cd /news/large-language-models/flint-is-an-open-weight-mixture-of-e… · home › topics › large-language-models › article
[ARTICLE · art-158349] src=openrouter.ai ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Flint is an open-weight mixture-of-experts model from Recursive

Recursive released Flint, an open-weight mixture-of-experts model with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. Flint is hosted by a single provider through OpenRouter, carries a 262,144-token context window, supports tool calling and JSON output via response_format without JSON-schema enforcement, and is offered free with rate limits. OpenRouter reports 100.00% uptime and 99.67% availability over the past 3 days for the model, which is aimed at investigating codebases, fixing bugs, implementing features, and writing tests.

by read3 min views3 publishedOct 26, 2026
Flint is an open-weight mixture-of-experts model from Recursive
Image: source

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited for investigating codebases, fixing bugs, implementing features, and writing tests.

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.67%

Availability over the last 3 days

Last 72 hours

Availability 99.67%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.67%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

OpenClaw is an open-source AI agent that connects to your messaging apps and takes real actions on your behalf, from running commands and browsing the web to managing files and sending emails.

There are many coding agents, but this one is yours.

4.43Btokens

Frequently asked questions

What is Flint (free)? Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited for investigating codebases, fixing bugs, implementing features, and writing tests.

Is Flint (free) free? Yes. The pricing shown on this page for Flint (free) is zero, so you are not charged for prompt or completion tokens. Free endpoints are rate limited — see the rate limit docs.

What is the context length of Flint (free)?

Flint (free) has a 262,144 token context window.

Does Flint (free) support tool calling and structured outputs?

Yes. Flint (free) accepts tools for function calling. It supports response_format for JSON output, without JSON-schema enforcement.

── more in #large-language-models 4 stories · sorted by recency
── more on @recursive 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/flint-is-an-open-wei…] indexed:0 read:3min 2026-10-26 · —