How to Use GPT-3.5 Turbo 0613 in opencode
GPT-3.5 Turbo 0613 handles short summaries, text extraction, and simple code drafts. Unlike GPT-3.5 Turbo 16K, its 4,096-token context must hold both the request and reply.
Prompts to try with GPT-3.5 Turbo 0613 in opencode
Copy an example into opencode, or ask in your own words.
Use GPT-3.5 Turbo 0613 to explain the project's date-parsing function. Send only that function and its direct dependencies, then return its accepted inputs, outputs, and three edge cases.
Use GPT-3.5 Turbo 0613 to draft tests for the selected validation function. Follow one nearby test as a format example and cover empty input, valid input, and malformed input.
Use GPT-3.5 Turbo 0613 to turn the current short diff into three release-note bullets. Describe only changes visible in the diff.
Use GPT-3.5 Turbo 0613 to draft a read-only SQL query from the project's relevant table definitions. Find the ten customers with the most orders, and explain the joins before I run it.
Use GPT-3.5 Turbo 0613 at temperature 0.2 to extract error names and messages from the selected source file into a JSON array. Parse the result and flag any entries unsupported by the source.
How to set up GPT-3.5 Turbo 0613 in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode 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 GPT-3.5 Turbo 0613
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": "openai/gpt-3.5-turbo-0613", "input": { "messages": [ { "role": "system" } ] } }'
Then paste one of the prompts above: opencode finds GPT-3.5 Turbo 0613 on Spiral, shows the price and runs it.
GPT-3.5 Turbo 0613 providers and prices
Spiral runs GPT-3.5 Turbo 0613 through OpenRouter. Open a card for today's price, with every fee included.
Up to $0.009627 per run at the default inputs. $1.30 per 1M input tokens, $2.60 per 1M output tokens.
Settings you can ask for
Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Seed | a whole number | ||
| Top p | 0 to 1 | ||
| Logprobs | on or off | ||
| Temperature | 0 to 2 | ||
| Top logprobs | 0 to 20 | ||
| Presence penalty | -2 to 2 | ||
| Frequency penalty | -2 to 2 |
Every API field of OpenAI: GPT-3.5 Turbo (older v0613) is on its tool page: open its card above.
What can you do with GPT-3.5 Turbo 0613 in opencode?
Turn small code excerpts into explanations, test drafts, and documentation with GPT-3.5 Turbo. Focus each request on one function or a short diff so the relevant code and answer fit together.
Extract contact details
Pull names, companies, and locations from a short passage. Mark missing details explicitly and validate the resulting records.
Summarize meeting notes
Turn a short transcript into decisions and action items. Keep names and deadlines tied to what the speakers actually said.
Sort support requests
Assign short customer messages to defined categories, using examples to explain ambiguous cases.
Draft customer replies
Write a concise response from a customer message and the relevant policy excerpt. Review the draft before sending it.
Explain a small function
Describe a function's inputs, outputs, and edge cases from its source code. Keep the request focused on a small excerpt.
Draft database queries
Convert a plain-English question into a proposed SQL query using a supplied schema. Check the query before running it.
Answer from a policy excerpt
Draft an answer using a short reference passage and identify questions the passage does not resolve.
Rewrite product text
Turn supplied specifications into a short description with a defined tone and length. Preserve the original claims.
More on GPT-3.5 Turbo 0613 and opencode
Overview
GPT-3.5 Turbo 0613 in other agents
More opencode guides
Questions about GPT-3.5 Turbo 0613 in opencode
Can opencode use GPT-3.5 Turbo 0613?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run GPT-3.5 Turbo 0613 like any built-in tool.
How much does GPT-3.5 Turbo 0613 cost in opencode?
Up to $0.009627 per run at the default inputs. $1.30 per 1M input tokens, $2.60 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.
Do I need an OpenRouter account to use GPT-3.5 Turbo 0613 in opencode?
No. Spiral runs GPT-3.5 Turbo 0613 on its own OpenRouter account. You sign in to Spiral once and never paste a key.
How long does it take to set up GPT-3.5 Turbo 0613 in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while GPT-3.5 Turbo 0613 runs?
GPT-3.5 Turbo 0613 runs in the background. opencode starts the run, checks on it and gives you the text, json when it's ready.
What is GPT-3.5 Turbo 0613 useful for?
Use it for short summaries, extracting details from text, drafting replies, and simple code tasks. Give it the relevant source material and a clearly defined output.
How much text can GPT-3.5 Turbo 0613 handle?
Its context budget is 4,096 tokens, shared by the request and reply. Send relevant excerpts and leave room for the answer.
Can GPT-3.5 Turbo 0613 return reliable JSON?
It supports function calling, but generated arguments still need validation. JSON mode was introduced with GPT-3.5 Turbo 1106, so requesting JSON alone is not a guarantee.
Where does GPT-3.5 Turbo 0613 struggle?
Complex reasoning is a weaker fit than straightforward text tasks. Break a large request into smaller tasks and check conclusions against the supplied evidence.
Can GPT-3.5 Turbo 0613 analyze pictures or recordings?
It takes text and returns text. Supply a transcript or extracted text for tasks involving recordings or scanned material.
Start using GPT-3.5 Turbo 0613 in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


