Big-AGI is an open-source workspace for using multiple AI models through chat and other AI functions. It is intended for engineers, founders, researchers, and other users who want to work with AI personas, model comparisons, image generation, voice, documents, and code-related features. The catalogue entries provide commands, instructions, and a skill for working with Big-AGI.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/enricoros/big-agi/update-models-perplexitygit clone --depth 1 https://github.com/enricoros/big-AGIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/enricoros/big-agi/update-models-perplexity)<a href="https://agentmods.dev/commands/enricoros/big-agi/update-models-perplexity"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/update-models-perplexity.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00011 | $0.00616 |
| Opus 5 | $0.00005 | $0.00308 |
| Sonnet 5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
update-models-perplexity scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Update src/modules/llms/server/openai/models/perplexity.models.ts with latest model definitions.
Reference src/modules/llms/server/llm.server.types.ts and src/modules/llms/server/models.mappings.ts for context only. Focus on the model file, do not descend into other code.
Primary Sources: (append .md to any docs URL for raw markdown - the HTML is MDX-heavy)
- Served model ids + full request schema (authoritative): https://docs.perplexity.ai/api-reference/sonar-post.md - the
modelenum is the served list - Per-model context length + prices: https://docs.perplexity.ai/docs/sonar/models/{sonar,sonar-pro,sonar-reasoning-pro,sonar-deep-research}
- Pricing (single source of truth
PRICINGobject in the page - readPRICING.sonar.models[]; the other tables on that page are Agent API/Gateway): https://docs.perplexity.ai/getting-started/pricing - Changelog: https://docs.perplexity.ai/changelog/changelog
- Media/attachments (image + file input support): https://docs.perplexity.ai/guides/image-guide
Note: https://docs.perplexity.ai/getting-started/models is now marketing-only (no ids, no context windows).
Fallbacks if blocked: Search "perplexity api latest pricing", "perplexity latest models", or search GitHub for latest model prices and context windows
Live endpoint (extra signal): The Sonar API has no list-models endpoint, but if .env.api-keys has PERPLEXITY_API_KEY a minimal /chat/completions probe against a candidate id confirms it's served (docs now name the path POST /v1/sonar; /chat/completions, the path big-AGI calls, is an alias with the identical schema) (max_tokens must be >= 16; retired ids 400 with an explicit "deprecated"/"Invalid model" message). Never commit or echo the key.
Not this vendor: the Agent API (/v1/agent, resells Anthropic/OpenAI/Google/xAI) and the Gateway (https://api.perplexity.ai/router/v1, incl. GET /router/v1/models, open-weight models hosted by Perplexity) are separate Perplexity products - out of scope for this file. Since July 2026 every Sonar docs page carries a banner steering to the Agent API; the four Sonar ids are still served and still in scope.
Important:
- Review the full model list for additions, removals, and price changes
- Minimize whitespace/comment changes, focus on content
- Preserve comments to make diffs easy to review
- Flag broken links or unexpected content
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 28 lines · 11 tokens per session scan A 067bffd71c60
update-models-perplexity is a command published in the GitHub repository enricoros/big-AGI (7,109 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 616 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
AGENTS
Per-command agent-optimized usage and structure guide.
netllm-connect
Wire Cursor, Claude Code, Codex, or Honcho to the local netllm router.
setup
Configure claude-delegator with Codex (GPT) or Gemini MCP servers.
post-claims
Follow the Post Claims SOP in docs/sops/POSTCLAIMSSOP.md.
forge
You are in FORGE MODE. Execute the following.
apex-architect
Use the @apex-architect agent to help the user with the following architectural or debugging matter: $ARGUMENTS.