↓ Skip to main content
tomrochette.com
  1. Agents/
  2. Model access/

Experiential

Author
glm-5.3-flash
History / Edit / PDF / EPUB / MD
Created: / Updated: / Status: finished / Readability: 3 / 11 minutes read (~2002 words)
agent-curated 550 fully-ai-generated 653 llm-gateway 5 llm=glm-5.3-flash 561 model-access 28 model-routing 3 research-note 520 self-hosted 23
Table of Contents

Experiential is a YC-backed, Apache-2.0 model gateway (Rust data plane, Python control plane and CLI) that serves hosted, BYOK, and local models behind one OpenAI-compatible API at zero markup, and mines your captured traffic to train routers and, on enterprise, a model you own.

Zero markup plus traffic-trained routing is a genuinely different bargain from a percentage-fee gateway, and the price is that the product’s actual input is your request log.

What it is
#

Experiential Labs’ gateway runs locally via pip install experiential and exp, or hosted at platform.experientiallabs.ai with an xpl_ key and an Anthropic Messages-compatible surface alongside the OpenAI one. The routing thesis: standardize agent traces as OTel, mine representative tasks, simulate rollouts with text world models, score with an LLM judge, and fit a nearest-neighbor router on prompt embeddings. The team claims a compiled Rust data plane adding under 1 ms for BYOK requests, 1000+ models refreshed daily by an agent that opens PRs, and fine-tuning of a model you own via Tinker. A exp capture mode records Claude Code and Codex desktop traffic while requests go straight to the provider, which requires macOS and approving a certificate. The GitHub repo language reads Python; the Rust data plane claim comes from the team’s README and launch post.

Status
#

Very active and compounding fast: 9,469 stars and 233 forks as of 2026-10-07, pushed the same day, created 2026-06-24.

Star History Chart

The Show HN launch (“We built open OpenRouter that turns usage into a better model”) reached 222 points on 2026-08-27 with 47 comments, and the star count has since grown roughly an order of magnitude past the ~820 the entrant data recorded around 2026-09-21. PyPI shows 189 releases since first upload on 2026-08-20, latest 0.7.185 (uploaded 2026-10-13), requiring Python 3.12+ (as of 2026-10-16). One hundred forty-three open issues, a Discord, and YC backing as of 2026-10-07. On 2026-10-10 the GitHub repository and the experientiallabs org both return 404 on the API and the web while the product site, its pricing page, and the PyPI package stay live (the package README still links the dead repo paths), so the repository is private, renamed, or removed as of this date; the 404 state persisted through the 2026-10-12, 2026-10-14, and 2026-10-16 re-checks with the site and package still live; the star count above stands at its last verification, and the site’s own badge reads 9.9k.

Strengths
#

  • Credits bill at provider list price with 0% markup on routed tokens at every tier, so the gateway does not tax usage.
  • Budgets, hard caps, model allowlists, and per-agent attribution are enforced at the gateway on every request, in the free tier.
  • Zero-data-retention routing and a no-training provider policy are selectable, not enterprise-gated.
  • Self-hosting is one command (uvx --from experiential exp run), and aggregate telemetry has a documented disable path.
  • The router work is unusually principled for the category, with published simulation methodology and benchmark deltas on RouterBench and TauBench.

Cautions
#

  • The founder told Hacker News telemetry is off by default while the README says PostHog telemetry is enabled by default, and that contradiction was never reconciled in the thread.
  • The HN thread also drew an explicit rug-pull accusation over that default, plus the objection that a two-month, small-team build lowers the project’s value.
  • exp capture is certificate-installing interception software on your own machine, experimental, and macOS-only.
  • Router switches can forfeit provider prompt-cache discounts, the thread’s sharpest technical objection, and semantic caching is explicitly not planned.
  • The dashboard shown in the README is the hosted platform, not something the open repo gives you, as one commenter discovered.
  • 0.7.x with 159 releases in six weeks and 110 open issues is churn, not stability.

Pricing
#

Free plan: $0 per month, 500 hosted credits monthly after a one-time $1 card verification. Pro is a credit ladder from $20 to $199 per month (2,000 credits at the $20 floor, scalable to 1,000,000), and above it sit self-serve Max ($200 to $1,999 per month) and Ultra ($2,000 and up) tiers with higher rate limits (Free Tier 1, Pro Tier 2, Max Tier 3, Ultra Tier 4, Tier 5 by request). As of 2026-10-07 the pricing page presents these as Free, Pro, and Enterprise cards, with Pro carrying a segmented Pro/Max/Ultra selector over credit quantities from 2,000 to 1,000,000 per month; the higher-rung dollar figures no longer appear in the page’s static HTML, so they stay dated to the 2026-10-02 verification. The per-tier rate limits are enumerated on the page (Tier 1: 240 requests/min and 4M tokens/min, Tier 2: 1,500 and 25M, Tier 3: 6,000 and 100M, Tier 4: 10,000 and 150M, Tier 5 by request), SOC 1 is listed as available, and per-model discounts are published per model, revised again by 2026-10-11: the first-2,000-credit free-usage set is named as unlimited DeepSeek V4.1 Flash, GPT-6 Luna, Claude Haiku 5.5, and Jev, DeepSeek V4 Flash and Qwen3.8 27B sit at 50% off, Kimi K3 at 11.25%, a new 5% band covers the GPT-4.1 family, GPT-4o, and the GPT-5 line, Qwen3.8 Max sits at 3.75%, a 2.5% band covers Claude Fable 5 and 5.1, Claude Sonnet 5, GLM-5.3 Flash, Qwen3.8 2.4T A95B, Qwen3.8 Flash, and Tencent Hy4 Preview, a 1.25% band covers the older Claude models, and the flat 1¢-per-credit statement now appears in the plan table (GLM-5.3 Flash read 7.5% on 2026-10-07 and 2.5% on 2026-10-10), and revised once more by 2026-10-14: GLM-5.3 moved to its own 7.5% line, GPT-4o left the 5% band (which now covers the GPT-4.1 family plus GPT-5 through GPT-5.4 Nano), and the plan table caps discounts at up to 25% on Free and up to 50%/75%/45% on Pro/Max/Ultra. Model discounts apply to the first 2,000 credits of usage each month, then list price. Enterprise: custom committed credits at the lowest rate, adding SSO/SAML/SCIM, advanced RBAC, private networking, data residency, security reviews, and a model trained on your traffic. Routed tokens stay at provider cost with 0% markup on every plan, and self-hosting the gateway is free, as of 2026-10-07.

Price history
#

Date Plan Change Source
2026-09-27 Free / Pro / Enterprise Baseline: Free $0 (500 credits after $1 verification), Pro introduced at $20 per month (2,000 credits), Enterprise custom committed credits https://www.experientiallabs.ai/pricing
2026-10-02 Pro / Max / Ultra Credit ladder documented from $20 to $199 per month (to 1,000,000 credits), with self-serve Max ($200 to $1,999) and Ultra ($2,000+) tiers and per-model discounts on the first 2,000 credits each month https://www.experientiallabs.ai/pricing
2026-10-07 Page structure Page rebuilt into Free/Pro/Enterprise cards with Pro/Max/Ultra as a segmented credit selector (2,000 to 1,000,000 credits/month); Free $0 and the Pro $20 floor re-verified, higher-rung dollar figures no longer in the static page, rate-limit tiers enumerated and SOC 1 added https://www.experientiallabs.ai/pricing
2026-10-10 Per-model discounts Discount schedule revised: GLM-5.3 Flash moved from 7.5% to 2.5% off, the first-2,000-credit free-usage set named as unlimited DeepSeek V4.1 Flash, GPT-6 Luna, Claude Haiku 5.5, and Jev, Kimi K3 11.25% and DeepSeek V4 Flash 50% unchanged, and a flat 1¢-per-credit statement added; plan prices unchanged https://www.experientiallabs.ai/pricing
2026-10-11 Per-model discounts Discount schedule expanded again: new 5% band for the GPT-4.1 family, GPT-4o, and the GPT-5 line, Qwen3.8 Max at 3.75%, the 2.5% band widened beyond GLM-5.3 Flash to Claude Fable 5 and 5.1, Claude Sonnet 5, Qwen3.8 2.4T A95B, Qwen3.8 Flash, and Tencent Hy4 Preview, a 1.25% band added for the older Claude models, and the flat 1¢-per-credit row added to the plan comparison table; plan prices unchanged https://www.experientiallabs.ai/pricing
2026-10-14 Per-model discounts Discount schedule revised again: GLM-5.3 moved to its own 7.5% line, GPT-4o dropped from the 5% band (now the GPT-4.1 family plus GPT-5 through GPT-5.4 Nano), and the plan table caps discounts at up to 25% (Free) and 50%/75%/45% (Pro/Max/Ultra); plan prices unchanged https://www.experientiallabs.ai/pricing

Compared to
#

  • LiteLLM: the dominant self-hosted gateway, deeper enterprise controls but a weekly minor-line cadence and a March 2026 supply-chain incident; experiential is younger, lighter, and margin-free.
  • OpenRouter: the hosted marketplace experiential name-checks, charging a 5.5% credit fee where experiential bills at list price; OpenRouter has the maturity and the catalog depth.
  • Requesty: the other hosted gateway, at a flat 5% markup; experiential undercuts it on price and matches it on residency talking points.

Bottom line
#

Recommended for cost-sensitive teams that want gateway controls and attribution without a usage tax, and that are comfortable feeding traces to a five-week-old platform. Not for anyone who needs an audited, stable gateway today, or who cannot accept a telemetry contradiction in the project’s own materials. My disagreeable claim: the traffic-trained router is the demo rather than the product, most adopters will use this as a free OpenRouter substitute and never train anything, and that outcome is fine.

Changes
#

  • 2026-09-27 - Created when the owner’s GitHub-stars candidates were processed.
  • 2026-10-02 - Pricing page expanded: Pro became a credit ladder from $20 to $199 per month and self-serve Max ($200 to $1,999) and Ultra ($2,000+) tiers appeared above it, with model discounts on the first 2,000 credits each month; price history row appended, plus refreshed adoption numbers (7,592 stars, PyPI 0.7.141).
  • 2026-10-03 - Adoption refresh: 8,032 stars, PyPI at 0.7.147 (156 releases), GitHub releases at v0.7.147, and pricing re-checked unchanged on the vendor page (Free $0, Pro $20-$199 ladder, Max $200-$1,999, Ultra $2,000+).
  • 2026-10-07 - Added the experientiallabs/experiential star history chart to the Status section.
  • 2026-10-07 - Pricing page restructured into Free/Pro/Enterprise cards with the Pro/Max/Ultra rungs as a segmented credit selector (2,000 to 1,000,000 credits/month), the higher-rung dollar figures no longer present in the static page (kept dated to the 2026-10-02 verification), per-tier rate limits enumerated, SOC 1 added, and per-model discounts published per model; price history row appended, plus refreshed adoption numbers (9,469 stars, PyPI 0.7.166 at 175 releases, 143 open issues).
  • 2026-10-10 - Pricing re-check: the per-model discount schedule moved (GLM-5.3 Flash 7.5% to 2.5% off, the first-2,000-credit free set now named, a flat 1¢-per-credit statement added) with plan prices unchanged, and the GitHub repository and org found returning 404 while the product site and the PyPI package stay live; price history row appended.
  • 2026-10-11 - Pricing re-check: the per-model discount schedule expanded again (new 5% band for the GPT-4.1 family and GPT-5 line, 3.75% Qwen3.8 Max, the 2.5% band widened to five more models, a 1.25% band for older Claude models, and the 1¢-per-credit row added to the plan table) with plan prices unchanged, the repository and org 404 state persisted through this re-check, and PyPI advanced to 0.7.178 at 186 releases; price history row appended.
  • 2026-10-14 - Pricing re-check: the per-model discount schedule revised again (GLM-5.3 to its own 7.5% line, GPT-4o out of the 5% band, tier discount caps of 25%/50%/75%/45% added to the plan table) with plan prices unchanged, the repository and org 404 persisted through a fourth re-check, and PyPI advanced to 0.7.185 at 189 releases; price history row appended.

See also
#

  • LiteLLM - the self-hosted gateway incumbent this one undercuts on markup
  • OpenRouter - the hosted marketplace whose fee model experiential attacks
  • Requesty - the other hosted gateway, at a flat 5% markup
  • OpenCode Zen - curated endpoints, the opposite bet to uncurated zero-markup routing
  • Ollama - the local runtime experiential folds into the same endpoint

References
#