mirror of
https://github.com/diegosouzapw/OmniRoute.git
synced 2026-08-15 11:43:10 +03:00
docs: synchronize provider and free-tier inventories
This commit is contained in:
diegosouzapw
@@ -1,7 +1,7 @@
|
||||
---
|
||||
title: "Free Tiers & Free-Token Budget"
|
||||
version: 3.8.40
|
||||
lastUpdated: 2026-06-28
|
||||
version: 3.8.50
|
||||
lastUpdated: 2026-08-02
|
||||
---
|
||||
|
||||
# Free Tiers & Free-Token Budget
|
||||
@@ -10,6 +10,7 @@ lastUpdated: 2026-06-28
|
||||
|
||||
> **Last researched:** 2026-06-17 — per-provider web research (official docs + last-7-days news, 50-agent pass with adversarial verification) refreshing every free-tier quota + ToS.
|
||||
> **Source of truth (catalog):** `open-sse/config/freeModelCatalog.ts` (per-MODEL budgets, pool-deduped). The token-budget numbers below come from live web research and are an **approximation** — see [Methodology & caveats](#methodology--caveats).
|
||||
> **Catalog scope (2026-08-02):** OmniRoute has **327 registered providers** and **154 catalog entries marked free/no-auth**. The budget below is deliberately narrower: **43 provider pools / 522 model budget entries** with quota, credit, uncapped, keyless, or discontinued-status evidence in the free-model catalog.
|
||||
|
||||
## TL;DR — how much free inference does OmniRoute actually aggregate?
|
||||
|
||||
@@ -17,11 +18,11 @@ lastUpdated: 2026-06-28
|
||||
| ------------------------------------------- | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| **Documented recurring grant (steady)** | **~1.53B** | Free-tier **pools** (per-model catalog), each shared pool counted **once**. The live source behind `/api/free-tier/summary` and the dashboard's Free-Tier Budget page. **Use this number.** |
|
||||
| **+ first month with signup credits** | **~2.15B** | Steady + one-time signup credits (Together $25, Z.AI 20M, DeepSeek 5M, …), deduped per account. **First month only** — does not recur. |
|
||||
| **+ permanently free, no published cap** | _un-quantifiable_ | `siliconflow`, `glm-cn` (GLM-4-Flash), `tencent`, `baidu`, `kilo-gateway`, `opencode-zen` — real recurring access, rate/concurrency-limited, **no token cap to count**. Listed, never summed (counting them at `RPM×24/7` is the inflation we reject). |
|
||||
| **+ recurring access, no published cap** | _un-quantifiable_ | `siliconflow`, `glm-cn` (GLM-4-Flash), `tencent`, `baidu`, `kilo-gateway`, `opencode-zen` — currently documented recurring access, rate/concurrency-limited, **no token cap to count**. Listed, never summed (counting them at `RPM×24/7` is the inflation we reject). |
|
||||
| **+ deposit-unlock boost** | **+~24M** | A one-time **$10** OpenRouter top-up raises its free pool from 50 → 1000 req/day. Reported separately so it never inflates the steady number. |
|
||||
| Theoretical ceiling (all rate limits, 24/7) | ~10B | Sum of every provider rate limit extrapolated to non-stop use. **Not a guarantee** — do not headline this. |
|
||||
|
||||
**Honest headline:** _OmniRoute aggregates **~1.53B documented free tokens per month** (up to ~2.15B in your first month with signup credits) across 43 free-tier pools — plus a long tail of permanently-free, no-cap providers — and RTK + Caveman compression (15–95% token savings) stretches that further._
|
||||
**Honest headline:** _OmniRoute aggregates **~1.53B documented free tokens per month** (up to ~2.15B in your first month with signup credits) across 43 free-tier pools — plus a long tail of recurring, rate-limited providers without published token caps — and RTK + Caveman compression (15–95% token savings) stretches that further._
|
||||
|
||||
> **Why this dropped from the previous ~1.94B.** The 2026-06-17 refresh is an honesty correction, not a loss: `gemini` is now pool-deduped (was inflated by counting each Flash variant separately, 462M → 60M), `cloudflare-ai` corrected to its real 10k-Neurons/day (122M → 30M), `doubao` reclassified as a one-time signup credit (not recurring), and shut-down tiers removed (`github-models` closed to new signups, `chutes`/`phind`/`kluster` discontinued). Partly offset by `llm7` (correct 5M/day → 150M) and new free providers (Kilo, OpenCode Zen, Z.AI GLM-Flash).
|
||||
>
|
||||
@@ -31,7 +32,7 @@ lastUpdated: 2026-06-28
|
||||
|
||||
Biggest **documented** contributors: `mistral` 1.00B, `llm7` 150M, `groq` 117M, `gemini` 60M, `cerebras` 30M, `cloudflare-ai` 30M, `sambanova` 30M. (`longcat` is excluded — its 10M LongCat-2.0 grant is a one-time, KYC-gated signup credit, not a recurring monthly budget.)
|
||||
|
||||
> ⚠️ The theoretical ceiling (~10B) is inflated by rate-limit-only providers with **no published token cap** (`tencent`, `siliconflow`, `nvidia`, `baidu`, `glm-cn`, `sparkdesk`) whose figures would be `RPM/TPM × 24/7 × 30d` — a theoretical maximum no single account will sustain. They are **excluded** from the defensible number (shown in the "permanently free, no cap" row instead). This is the same inflation that makes competitors' multi-billion claims unreliable.
|
||||
> ⚠️ The theoretical ceiling (~10B) is inflated by rate-limit-only providers with **no published token cap** (`tencent`, `siliconflow`, `nvidia`, `baidu`, `glm-cn`, `sparkdesk`) whose figures would be `RPM/TPM × 24/7 × 30d` — a theoretical maximum no single account will sustain. They are **excluded** from the defensible number (shown in the "recurring access, no published cap" row instead). This is the same inflation that makes competitors' multi-billion claims unreliable.
|
||||
|
||||
---
|
||||
|
||||
@@ -43,8 +44,8 @@ A 50-agent web-research pass (official docs + last-7-days news, adversarially ve
|
||||
- **GitHub Models** — closed to **new** customers on 2026-06-16; existing accounts keep API/playground access, so it stays in the catalog with a note (not removed).
|
||||
- **Gemini** — `2.0 Flash` / `2.0 Flash-Lite` shut down 2026-06-01 and `2.5 Pro` left the free tier (2026-04); free tier is now **Flash-family only** (2.5/3/3.1/3.5 Flash + Gemma). The catalog now **pools** the Flash family (was inflated by counting each variant separately: 462M → 60M).
|
||||
- **Corrected numbers:** `cloudflare-ai` 122M → **30M** (real 10k-Neurons/day), `doubao` reclassified as a one-time signup credit (not recurring), `llm7` 4M → **150M** (documented 5M tokens/day), `together` "-Free" endpoints discontinued → only the **$25** signup credit remains, `longcat` Preview ended + Flash models retired → **LongCat-2.0** only, reclassified as a one-time **10M**-token signup credit (KYC-gated, not recurring).
|
||||
- **New free providers discovered:** ⭐ **Kilo Code** (`kilo-gateway` — rotating "Auto Free" set: NVIDIA Nemotron 3 family, StepFun, Poolside, Nex-N2-Pro), ⭐ **OpenCode Zen** (`opencode-zen` — 6 rotating free coding models), ⭐ **Z.AI / Zhipu** (`glm-cn` — GLM-4-Flash / 4.5-Flash / 4.7-Flash permanently free + 20M signup bonus), and `arcee-ai` Trinity Large Preview.
|
||||
- **New honest tiers** (see Methodology): a _permanently-free-but-uncapped_ category (real recurring access, no token cap to count) and a _deposit-unlock boost_ (OpenRouter $10 → +24M/mo), both surfaced **separately** so they never inflate the headline.
|
||||
- **New free providers discovered:** ⭐ **Kilo Code** (`kilo-gateway` — rotating "Auto Free" set: NVIDIA Nemotron 3 family, StepFun, Poolside, Nex-N2-Pro), ⭐ **OpenCode Zen** (`opencode-zen` — 6 rotating free coding models), ⭐ **Z.AI / Zhipu** (`glm-cn` — GLM-4-Flash / 4.5-Flash / 4.7-Flash currently listed at $0 + 20M signup bonus), and `arcee-ai` Trinity Large Preview.
|
||||
- **New honest tiers** (see Methodology): a _recurring-but-uncapped_ category (real documented access, no token cap to count) and a _deposit-unlock boost_ (OpenRouter $10 → +24M/mo), both surfaced **separately** so they never inflate the headline.
|
||||
|
||||
> The detailed per-provider table further down is the **2026-06-05 snapshot**; the deltas above supersede it. The live, canonical source is the per-model catalog `open-sse/config/freeModelCatalog.ts`.
|
||||
|
||||
@@ -55,7 +56,7 @@ A 50-agent web-research pass (official docs + last-7-days news, adversarially ve
|
||||
- Numbers are **upper-bound estimates** from each provider's documented free-tier limits as of **2026-06-17**, gathered by web research (confidence tagged per row). Free tiers change constantly — re-verify before relying on a figure.
|
||||
- `estMonthlyFreeTokens` = recurring monthly tokens only. **One-time signup credits do not recur** and count as 0. Discontinued tiers are also 0.
|
||||
- Daily token cap → `monthly = daily × 30`. Only RPD documented → `RPD × ~800 output tokens × 30`. Only RPM/TPM (no daily cap) → **uncapped** (see below).
|
||||
- **Permanently free, but no published token cap** (`siliconflow`, `glm-cn`, `tencent`, `baidu`, `kilo-gateway`, `opencode-zen`): these are real recurring free access, rate/concurrency-limited. We classify them `recurring-uncapped` and **never sum them** — multiplying `RPM × 24/7 × 30d` would produce a fantasy ceiling (the inflation we reject). They are listed so you know they exist.
|
||||
- **Recurring access, but no published token cap** (`siliconflow`, `glm-cn`, `tencent`, `baidu`, `kilo-gateway`, `opencode-zen`): these currently documented free plans are rate/concurrency-limited. We classify them `recurring-uncapped` and **never sum them** — multiplying `RPM × 24/7 × 30d` would produce a fantasy ceiling (the inflation we reject). They are listed so you know they exist.
|
||||
- **Deposit-unlock boost:** a one-time small top-up that permanently raises a free quota (OpenRouter: $10 → 1000 req/day ≈ +24M/mo). Reported as a separate figure, kept out of the steady headline.
|
||||
|
||||
---
|
||||
@@ -171,7 +172,7 @@ A 50-agent web-research pass (official docs + last-7-days news, adversarially ve
|
||||
|
||||
## Per-provider free-tier (refreshed 2026-06-17)
|
||||
|
||||
> Regenerated from the per-model catalog (`open-sse/config/freeModelCatalog.ts`), pool-deduped. Sorted by recurring steady tokens/mo. `uncapped*` = permanently free but no published token cap (rate/concurrency-limited) — real access, **not** summed into the headline. `—` = credit-only / keyless / not token-quantifiable.
|
||||
> Regenerated from the per-model catalog (`open-sse/config/freeModelCatalog.ts`), pool-deduped. Sorted by recurring steady tokens/mo. `uncapped*` = recurring access currently documented without a published token cap (rate/concurrency-limited) — real access, **not** summed into the headline. `—` = credit-only / keyless / not token-quantifiable.
|
||||
|
||||
| Provider | Free type | Steady tokens/mo | First-month credit | ToS | Models |
|
||||
| ---------------- | ------------- | ---------------- | ------------------ | --------- | ------ |
|
||||
@@ -309,21 +310,21 @@ A 50-agent web-research pass (official docs + last-7-days news, adversarially ve
|
||||
- **`predibase`** — The shipped freeNote ($25 free trial credits, 30-day validity) still matches current documentation. However, the catalog omits the concurrent 20,000 tokens/day serverless rate limit that applies duri…
|
||||
- **`publicai`** — The shipped freeNote ("Free community inference tier") is broadly accurate but understates the specificity: the 20 RPM rate limit is now documented. No major tightening found; the service remains fre…
|
||||
- **`puter`** — Partially matches: the "500+ models" count is still accurate. However "users pay via Puter account" understates the reality — free accounts receive an undocumented starting credit that can be exhaust…
|
||||
- **`qoder`** — Our catalog ships freeNote "(none)", but Qoder does have a free tier: a Community Edition with unlimited basic-model completions (daily-capped, unspecified limit) plus a one-time 14-day/300-credit Pr…
|
||||
- **`qoder`** — Our catalog ships freeNote "(none)", but Qoder does have a free tier: a Community Edition whose basic-model completions have no published total but remain daily-capped, plus a one-time 14-day/300-credit Pr…
|
||||
- **`qwen-web`** — Session-token access against chat.qwen.ai is not a dependable free-provider path and may be rejected upstream.
|
||||
- **`sambanova`** — Our shipped note only described the one-time $5 credit (30-day validity). The current reality includes a permanent recurring free tier with documented rate limits (20 RPM, 20 RPD, 200k TPD) that pers…
|
||||
- **`sambanova`** — Our shipped note only described the one-time $5 credit (30-day validity). Current documentation also describes a recurring free tier with rate limits (20 RPM, 20 RPD, 200k TPD); availability must still be re…
|
||||
- **`sensenova`** — Our shipped freeNote says "Free SenseTime models" which is vague but directionally correct — free access does exist. However, reality is more nuanced: free access is a time-limited public beta (Token…
|
||||
- **`serper-search`** — The shipped freeNote says "(none)" which is partially accurate — there is no recurring free plan — but Serper does offer 2,500 one-time trial credits on signup. The catalog note could be more precise…
|
||||
- **`siliconflow`** — Partially matches but more nuanced: the $1 free credits are a one-time trial (not recurring), while the "permanently free models" component still holds — free $0 models continue to exist (Qwen3-8B, D…
|
||||
- **`sparkdesk`** — Partially matches — the shipped freeNote "Free iFlytek Spark models" is accurate in that Spark Lite is permanently free, but understates the constraint (2 QPS per App ID) and overstates scope (only S…
|
||||
- **`siliconflow`** — Partially matches but more nuanced: the $1 free credits are a one-time trial (not recurring), while selected $0 models continue to be listed after identity verification (Qwen3-8B, D…
|
||||
- **`sparkdesk`** — Partially matches — the shipped freeNote "Free iFlytek Spark models" is accurate in that Spark Lite is currently listed at $0, but understates the constraint (2 QPS per App ID) and overstates scope (only S…
|
||||
- **`stepfun`** — The shipped freeNote "Free Step-2 models" is stale. Step-2 LLM free access is no longer offered; the platform has transitioned to Step 3.x models on a paid-per-token basis with no free LLM tier. Only…
|
||||
- **`t3-web`** — The shipped freeNote is broadly accurate (limited model access, Pro unlocks 50+ models for $8/month), but misses two key updates: (1) the free tier now resets daily instead of monthly (changed around…
|
||||
- **`tavily-search`** — Catalog ships freeNote "(none)" implying no free tier, but Tavily does in fact offer a documented recurring free tier of 1,000 credits/month with no credit card required. This is a significant discre…
|
||||
- **`tencent`** — Largely matches — the shipped freeNote ("Free Hunyuan Lite models") is accurate. Hunyuan-lite has been permanently free since May 2024 and remains so as of 2026. The catalog note undersells the detai…
|
||||
- **`tencent`** — Largely matches — the shipped freeNote ("Free Hunyuan Lite models") is accurate. Hunyuan-lite has been listed at $0 since May 2024 and remained so at the 2026 review. The catalog note undersells the detai…
|
||||
- **`theoldllm`** — Our shipped freeNote was "(none)" — this still matches in the sense that no structured API/free tier offering exists; the service remains a UI-only chat wrapper with no catalogable API tier.
|
||||
- **`together`** — The shipped note says "$25 signup credits + 3 permanently free models" but reality shows far more permanently free models (~80, not 3). The $25 trial credit figure is contested — official billing doc…
|
||||
- **`uncloseai`** — Largely matches — still free forever with no signup. However, the ToS (terms-of-use.html) clarifies IP-based throttling exists for excessive use and prohibits building competing ML services without a…
|
||||
- **`veoaifree-web`** — The shipped freeNote states "6 requests/hour" but no such explicit limit is currently documented anywhere on veoaifree.com. The site claims unlimited free generation with no login. The models listed …
|
||||
- **`together`** — The shipped note says "$25 signup credits + 3 permanently free models" but the review found far more models currently listed at $0 (~80, not 3). The $25 trial credit figure is contested — official billing doc…
|
||||
- **`uncloseai`** — Largely matches — the site still advertises free access without signup as of the review. However, the ToS (terms-of-use.html) clarifies IP-based throttling exists for excessive use and prohibits building competing ML services without a…
|
||||
- **`veoaifree-web`** — The shipped freeNote states "6 requests/hour" but no such explicit limit is currently documented anywhere on veoaifree.com. The site advertises no-login generation without a published cap; actual throttling and availability may differ. The models listed …
|
||||
- **`voyage-ai`** — The shipped freeNote "200M free tokens for embeddings and reranking" is directionally correct on the token count but misleading — it omits that this is a one-time per-account allocation, not a recurr…
|
||||
- **`yi`** — The shipped freeNote "Free Yi-Light models" references a model name ("Yi-Light") that does not appear in any current 01.AI documentation or model catalog — no such model is listed on platform.01.ai, …
|
||||
|
||||
|
||||
Reference in New Issue
Block a user