How to Use Llama 3.1 Euryale 70B v2.2 in Gemini CLI
Llama 3.1 Euryale 70B v2.2 is built for creative roleplay and fiction. Compared with Euryale 70B v2.1, its training adds conversations intended to improve continuity across turns.
Prompts to try with Llama 3.1 Euryale 70B v2.2 in Gemini CLI
Copy an example into Gemini CLI, or ask in your own words.
Use Llama 3.1 Euryale 70B v2.2 to draft 12 greeting lines for the harbor merchant using this project's character notes. Keep each line under 20 words and flag any lore assumptions for review.
Read this project's quest outline, then use Llama 3.1 Euryale 70B v2.2 to draft a 400-word encounter with the missing cartographer. End with three player choices and stop before choosing one.
Use Llama 3.1 Euryale 70B v2.2 to rewrite the tavern dialogue in this project so the innkeeper sounds guarded and impatient. Preserve every clue and quest condition; show the proposed text before editing.
Use Llama 3.1 Euryale 70B v2.2 with temperature 1.2 and min_p 0.2 to draft three 150-word openings for this project's lighthouse encounter. Keep the location and cast fixed, but vary the source of tension.
Use Llama 3.1 Euryale 70B v2.2 to draft eight exchanges between the rival explorers described in this project's lore. Give each a different speaking rhythm and leave the expedition's outcome unresolved.
How to set up Llama 3.1 Euryale 70B v2.2 in Gemini CLI
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Or add it to ~/.gemini/settings.json yourself:
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
- Sign in
Start gemini and run:
/mcp auth spiral
- Check it
In Gemini CLI, run /mcp. From your shell:
gemini mcp list
Use the Spiral skill
- Send Gemini CLI this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Llama 3.1 Euryale 70B v2.2
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "openrouter", "model": "sao10k/l3.1-euryale-70b", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Gemini CLI finds Llama 3.1 Euryale 70B v2.2 on Spiral, shows the price and runs it.
Llama 3.1 Euryale 70B v2.2 providers and prices
Spiral runs Llama 3.1 Euryale 70B v2.2 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.004566 per run at the default inputs. $1.105 per 1M input tokens, $1.105 per 1M output tokens.
Settings you can ask for
Ask Gemini CLI for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Min p | 0 to 1 | ||
| Top k | a whole number from 0 | ||
| Top p | 0 to 1 | ||
| Max tokens | 1 to 16384 | The most output tokens to generate. | |
| Temperature | 0 to 2 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 | ||
| Repetition penalty | 0 to 2 |
Every API field of Sao10K: Llama 3.1 Euryale 70B v2.2 is on its tool page: open its card above.
What can you do with Llama 3.1 Euryale 70B v2.2 in Gemini CLI?
Turn your game's character notes into dialogue drafts and branching scenes with Euryale 70B v2.2. Have your coding agent compare the drafts with the project's lore before adding them.
Game character dialogue
Draft a shopkeeper's greeting, bargaining exchange, and farewell using a defined personality and knowledge of the player.
Interactive fiction
Write a scene that ends at a decision point, then continue from the reader's chosen action.
Tabletop roleplay
Rehearse an encounter with a suspicious innkeeper or rival explorer, leaving the player's decisions to the player.
Character voice exploration
Give three characters the same uncomfortable news and draft a distinct reaction for each.
Scene rewrites
Rewrite a confrontation from another character's viewpoint while keeping the events and ending fixed.
Serialized fiction drafts
Draft the next short installment from an approved recap, character notes, and a specific unresolved conflict.
Dialogue rehearsal
Explore a fictional conversation over several exchanges before adapting it into a script or comic.
More on Llama 3.1 Euryale 70B v2.2 and Gemini CLI
Overview
Llama 3.1 Euryale 70B v2.2 in other agents
Questions about Llama 3.1 Euryale 70B v2.2 in Gemini CLI
Can Gemini CLI use Llama 3.1 Euryale 70B v2.2?
Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Llama 3.1 Euryale 70B v2.2 like any built-in tool.
How much does Llama 3.1 Euryale 70B v2.2 cost in Gemini CLI?
Up to $0.004566 per run at the default inputs. $1.105 per 1M input tokens, $1.105 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.
Do I need an OpenRouter account to use Llama 3.1 Euryale 70B v2.2 in Gemini CLI?
No. Spiral runs Llama 3.1 Euryale 70B v2.2 on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up Llama 3.1 Euryale 70B v2.2 in Gemini CLI?
About two minutes: add the server, then sign in, then check it.
Does Gemini CLI wait while Llama 3.1 Euryale 70B v2.2 runs?
Llama 3.1 Euryale 70B v2.2 runs in the background. Gemini CLI starts the run, checks on it and gives you the text, json when it's ready.
What is Euryale 70B v2.2 best used for?
Creative roleplay is its stated focus. Try character conversations, scene drafts, and interactive fiction.
What changed from Euryale 70B v2.1?
The maker added conversation instruction data aimed at improving coherence across turns. That is a training goal, so check continuity in your own scenes.
How much text can Euryale 70B v2.2 handle?
OpenRouter lists a 131,072-token context window and up to 16,384 completion tokens. For longer fiction, request one scene at a time.
Which sampling settings should I try?
The maker recommends temperature 1.2 and minimum token probability 0.2. Treat those as starting values and compare results using the same scene brief.
What weakness should I watch for?
The maker reports occasional erratic responses and recommends regeneration. Review each continuation before accepting it into your story.
Start using Llama 3.1 Euryale 70B v2.2 in Gemini CLI
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Gemini CLI:
set up https://spiral.ai/SKILL.md


