Model Guide
Agnes 2.5 Flash: The New Free Coding Model, on OpenClaw Launch
Agnes 2.5 Flash is the newest flagship model from Agnes AI (Sapiens AI) — a major step up from Agnes 2.0 Flash on coding, multi-step agent tasks, and reasoning, benchmarked comparable to Claude Opus 4.7, and free indefinitely. This guide covers what changed and how to run it on your OpenClaw Launch instances the moment the Agnes API opens it up.
What Is Agnes 2.5 Flash?
Agnes 2.5 Flash is the successor to agnes-2.0-flash, the free multimodal model already available on OpenClaw Launch through the Agnes API key integration. Agnes AI positions 2.5 Flash as the model built for everyday developer use — coding, agent workflows, and complex development scenarios — and reports significant gains over 2.0 in four areas:
- Code comprehension across large, unfamiliar codebases
- Bug detection and engineering fixes in existing projects
- Multi-step, cross-file task execution
- Complex reasoning
In Agnes AI’s own demonstrations, 2.5 Flash detects and fixes bugs in existing codebases, builds full applications from scratch, and makes coordinated cross-file edits — with results the company describes as competitive with Claude Opus 4.7. Like the rest of the Agnes lineup, it keeps a large 256K token context window and speaks the standard OpenAI-compatible chat format, so nothing in your OpenClaw setup needs to change to use it.
Is It Really Free?
Yes. Agnes AI has committed to keeping Agnes 2.5 Flash free indefinitely (“不限期免费”). There is no per-request charge, no credit card, and no published hard quota — the same terms that made 2.0 Flash a popular free default. Agnes is also previewing a premium tier, Agnes 2.5 Pro, aimed at heavier enterprise workloads (pricing still to be announced), alongside the Agnes Code desktop IDE. For agent hosting on OpenClaw Launch, the free 2.5 Flash is the relevant one.
Rollout status (as of this writing)
Agnes 2.5 Flash is rolling out first in the Agnes Code desktop app, with full API access arriving shortly. OpenClaw Launch routes your bot’s chat through the Agnes OpenAI-compatible API, so until Agnes flips 2.5 on for the API, the working free model to select today is still agnes-2.0-flash. You do not need to do anything to switch: the moment the Agnes API starts serving agnes-2.5-flash, it appears automatically in your model picker and becomes the suggested default for new Agnes-funded deploys — no redeploy required.
How to Use Agnes 2.5 Flash on OpenClaw Launch
The setup is the same free Agnes key that already unlocks 2.0 Flash. Once you have it saved, upgrading is a one-click model switch as soon as 2.5 is live.
- Get a free Agnes key — Sign up at platform.agnes-ai.com (no card required) and create an API key. Agnes keys start with
sk-. Full walkthrough: the Agnes API key setup guide. - Save it on OpenClaw Launch — Open the API Keys page, find the Agnes card, paste your
sk-key, and click Save. We validate it against the Agnes API before storing, and it is encrypted at rest. - Set your chat model — In the Agnes card, click “Set as primary model” and pick the newest Agnes model offered. Today that is
agnes-2.0-flash; as soon as the API serves it,agnes-2.5-flashshows up in the same dropdown as the suggested option. Applying it takes effect on your running instances immediately — no redeploy.
This works for both frameworks. On OpenClaw, the model routes directly through your declared Agnes provider; on Hermes Agent, the same key is wired into the custom-provider slot at model-switch time. Either way you are on the free Agnes gateway with your own key.
Should You Switch From 2.0 to 2.5?
For coding and agent work, yes — that is exactly the workload Agnes 2.5 Flash was built to improve, and it is the same price ($0). If your bot mostly does lightweight chat, 2.0 Flash remains perfectly capable and stays available. Because switching is a one-click model change with no redeploy and no cost, the low-risk move is to try 2.5 on your instance the day it goes live and keep it if you like the results.
Troubleshooting
I don’t see agnes-2.5-flash in my model picker yet
- The Agnes API has not started serving it yet. OpenClaw Launch only lists Agnes models that the live Agnes catalog actually serves, so you never select an id that would return a 404. Keep using
agnes-2.0-flashand 2.5 will appear automatically once the API opens it. - Make sure your Agnes key is saved and confirmed on the API Keys page — the Agnes section only shows once a valid key is on file.
Model Not Found (404)
- If you set the model id by hand (for example via
/modelin chat) before the API is live, Agnes returnsmodel_not_found. Use the model picker instead of typing the id — it only offers what is currently available.
401 Unauthorized
- Confirm the key starts with
sk-and has no stray spaces or newlines. Regenerate it on the Agnes dashboard and re-save if needed.
Frequently Asked Questions
What is Agnes 2.5 Flash?
Agnes 2.5 Flash is Agnes AI’s newest free flagship model, the successor to Agnes 2.0 Flash. It delivers significant improvements in code comprehension, engineering fixes, multi-step task execution, and complex reasoning, with performance Agnes describes as comparable to Claude Opus 4.7. It is free indefinitely and keeps a 256K token context window.
Is Agnes 2.5 Flash free?
Yes. Agnes AI has committed to keeping Agnes 2.5 Flash free indefinitely — no per-request cost and no credit card required. A separate premium tier, Agnes 2.5 Pro, is aimed at heavier enterprise use, with pricing yet to be announced.
Can I use Agnes 2.5 Flash on OpenClaw Launch right now?
It is rolling out. Agnes 2.5 Flash is live first in the Agnes Code desktop app, with API access arriving shortly. OpenClaw Launch talks to Agnes through its API, so the model becomes selectable on your instance the moment the Agnes API serves it — automatically, with no redeploy. Until then, agnes-2.0-flash is the free Agnes model to use.
How is Agnes 2.5 Flash different from 2.0 Flash?
2.5 Flash is a substantial upgrade focused on development work: better code understanding, stronger bug-fixing on existing projects, more reliable multi-step and cross-file execution, and improved complex reasoning. Both are free and share the same OpenAI-compatible API and 256K context, so switching is a one-click model change.
Does it work with Hermes Agent too?
Yes. The same free Agnes key works on both OpenClaw and Hermes Agent instances. Save your key once and pick the Agnes model from the picker on either framework.
What's Next?
- Agnes API key setup on OpenClaw — The full step-by-step for getting and saving your free Agnes key
- Agnes on Hermes Agent — Same free key, set up for Hermes Agent instances
- AI coding plans compared — How free models like Agnes stack up against paid coding plans
- API Keys page — Add or manage all your provider keys in one place