[cerebras] Add Gemma 4 31B model config

[ryanl-cerebras]

Description

Adds the current Cerebras Gemma 4 31B public model to the general and pricing catalogs. The configuration records its 40,960-token maximum output, tool and image support, and current input and output pricing.

• New model pricing
• Update existing pricing
• New model configuration
• Bug fix

Source Verification

Source Link: https://api.cerebras.ai/public/v1/models

The live public catalog reports gemma-4-31b with $0.99 per million input tokens and $1.49 per million output tokens. Portkey prices are stored in cents per token, so these convert to 0.000099 and 0.000149 respectively.

Additional announcement: https://www.cerebras.ai/blog/gemma-4-on-cerebras-the-fastest-inference-is-now-multimodal

Checklist

• I have validated the JSON using jq
• I have verified that prices are in cents per token, not dollars
• I have included the source link above
• I have signed the CLA, if required for a first-time contributor

Validation

• jq syntax validation for both changed files
• duplicate-key validation
• ESLint
• Prettier
• live catalog assertions for model ID, capabilities, output limit, and pricing conversion

Related Issue

None.

[ryanl-cerebras]

Where do I signed the CLA? I could not find a link.