context pricing above 272k tokens (as in providers/openai/gpt-5.6-terra.yaml and providers/openrouter/openai/gpt-5.4.yaml). With a 1.05M context_window, spend estimates for large prompts can be materially wrong.

 

^{Reviewed by Cursor Bugbot for commit 964f4f4. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 10
• Passed: 10
• Failed: 0
• Validation failed: 0
• Errored: 0
• Skipped: 0
• Success rate: 100.0%

Provider	Model	Scenarios
openrouter	openai/gpt-5.6-terra	success: tool-call:text-text:stream, tool-call:text-text, params:text-text:stream, params:text-text, structured-output:text-text, structured-output:text-text:stream, json-output:text-text, json-output:text-text:stream, reasoning:text-text, reasoning:text-text:stream

Successes (10)

openrouter/openai/gpt-5.6-terra — tool-call:text-text:stream (success)

Output

{"location":"London"}
VALIDATION: tool-call stream SUCCESS

openrouter/openai/gpt-5.6-terra — tool-call:text-text (success)

Output

Function: get_weather
Arguments: {"location":"London"}
VALIDATION: tool-call SUCCESS

openrouter/openai/gpt-5.6-terra — params:text-text:stream (success)

Output

The capital of France is Paris.

openrouter/openai/gpt-5.6-terra — params:text-text (success)

Output

The capital of France is Paris.

openrouter/openai/gpt-5.6-terra — structured-output:text-text (success)

Output

{"name":"Science fair","date":"Friday","participants":["Alice","Bob"]}
VALIDATION: structured-output SUCCESS

openrouter/openai/gpt-5.6-terra — structured-output:text-text:stream (success)

Output

{"name":"Science fair","date":"Friday","participants":["Alice","Bob"]}
VALIDATION: structured-output stream SUCCESS

openrouter/openai/gpt-5.6-terra — json-output:text-text (success)

Output

{
  "red": "#FF0000",
  "green": "#00FF00",
  "blue": "#0000FF"
}
VALIDATION: json-output SUCCESS

openrouter/openai/gpt-5.6-terra — json-output:text-text:stream (success)

Output

{
  "red": "#FF0000",
  "green": "#00FF00",
  "blue": "#0000FF"
}
VALIDATION: json-output stream SUCCESS

openrouter/openai/gpt-5.6-terra — reasoning:text-text (success)

Output

Exponentiation is evaluated **right to left**:

\[
3^3^3^3 = 3^{(3^{(3^3)})}
\]

Step by step:

1. Compute the top exponent:

\[
3^3 = 27
\]

2. Then:
... (truncated, 489 chars omitted)

openrouter/openai/gpt-5.6-terra — reasoning:text-text:stream (success)

Output

Exponentiation is evaluated **right to left**:

\[
3^3^3^3 = 3^{(3^{(3^3)})}
\]

Step by step:

1. Evaluate the top exponent:

\[
3^3 = 27
\]

2. Then
... (truncated, 428 chars omitted)