Langfuse 4.75.0 released
A feature release that raises AI Gateway rate limits, improves Codex setup, and adds gateway member analytics with various bug fixes.
What changed in 4.75.0
- AI Gateway rate limits increased to 10k requests per minute and 5 GiB per minute for Pro, Team, and Enterprise plans.
- Codex setup simplified to use an exported key and config.toml file.
- Gateway members can now view analytics of their own usage.
- Multiple UI improvements including gateway provider models table layout, organization settings visibility, and dialog handling.
- Performance improvements to image sizes, session aggregation, and event processing throttling response.
Summarised by AgentGid from Langfuse's official release notes on GitHub, as reported there; read the original before relying on it. Price, status and release dates come from our daily data.
Langfuse at a glance
| What it is | An open-source platform for tracing, evaluating and debugging LLM apps and agents: every model and tool call with its cost and latency, prompt management, datasets and evaluations. |
|---|---|
| Latest version | 4.82.0, Nov 17, 2026. This page is about an earlier release. |
| Release pace | 25 stable releases in the last 30 days; 4.75.0 came 1 day after the previous one |
| Price | Free + $29/mo. Free to self-host. Langfuse Cloud has a free Hobby tier (50k units/month), Core at $29/month (100k units/month), Pro at $199/month (100k units/month) with optional Teams add-on at… Official pricing ↗ (checked Nov 6, 2026) |
| Live status | Up 4 incidents in the last 30 days on the official status page |
| Downloads, last 7 days | 14.7M up 0.7% |
| Gid Score | 69 #2 in Agent tooling for cost, context and memory |
Langfuse overview Monthly changelogIs Langfuse down?Alternatives