awesome-free-ai-coding · every free model · every provider · filter the list

Where flint-v1.0 is free

4 rows on the list serve flint-v1.0 free: opencode, OpenRouter (free models), Kilo Code and AIHubMix (free models). None asks for a card; Kilo Code answers with no account at all. The providers’ last scheduled probes were on 2026-11-12; their offers are rechecked twice a week.

Every free model · the whole list

Who serves it free

opencode

🤖 Coding agents & CLIs · no card · last probe 2026-11-12 · listed since 2026-11-10

Open-source coding agent whose opencode Zen gateway prices a rotating set of models at zero — inside OpenCode only, no sign-in; any provider via BYOK

Provider-wide limits

Limits, in the vendor’s words: Free model usage: Usage allowance: amount not published (period not published); scope not published

Free models work only inside OpenCode; other clients receive 403 FreeTierError: OpenCode's free tier can only be used from within OpenCode. Use opencode/<model-id> and select the Free variant. Offers rotate; each named free offer is “available on OpenCode for a limited time”. Collected free-model data may improve models; NVIDIA offers are trial-only and exclude personal or confidential data. Flint 40B Free allows training and retains data for 30 days. Beam Free’s provider does not train on inputs and retains them for 30 days; its listed territorial exclusions include Russia. Inkling 2 Small Free permits training. It has model-specific territorial exclusions, including Russia. LongCat 2.5 Free is hosted in China; its provider does not train on inputs or retain them.

No API endpoint to paste: this row is a tool you install or sign in to.
In opencode’s own model list: Flint 40B Free
What you send may be used to train or improve models (the vendor’s words).

OpenRouter (free models)

🧭 Aggregators (one key, many providers) · no card · last probe 2026-11-12 · listed since 2026-11-10

One API key for a rotating set of :free model variants, open-weight and stealth models among them

Provider-wide limits

Limits, in the vendor’s words: 50 requests/day; 20 requests/minute per account

1,000 requests/day per account (after 10 credits purchased all-time)

OpenRouter’s FAQ says its free models “have low rate limits” and “are usually not suitable for production use”, and its limits page warns that a negative credit balance can produce errors “including for free models” and that a 429 can come from the upstream provider rather than the platform (read 2026-09-27). The docs define the daily counter as “Free-model requests recorded so far in the current UTC day”. The higher daily ceiling is granted “starting one credit below the table’s threshold” to absorb rounding and top-up fees.

Base URL: https://openrouter.ai/api/v1
Key: OPENROUTER_API_KEY — get one at https://openrouter.ai/settings/keys
Anthropic-format base (Claude Code’s ANTHROPIC_BASE_URL): https://openrouter.ai/api
Codex CLI: configs/codex/openrouter-free.config.toml — copy it to ~/.codex/, then codex -p openrouter-free -m recursive/flint-v1.0:free; set up on the lane by the vendor’s own page, https://openrouter.ai/docs/cookbook/coding-agents/codex-cli: “Configure Codex for OpenRouter”
Callable ids: recursive/flint-v1.0:free
What you send may be used to train or improve models unless you turn that off (the vendor’s words).

Kilo Code

🤖 Coding agents & CLIs · no card · not offered in Iran, Syria, Cuba and 1 more place · last probe 2026-11-12 · listed since 2026-11-10

Open-source coding agent with an Auto Free mode and a keyless OpenAI-compatible gateway, alongside BYOK and local models

Limits, in the vendor’s words: 200 requests/hour per IP

The free-model lineup rotates. Auto Free routes over the free models in the catalog’s autoRouting list. Other models use pay-as-you-go credits or a Kilo Pass subscription.

Base URL: https://api.kilo.ai/api/gateway
Key: none — the lane is anonymous
Codex CLI: configs/codex/kilo-code.config.toml — copy it to ~/.codex/, then codex -p kilo-code
Callable ids: openrouter/free
openrouter/free: the router chooses the model (conditions)
What you send may be used to train or improve models (the vendor’s words).

AIHubMix (free models)

🧭 Aggregators (one key, many providers) · no card · last probe 2026-11-12 · listed since 2026-11-09

OpenAI-compatible model gateway with zero-priced routes and an Anthropic-format endpoint for coding clients

Provider-wide limits

Limits, in the vendor’s words: Free IDs end in -free; paid twins are metered at list prices. The daily request and token caps are independent per account and model, rather than a pool to split across models. Published caps apply to their named model IDs; the remaining routes have no numerical budget published. Request limits and campaign durations apply to their named IDs. nemotron-3.5-content-safety-free is a classifier; the lfm-2.5-2.6b-free developer advises against agentic coding use.

Base URL: https://aihubmix.com/v1
Key: AIHUBMIX_API_KEY — get one at https://console.aihubmix.com/workspaces/default/keys
Anthropic-format base (Claude Code’s ANTHROPIC_BASE_URL): https://aihubmix.com
Codex CLI: configs/codex/aihubmix.config.toml — copy it to ~/.codex/, then codex -p aihubmix -m flint-v1.0-free; set up on the lane by the vendor’s own page, https://docs.aihubmix.com/en/api/Codex-CLI: “Connect AIHubMix in Codex (CLI and desktop app)”
Callable ids: flint-v1.0-free

Generated from registry.yaml on 2026-11-12 and re-verified twice a week; every free model on the list is at https://mvalentsev.github.io/awesome-free-ai-coding/models/, and the full list, the Atom feed and the machinery at https://github.com/mvalentsev/awesome-free-ai-coding.

Something wrong or missing? Suggest a service or a change — or read how the list works.