skills.rest
OnlyTerp
OnlyTerpCOMMUNITY
Explore all skills by this author →
GitHub

opencode-mistral-cache-key

Set the prompt_cache_key for Mistral models in OpenCode's transform.ts file.

113|8|Updated May 28, 2026
Search Tags:#cost savings#OpenCode#Mistral#prompt caching#API optimization
One-click install
npx skills add https://github.com/OnlyTerp/prompt-cache-skills --skill opencode-mistral-cache-key
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: opencode-mistral-cache-key
Source: https://github.com/OnlyTerp/prompt-cache-skills/tree/main/skills/opencode-mistral-cache-key
Command: npx skills add https://github.com/OnlyTerp/prompt-cache-skills --skill opencode-mistral-cache-key

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

OpenCode fails to set the necessary prompt_cache_key for Mistral models, leading to missed opportunities for prompt caching and reduced cost savings.

Core Features & Use Cases

  • Optimize Cache Usage: Automatically sets the required prompt_cache_key for Mistral requests, enabling prompt caching.
  • Cost Savings: Increases cache hit rates to achieve up to 90% cost savings on cached tokens.
  • Use Case: Integrates with OpenCode to ensure that API calls to Mistral benefit from caching, reducing unnecessary API usage and costs.

Quick Start

Apply the opencode-mistral-cache-key skill to your OpenCode setup to activate prompt caching for Mistral models.

Frequently Asked Questions about opencode-mistral-cache-key

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enable prompt caching for Mistral models in OpenCode?▼

To enable prompt caching for Mistral models in OpenCode, you must apply a modification to the `transform.ts` file to set the missing `prompt_cache_key` parameter. This fix automatically configures API requests to utilize caching.

Why does OpenCode fail to reduce API costs with Mistral prompt caching?▼

OpenCode fails to reduce API costs because it lacks the `prompt_cache_key` setting for Mistral models. Without this key, API requests miss caching opportunities, preventing potential cost savings of up to 90% on cached tokens.

What are the cost savings from optimizing Mistral API cache hit rates?▼

Optimizing Mistral API cache hit rates can achieve up to 90% cost savings on cached tokens. By ensuring the `prompt_cache_key` is properly set, unnecessary API usage is drastically reduced, improving both performance and cost efficiency.

Do I need to modify OpenCode source files to apply the Mistral cache fix?▼

Yes, applying the Mistral cache fix requires direct modification of OpenCode's `transform.ts` file. This source code adjustment is necessary to inject the `prompt_cache_key` setting into the API integration.

Does OpenCode natively support the prompt_cache_key setting for Mistral integrations?▼

No, OpenCode does not natively support the `prompt_cache_key` setting for Mistral integrations. This skill provides the necessary script to patch the integration and activate prompt caching for reduced API usage.

Related Skills

Explore More Software Engineering Skills→
justinlevinedotmejustinlevinedotme
7

mcp-installer

Locate and provision MCP servers for OpenCode workflows.

Community
Intermediate
dkyazzentwatwadkyazzentwatwa
32

nav-stats

Generate session efficiency reports with token savings and cache performance metrics.

Community
Intermediate
felvieirafelvieira
22

cost-tracker

Aggregate tokens, API usage, and execution time to generate per-skill and session cost reports.

Community
Advanced
nrupalanrupala

use-native-credential-proxy

Replace OneCLI gateway with NanoClaw's credential proxy for .env-based API requests.

Community
Intermediate