How to Use o3 in Hermes
Use o3 to debug difficult code, solve math problems, and interpret charts. Compared with o3-pro, it suits complex work that does not need the extra deliberation aimed at more reliable answers.
Prompts to try with o3 in Hermes
Copy an example into Hermes, or ask in your own words.
Every morning, use o3 to review the incident summaries supplied for that run. Group related failures, rank plausible shared causes, and list the evidence needed to test each cause.
Each week, use o3 to compare the dated research abstracts supplied for that run. Group findings by hypothesis, flag disagreements, and distinguish reported results from your interpretations.
Each Monday, use o3 to compare the current and previous requirements supplied for that run. Identify contradictions and changed assumptions, then produce a concise list of decisions needed.
Every Monday at 9am: ask o3 through Spiral to review the diff on this branch and list the three riskiest changes.
Get a second opinion from o3 on this function, then tell me what the call cost.
How to set up o3 in Hermes
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Hermes 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 Spiral's MCP server
- Add the server and sign in
Hermes opens your browser: sign in to Spiral and click Authorize. No API key. When Hermes asks Enable all tools? \[Y/n/select], answer Y: n cancels without saving the server, and select hides the tools you leave out.
hermes mcp add spiral \ --url https://api.spiral.ai/mcp \ --auth oauth \ --connect-timeout 300
- Check it
In a chat that was already open, run /reload-mcp.
hermes mcp list hermes mcp test spiral
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 o3
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": "openai", "model": "openai/o3", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: Hermes finds o3 on Spiral, shows the price and runs it.
o3 providers and prices
Spiral runs o3 through OpenAI. Open a card for today's price, with every fee included.
Up to $0.04269 per run at the default inputs. $2.60 per 1M input tokens, $0.65 per 1M cached input tokens, $10.40 per 1M output tokens.
Settings you can ask for
Ask Hermes for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Max tokens | 16 to 100000 | The most output tokens to generate. | |
| Parallel tool calls | on or off |
Every API field of o3 is on its tool page: open its card above.
What can you do with o3 in Hermes?
OpenAI o3 can turn recurring evidence into a review of risks, inconsistencies, and next steps. Give each scheduled review a clear question and require supporting observations for its conclusions.
Investigate a difficult bug
Give OpenAI o3 the failing behavior, relevant code, and test results. Ask for a likely cause, a minimal fix, and a regression test that demonstrates the problem.
Review a database migration
Have OpenAI o3 compare a proposed migration with its requirements. Request failure scenarios, data consistency checks, and a rollback plan.
Check a mathematical solution
Supply the problem and proposed answer to OpenAI o3. Ask it to identify invalid assumptions, check boundary cases, and return a corrected solution when needed.
Compare scientific explanations
Give OpenAI o3 observations and competing hypotheses. Request the evidence for each explanation and an experiment that could distinguish them.
Interpret a chart
Provide OpenAI o3 with a chart image and its surrounding context. Ask for the main trend, supporting observations, and claims the chart does not establish.
Compare conflicting requirements
Ask OpenAI o3 to reconcile supplied specifications or policy excerpts. Request the conflicting passages, their practical consequences, and the decisions still needed.
Plan a complicated project
Give OpenAI o3 the goal, constraints, and dependencies. Ask for an ordered plan with checkpoints and explicit conditions for moving to the next task.
Find evidence across long source material
Provide OpenAI o3 with labeled source excerpts and a specific question. Ask it to extract relevant passages and distinguish documented conclusions from unresolved questions.
More on o3 and Hermes
Overview
o3 in other agents
Questions about o3 in Hermes
Can Hermes use o3?
Yes. Add Spiral to Hermes as an MCP server, and Hermes can find and run o3 like any built-in tool.
How much does o3 cost in Hermes?
Up to $0.04269 per run at the default inputs. $2.60 per 1M input tokens, $0.65 per 1M cached input tokens, $10.40 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Hermes plan is separate.
Do I need an OpenAI account to use o3 in Hermes?
No. Spiral runs o3 on its own OpenAI account. You sign in to Spiral once and never paste a key.
How long does it take to set up o3 in Hermes?
About two minutes: add the server and sign in, then check it.
Does Hermes wait while o3 runs?
o3 runs in the background. Hermes starts the run, checks on it and gives you the text, json when it's ready.
What is OpenAI o3 good at?
OpenAI o3 is suited to difficult coding, math, science, and visual analysis. Useful tasks include investigating a bug, checking a calculation, or interpreting a chart alongside its supporting explanation.
How does o3-pro differ from o3?
o3-pro uses o3 as its underlying model and thinks longer to produce more reliable responses. Choose it for a difficult question where you want additional deliberation.
How much material can OpenAI o3 handle?
o3 and o3-pro each have a 200,000-token context window and a maximum output allowance of 100,000 tokens. Internal reasoning also uses generated tokens, so that allowance does not mean 100,000 tokens of readable text.
How should I prompt OpenAI o3?
Use brief, direct instructions. State the question, provide the relevant evidence, and specify the final result you need, such as a patch, comparison table, or short recommendation.
Does OpenAI o3 know about recent events?
o3 and o3-pro have a June 1, 2024 knowledge cutoff. For later events, provide dated source material and ask the model to base its answer on that evidence.
Start using o3 in Hermes
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Hermes:
set up https://spiral.ai/SKILL.md


