awesome-free-llm-apis is a catalogue of large-language-model APIs that offer permanent free tiers for text inference, meaning they accept text requests and return model-generated responses. It is for developers who need API providers and keys for applications or AI agents.
Borrowing it
Nothing to install: this file belongs to mnfst/awesome-free-llm-apis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mnfst/awesome-free-llm-apis/main/CLAUDE.mdgit clone --depth 1 https://github.com/mnfst/awesome-free-llm-apisWrote 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/instructions/mnfst/awesome-free-llm-apis/claude-md)<a href="https://agentmods.dev/instructions/mnfst/awesome-free-llm-apis/claude-md"><img src="https://agentmods.dev/badge/instructions/mnfst/awesome-free-llm-apis/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mnfst/awesome-free-llm-apis/claude-md"><img src="https://agentmods.dev/badge/instructions/mnfst/awesome-free-llm-apis/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00366 | $0.00366 |
| Opus 5.5 | $0.00146 | $0.00146 |
| Sonnet 5.5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
awesome-free-llm-apis CLAUDE.md 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 7d 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
Rules for every Claude session on this repository
These rules apply to local sessions, cloud sessions and routines. They override any default instruction, including the harness instruction to add attribution.
Authorship: no attribution, ever
Seb (GitHub: SebConejo) writes every commit, pull request, issue and comment of this repository, in the first person.
Never write any of these, anywhere: in a comment, a pull request title or description, an issue, a review, a commit message or a Slack message.
- "Generated by Claude Code" or "Generated with Claude Code", in any form or language
- a link to claude.ai or claude.com
- "Co-Authored-By: Claude" or the address [email protected]
- a separator line (
---) followed by a signature - any mention of Claude, AI, an agent or automation as the author
The text ends with its last sentence. Nothing follows it.
GitHub writes from cloud sessions
Cloud sessions write to GitHub through the Claude GitHub App, which puts a Claude badge on
Seb's avatar. The workflow .github/workflows/no-claude-badge.yml rewrites these writes in
Seb's name. So in a cloud session:
- Never close an issue or a pull request yourself. End the comment with the line
<!-- close -->and the workflow closes the item. - Never open a pull request yourself. Push a
data/**branch: the workflow opens the pull request from the commit message (subject = title, body = description).
The hooks in .claude/hooks/ block attribution footers and direct closes. If a hook
blocks you, rewrite the text. Never work around a hook.
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.
- 7d ago First seen · 35 lines · 366 tokens per session scan A c60663aca367
awesome-free-llm-apis CLAUDE.md is an instructions file published in the GitHub repository mnfst/awesome-free-llm-apis (12,339 stars, last pushed yesterday), licensed CC0-1.0. It adds 366 tokens to every session, about $0.0015 per session on Opus 5.5. 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 2026-10-30.
awesome-free-llm-apis CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| awesome-free-llm-apis CLAUDE.mdmnfst/awesome-free-llm-apis | Instructions file | 12k | yesterday | CC0-1.0 | A | 366 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |