free-coding-models 0.5.97 → 0.5.99

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (8) hide show
  1. package/README.md +12 -12
  2. package/changelog/v0.5.98.md +39 -0
  3. package/changelog/v0.5.99.md +17 -0
  4. package/package.json +1 -1
  5. package/sources.js +159 -110
  6. package/web/dist/assets/index-Zr5Q6fX9.js +45 -0
  7. package/web/dist/index.html +1 -1
  8. package/web/dist/assets/index-C2lIYp0O.js +0 -45
package/sources.js CHANGED
@@ -49,9 +49,11 @@ export const nvidiaNim = [
49
49
  // Removed (2026-09-05): moonshotai/kimi-k2.6 (Kimi K2.6) - Model page returns 404 and model is absent from the NVIDIA model catalog; could not verify existence
50
50
  // Removed (2026-08-30): deepseek-ai/deepseek-v4-pro (DeepSeek V4 Pro) — 410 Gone per NVIDIA NIM forum; replaced by deepseek-v4-flash:0731 (forums.developer.nvidia.com/t/deepseek-v4-pro-flash-removed/379558)
51
51
  // Removed (2026-09-21): deepseek-ai/deepseek-v4-flash-0731 (DeepSeek V4 Flash) — NVIDIA deprecation banner on the model page: deprecated 2026-09-19, no longer supported after 2026-09-21; DeepSeek retired V4 Flash in favor of V4.1 Flash (not registered on NIM)
52
- ['moonshotai/kimi-k3', 'Kimi K3', 'S+', '76.8%', '1M'], // Fixed (2026-09-21): tier 'S' → 'S+' + sweScore '-' → '76.8%' (tracker-sourced SWE-bench Verified; 76.8% is S+ on the documented scale)
52
+ // Removed (2026-10-17 audit): moonshotai/kimi-k3 (Kimi K3) — officially deprecated on the NIM model card (deprecated 2026-10-14, unsupported after 2026-10-15) and absent from /v1/models; no Moonshot model remains usable on NIM (kimi-k2.6 endpoint was shut down 2026-07-07 and its catalog page 404s)
53
53
  ['z-ai/glm-5.3-flash', 'GLM-5.3-Flash', 'S+', '-', '1M'], // Added (2026-09-22) — live on NIM /v1/models (needed a 230s cold start on first probe)
54
54
  ['z-ai/glm-5.3', 'GLM 5.3', 'S+', '-', '1M'], // Fixed (2026-09-29 audit): ctx '200k' → '1M' (NVIDIA docs state 1,048,576 tokens)
55
+ ['nvidia/nemotron-3.5-super-vl-120b-a12b', 'Nemotron 3.5 Super VL', 'S+', '71.07%', '262k'], // Added (2026-10-17 audit) — new hosted model, live on /v1/models + build.nvidia.com; multimodal 120B/12B MoE, SWE-bench Verified 71.07% per the NVIDIA model card
56
+ ['stepfun-ai/step-5-preview', 'Step 5 Preview', 'S', '-', '1M'], // Added (2026-10-17 audit) — new StepFun flagship preview (600B/27B-active MoE), live on /v1/models, 1M ctx; mirrors the Step 5 rollout on other gateways
55
57
  // Removed (2026-09-28 audit re-check): deepseek-ai/deepseek-v4-pro, deepseek-ai/deepseek-v4-flash-0731, minimaxai/minimax-m2.7, stepfun-ai/step-3.7-flash, nvidia/nemotron-3-nano-30b-a3b re-appear in the public catalog but were all probed 410/404 here 2026-09-05..21 — ghost catalog entries again, still excluded (issue #181 policy)
56
58
  // Removed (2026-08-30): stepfun-ai/step-3.7-flash (Step 3.7 Flash) — 410 Gone per NVIDIA NIM TUI ping (no replacement listed; superseded by step-3.7-flash via Routeway `step-3.7-flash:free`)
57
59
  ['nvidia/nemotron-3-ultra-550b-a55b', 'Nemotron 3 Ultra', 'S+', '71.9%', '1M'],
@@ -66,7 +68,7 @@ export const nvidiaNim = [
66
68
  // Removed (2026-09-09): minimaxai/minimax-m3 (MiniMax M3) - 410 Gone per live chat probe: reached end of life 2026-09-09T09:00:00Z (shutdown was announced in-file on 2026-09-08)
67
69
  // Removed (2026-09-29 audit): mistralai/mistral-nemotron (Mistral Nemotron) — 410 Gone on live probe: end of life 2026-09-28T08:00:00Z
68
70
  // Removed (2026-09-29 audit): moonshotai/kimi-k2-thinking (Kimi K2 Thinking) — 410 Gone on live probe: end of life 2026-05-12T00:00:00Z; replaced by moonshotai/kimi-k2.6 (re-added below)
69
- ['moonshotai/kimi-k2.6', 'Kimi K2.6', 'S+', '80.2%', '256k'], // Re-added (2026-09-29 audit) — servable again on NIM (listed + chat probe 401 = alive); ctx 256k per NVIDIA API reference; tier/score match kimi-k2.6 on onomeo
71
+ // Removed (2026-10-10 audit): moonshotai/kimi-k2.6 (Kimi K2.6) — catalog page 404 again and absent from the build.nvidia.com hosted list; only a stale entry lingers in the public /v1/models union. The 2026-09-29 "listed + 401 probe" re-add was the weak signal; page 404 is authoritative (same evidence pattern as the 2026-09-05 removal). Replacement: moonshotai/kimi-k3
70
72
  // Removed (2026-07-27): deepseek-ai/deepseek-v3.2 (DeepSeek V3.2) — HTTP 404
71
73
  // Removed (2026-09-21): qwen/qwen3-coder-480b-a35b-instruct (Qwen3 Coder 480B) — 410 Gone on live probe: end of life 2026-06-11; the 2026-09-15 re-add was erroneous (model was never alive on NIM in September). Free 480B coder is still on DashScope as qwen3-coder-480b-a35b-instruct
72
74
  // ── A+ tier — SWE-bench Verified 50–60% ──
@@ -80,8 +82,8 @@ export const nvidiaNim = [
80
82
  // ── A tier — SWE-bench Verified 40–50% ──
81
83
  // Removed (2026-09-05): nvidia/nemotron-nano-3-30b-a3b (Nemotron Nano 30B) - Model page returns 404 and model is absent from the NVIDIA model catalog; superseded by Nemotron 3.5 Lightning
82
84
  ['deepseek-ai/deepseek-v4.1-flash', 'DeepSeek V4.1 Flash', 'S+', '-', '1M'], // Added (2026-09-29 audit) — live on NIM, 552B/8B-active MoE, ctx 1M per NVIDIA docs; DeepSWE v1.1 74.2 + Terminal-Bench 2.1 90.6, no published SWE-bench Verified (score '-' pending)
83
- ['nvidia/nemotron-nano-3-30b-a3b', 'Nemotron Nano 3 30B', 'A', '-', '-'], // Re-added (2026-09-29 audit) — servable again on NIM (listed + chat probe 401 = alive), no NVIDIA docs page so ctx unverified
84
- ['mistralai/codestral-22b-instruct-v0.1', 'Codestral 22B', 'A', '-', '-'], // Re-added (2026-09-29 audit) — servable again on NIM (listed + chat probe 401 = alive); previously 404 on 2026-08-30; ctx unverified
85
+ // Removed (2026-10-10 audit): nvidia/nemotron-nano-3-30b-a3b (Nemotron Nano 3 30B) — catalog page 404 under every id variant, absent from the hosted list; replaced in the 30B A3B class by nemotron-3.5-lightning. 2026-09-29 re-add reversed (same ghost-entry pattern as issue #181)
86
+ // Removed (2026-10-10 audit): mistralai/codestral-22b-instruct-v0.1 (Codestral 22B) — catalog page 404, old v0.1 retired from NIM, no newer Codestral hosted; use Codestral `codestral-2508` via Mistral LP
85
87
  ['openai/gpt-oss-20b', 'GPT OSS 20B', 'A+', '50.3%', '131k'], // Fixed (2026-09-29 audit): ctx '128k' → '131k' (official contextLength 131072)
86
88
  ['google/gemma-4-31b-it', 'Gemma 4 31B', 'A+', '52.0%', '262k'], // Fixed (2026-09-21): ctx '256k' → '262k' (official contextLength 262144)
87
89
  // Removed (2026-08-30): mistralai/mistral-large-2-instruct (Mistral Large 2) — 404 NOT FOUND per NVIDIA NIM TUI ping (model not in NIM catalog; use Mistral LP `mistral-large-2512`)
@@ -141,8 +143,7 @@ export const cerebras = [
141
143
  // 📖 Keep this catalog conservative: only models surfaced in current SambaNova docs.
142
144
  export const sambanova = [
143
145
  // ── S+ tier ──
144
- ['MiniMax-M2.7', 'MiniMax M2.7', 'S+', '78.0%', '192k'], // Fixed (2026-09-28 audit): ctx '196k' → '192k' per official docs
145
- ['MiniMax-M3', 'MiniMax M3', 'S+', '78.4%', '1M'], // Added (2026-09-02) — verified live 2026-09-05 via /v1/models
146
+ // Removed (2026-10-10 audit): MiniMax-M2.7 + MiniMax-M3 — the official Free Tier rate-limit table now covers only 5 models (DeepSeek-V3.1/V3.2, gpt-oss-120b, gemma-4-31B-it, Llama 3.3 70B); both MiniMax require the Developer Tier with a linked payment method. Reverses the 2026-09-02/09-28 free reads
146
147
  // ── S tier ──
147
148
  ['DeepSeek-V3.1', 'DeepSeek V3.1', 'S', '66.0%', '131k'], // Fixed (2026-07-27): ctx '128k' → '131k' (API exact 131072)
148
149
  ['DeepSeek-V3.2', 'DeepSeek V3.2', 'S+', '70.0%', '32k'],
@@ -169,15 +170,18 @@ export const openrouter = [
169
170
  ['nvidia/nemotron-3-ultra-550b-a55b:free', 'Nemotron 3 Ultra', 'S+', '71.9%', '1M'],
170
171
  ['poolside/laguna-xs-2.1:free', 'Poolside Laguna XS 2.1', 'S+', '70.9%', '262k'],
171
172
  ['poolside/laguna-s-2.1:free', 'Poolside Laguna S 2.1', 'S+', '-', '262k'],
173
+ ['xingchen-agi/xing4.0-29b-a4b:free', 'Xing4.0 29B A4B', 'S+', '75.0%', '262k'], // Added (2026-10-17 audit) — new :free entry (TeleAI Xing4.0 agentic coder, SWE-bench Verified 75.0% per the published model card)
172
174
  // Removed (2026-09-15): minimax/minimax-m2.7:free (MiniMax M2.7) — no longer free on OpenRouter
173
175
  // Removed (2026-09-15): minimax/minimax-m3:free (MiniMax M3) — no longer free on OpenRouter
174
176
  // Removed (2026-09-28 audit): z-ai/glm-5.2:free (GLM-5.2) — gone from the live :free catalog (now paid-only)
175
177
  // ── S tier — SWE-bench Verified 60–70% ──
176
178
  ['cohere/north-mini-code:free', 'North Mini Code', 'S', '-', '256k'],
177
179
  ['nvidia/nemotron-3-super-120b-a12b:free', 'Nemotron 3 Super', 'S', '60.5%', '262k'],
178
- ['qwen/qwen3.8-27b:free', 'Qwen3.8 27B', 'S', '-', '262k'], // Added (2026-09-21) — new in the live :free catalog
180
+ // Removed (2026-10-17 audit): inclusionai/ling-3.1-flash (Ling 3.1 Flash) — no longer $0/$0: now bills $0.075/M in + $0.225/M out with no :free variant; reverses the 2026-10-10 add
181
+ // Removed (2026-10-10 audit): qwen/qwen3.8-27b:free (Qwen3.8 27B) — deleted from the live :free catalog (Kilo mirror dropped it the same day); no free Qwen replacement
179
182
  // ── A+ tier — SWE-bench Verified 50–60% ──
180
183
  ['nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free', 'Nemotron 3 Omni', 'A+', '52.0%', '256k'],
184
+ ['nvidia/nemotron-3.5-super-vl:free', 'Nemotron 3.5 Super VL', 'S+', '71.1%', '1M'], // Added (2026-10-17 audit) — new :free entry, 1M ctx per the live API; SWE score follows the same model on NVIDIA NIM (71.07% rounded per family reads), S+ on the documented scale
181
185
  ['google/gemma-4-31b-it:free', 'Gemma 4 31B', 'A+', '52.0%', '262k'],
182
186
  ['google/gemma-4-26b-a4b-it:free', 'Gemma 4 26B MoE', 'A', '38.0%', '262k'],
183
187
  // Removed (2026-09-28 audit): nex-agi/nex-n2.5-pro:free — nex-agi dropped from the live :free catalog entirely
@@ -186,8 +190,9 @@ export const openrouter = [
186
190
  ['nvidia/nemotron-3.5-lightning:free', 'NVIDIA Nemotron 3.5 Lightning', 'B+', '-', '1M'],
187
191
  // Removed (2026-09-29 audit): inclusionai/ling-3.0-flash-fin:free — :free variant gone from the live catalog, base id now bills $0.06/M prompt; replacement: inclusionai/ling-3.0-flash-sante:free
188
192
  ['thinkingmachines/inkling:free', 'Inkling', 'B+', '-', '1M'], // Added (2026-09-02)
189
- ['inclusionai/ling-3.0-flash-sante:free', 'Ling 3.0 Flash Sante', 'B+', '-', '262k'],
190
- ['stealth/space-bunny-alpha', 'Space Bunny Alpha', 'A', '-', '1M'], // Added (2026-09-29 audit) — anonymous stealth model, $0/$0 pricing, 1M ctx, strong-coding claim per OpenRouter description
193
+ // Removed (2026-10-10 audit): inclusionai/ling-3.0-flash-sante:free — :free variant removed, base id now bills per-token; replacement: inclusionai/ling-3.1-flash ($0/$0)
194
+ // Removed (2026-10-10 audit): stealth/space-bunny-alpha — stealth preview rotated out of the live list, no stealth model currently live (next stealth slot: glyph-cluster on Kilo/Vercel)
195
+ // Removed (2026-10-17 audit): apodex/apodex-1.1-mini:free — delisted from OpenRouter entirely (no free or paid listing in the live API); the model moved to Novita as a zero-price partner launch
191
196
  ['openrouter/free', 'Free Models Router', 'A', '-', '200k'], // Added (2026-09-29 audit) — OpenRouter's meta-router, $0 but routes to a RANDOM free model per request (utility pick, quality varies)
192
197
  // Removed (2026-09-28 audit): nex-agi/nex-n2.5-mini:free — nex-agi dropped from the live :free catalog entirely
193
198
  // Removed (2026-09-28 audit): inclusionai/ling-3.0-flash-vl:free — :free variant removed from the live catalog (base model now billed)
@@ -195,7 +200,7 @@ export const openrouter = [
195
200
  ['thinkingmachines/inkling-small:free', 'Inkling Small', 'B', '-', '1M'], // Added (2026-09-02)
196
201
  ['dots-studio/dots-3-note-preview:free', 'Dots 3 Note Preview', 'B', '-', '512k'], // Added (2026-09-02)
197
202
  // ── C tier — lightweight/edge models ──
198
- ['nvidia/nemotron-3.5-content-safety:free', 'Nemotron 3.5 Content Safety', 'C', '-', '128k'],
203
+ // Removed (2026-10-10 audit): nvidia/nemotron-3.5-content-safety:free — moderation classifier, not coding-capable (catalog hygiene; same cleanup on Kilo/Requesty)
199
204
  ]
200
205
 
201
206
  // 📖 GitHub Models source - https://models.github.ai
@@ -234,12 +239,13 @@ export const mistral = [
234
239
  ['ministral-14b-2512', 'Ministral 3 14B', 'B+', '-', '256k'], // Fixed (2026-09-16): ministral-3-14b-25-12 → ministral-14b-2512 (live /v1/models, ctx 262144)
235
240
  // ── B tier — SWE-bench Verified 20–30% ──
236
241
  ['ministral-8b-2512', 'Ministral 3 8B', 'B', '-', '256k'], // Fixed (2026-09-16): ministral-3-8b-25-12 → ministral-8b-2512 (live /v1/models, ctx 262144)
237
- ['labs-leanstral-1-5', 'Leanstral 1.5', 'B', '-', '256k'], // Added (2026-09-22) — free-listed on Mistral LP; targets Lean 4 theorem proving, niche coding use
238
- ['ministral-3b-2512', 'Ministral 3 3B', 'B', '-', '131k'], // Fixed (2026-09-16): ministral-3-3b-25-12 → ministral-3b-2512; ctx 256k → 131k (max_context_length 131072; 2026-09-28 audit re-confirmed 131k)
242
+ // Removed (2026-10-17 audit): labs-leanstral-1-5-1 (Leanstral 1.5.1) — Labs Leanstral line deprecated 2026-09-29 and retired 2026-09-30 per the docs.mistral.ai deprecation table; free-tier probe now returns 403 tier_not_allowed (the signature the repo documented for paid-only models)
243
+ ['ministral-3b-2512', 'Ministral 3 3B', 'B', '-', '128k'], // Fixed (2026-10-17 audit): ctx '131k' → '128k' (official max_context_length 128000 per docs.mistral.ai); id fixed 2026-09-16
239
244
  // Removed (2026-09-16): mistral-small-creative-25-12 (Mistral Small Creative) — absent from the live catalog
240
245
  // ── Coding models (codestral-2508 aliases, live-verified 2026-09-22 via api.mistral.ai/v1/models) ──
241
246
  ['mistral-code-latest', 'Mistral Code', 'A', '-', '256k'], // Added (2026-09-22): aliases codestral-2508 / codestral-latest; ctx 256000
242
247
  ['mistral-code-fim-latest', 'Mistral Code FIM', 'A', '-', '256k'], // Added (2026-09-22): FIM alias of codestral-2508; ctx 256000
248
+ ['mistral-vibe-cli-latest', 'Mistral Vibe CLI', 'A', '-', '256k'], // Added (2026-10-10 audit) — new free-tier coding model on live /v1/models (Vibe CLI agent line)
243
249
  ]
244
250
 
245
251
  // 📖 Mistral Codestral source - https://codestral.mistral.ai
@@ -257,7 +263,9 @@ export const codestral = [
257
263
  export const scaleway = [
258
264
  // ── S+ tier — SWE-bench Verified ≥70% ──
259
265
  ['glm-5.2', 'GLM 5.2', 'S+', '82.8%', '256k'], // Fixed (2026-08-13): ctx '1M' → '256k' (Serverless tier per official catalog)
266
+ ['glm-5.3', 'GLM 5.3', 'S+', '-', '256k'], // Added (2026-10-17 audit) — free Serverless on the official supported-models page; score pending a published SWE-bench Verified figure
260
267
  ['deepseek-v4-flash-0731', 'DeepSeek V4 Flash', 'S+', '-', '256k'], // Added (2026-08-13)
268
+ ['deepseek-v4.1-flash', 'DeepSeek V4.1 Flash', 'S+', '-', '256k'], // Added (2026-10-17 audit) — free Serverless on the official supported-models page (upstream retired V4-Flash-0731 on 2026-09-10 but Scaleway still serves both)
261
269
  // Removed (2026-09-05): devstral-2-123b-instruct-2512 (Devstral 2 123B) - Deprecated 2026-07-01, End of Life 2026-08-01; after EOL the model is no longer accessible on Generative APIs Serverless
262
270
  // ── S tier — SWE-bench Verified 60–70% ──
263
271
  ['qwen3.5-397b-a17b', 'Qwen3.5 400B VLM', 'S+', '76.2%', '250k'],
@@ -268,6 +276,7 @@ export const scaleway = [
268
276
  // Removed (2026-09-15): qwen3-coder-30b-a3b-instruct (Qwen3 Coder 30B) — Deprecated 2026-07-01, EOL 2026-10-01; replacement: qwen3.6-35b-a3b
269
277
  // Audit (2026-09-28): all 11 entries confirmed live; qwen3-coder-30b-a3b-instruct still EOL 2026-10-01, not re-added
270
278
  ['qwen3.6-35b-a3b', 'Qwen3.6 35B MoE', 'S+', '73.4%', '256k'],
279
+ ['qwen3-coder-30b-a3b-instruct', 'Qwen3 Coder 30B', 'A+', '51.6%', '128k'], // Re-added (2026-10-17 audit) — live free Serverless again on the official supported-models page (the 2026-10-01 EOL verdict is reversed upstream); 51.6% is the official Qwen SWE-bench Verified for the 30B coder
271
280
  // Removed (2026-09-05): holo2-30b-a3b (Holo2 30B) - Deprecated 2026-07-09, End of Life 2026-08-09; after EOL the model is no longer accessible on Generative APIs Serverless
272
281
  ['gemma-4-26b-a4b-it', 'Gemma 4 26B MoE', 'A+', '-', '256k'],
273
282
  // Removed (2026-09-02): gemma-4-31b-it (Gemma 4 31B IT) — Dedicated tier only, not available on Serverless
@@ -305,12 +314,16 @@ export const googleai = [
305
314
  ]
306
315
 
307
316
  // 📖 ZAI source - https://open.z.ai
308
- // 📖 Free tier is limited to Flash models; paid GLM models are intentionally excluded.
309
- // 📖 Verified live (2026-08-23) via ping test: glm-4.5-flash and glm-4.6v-flash still serve free;
310
- // 📖 glm-4.7-flash is free but was returning "overloaded" 429s; API /models lists only 9 text models.
317
+ // 📖 ⚠️ NO FREE TIER LEFT (2026-10-17 audit) — the GLM Coding Plan devpack free window
318
+ // 📖 (zero-quota 23:00-09:00 SGT, ran 2026-09-03 → 2026-10-07) is over and the plan is
319
+ // 📖 now paid-only (Lite/Pro/Max, from $18/mo; docs.z.ai/devpack/overview). GLM-5.3-Flash
320
+ // 📖 bills $0.15/$0.50 per 1M on the pay-per-token API. Free GLM-5.3-Flash remains on
321
+ // 📖 NVIDIA NIM / OpenRouter / Pollinations / OrcaRouter / onomeo gateways.
322
+ // 📖 Kept as an empty array so downstream provider-metadata/config code that imports
323
+ // 📖 `zai` and references the 'zai' key (id normalizers, ZAI_API_KEY) doesn't crash; the
324
+ // 📖 entry is also commented out of the `sources` map below so it won't appear in the catalog.
311
325
  export const zai = [
312
- // ── S+ tier — SWE-bench Verified ≥70% ──
313
- ['zai/glm-5.3-flash', 'GLM-5.3-Flash', 'S+', '-', '1M'], // Added (2026-09-02) — free via Coding Plan devpack campaign (runs to 2026-10-07); zero quota 23:00-09:00 SGT
326
+ // Removed (2026-10-17 audit): zai/glm-5.3-flash (GLM-5.3-Flash) — the Coding Plan devpack free window ended 2026-10-07 and the GLM Coding Plan is paid-only (Lite $18/mo+); the id now serves a paid model. Free GLM-5.3-Flash: z-ai/glm-5.3-flash on NVIDIA NIM
314
327
  // Removed (2026-09-29 audit): zai/glm-5.3 (GLM-5.3) — paid-only on the API ($1.4/$4.4 per 1M) and needs the paid $18/mo Coding Plan; docs pricing page has no free column for it (provider premise: Flash models only)
315
328
  // Removed (2026-09-21): zai/glm-5.2 + zai/glm-5.1 — Coding Plan requests for both are now silently redirected to GLM-5.3 (official docs.z.ai plan update), so the ids no longer serve a distinct free model; both remain paid-API models
316
329
  // Removed (2026-09-28 audit): zai/glm-5 — legacy id, Coding Plan auto-routes GLM-5 requests to GLM-5.3
@@ -336,25 +349,25 @@ export const qwen = [
336
349
  ['qwen3.6-plus', 'Qwen3.6 Plus', 'S+', '78.8%', '1M'],
337
350
  // Removed (2026-09-15): qwen3-235b-a22b (Qwen3 235B) — legacy base, Oct 10 2026 shutdown; replacement: qwen3.5-397b-a17b
338
351
  ['qwen3.7-plus', 'Qwen3.7 Plus', 'S+', '-', '1M'],
339
- ['qwen3.6-max-preview', 'Qwen3.6 Max Preview', 'S+', '80.9%', '256k'], // ⚠️ DEPRECATED - shutdown 2026-10-10 (Alibaba notice id 1950, 2026-09-29 audit); replacement: qwen3.7-max
352
+ // Removed (2026-10-10 audit): qwen3.6-max-preview (Qwen3.6 Max Preview) — retired 2026-10-10 per Alibaba decommissioning notice 1950 (the ⚠️ date below hit); replacement: qwen3.7-max
340
353
  ['qwen3.8-max', 'Qwen3.8 Max', 'S+', '-', '1M'],
341
354
  ['qwen3.8-2.4t-a95b', 'Qwen3.8 2.4T A95B', 'S+', '-', '1M'],
342
355
  ['qwen3.8-max-0902', 'Qwen3.8 Max 0902', 'S+', '-', '1M'], // Added (2026-09-15) — verified via live audit
343
356
  // ── S tier — SWE-bench Verified 60–70% ──
344
357
  ['qwen3.5-plus', 'Qwen3.5 Plus', 'S+', '80.0%', '1M'],
345
- ['qwen3-coder-plus', 'Qwen3 Coder Plus', 'S', '69.6%', '1M'], // ⚠️ DEPRECATED - shutdown 2026-10-10 (Alibaba notice id 1950, 2026-09-29 audit); replacement: qwen3.7-plus
346
- ['qwen3-coder-next', 'Qwen3 Coder Next', 'S+', '70.6%', '256k'], // ⚠️ DEPRECATED - shutdown 2026-10-10 (Alibaba notice id 1949, 2026-09-29 audit); replacement: qwen3.7-plus
358
+ // Removed (2026-10-10 audit): qwen3-coder-plus (Qwen3 Coder Plus) — retired 2026-10-10 per Alibaba decommissioning notice 1950 (the ⚠️ date below hit); replacement: qwen3.7-plus
359
+ // Removed (2026-10-10 audit): qwen3-coder-next (Qwen3 Coder Next) — retired 2026-10-10 per Alibaba decommissioning notice 1949 (the ⚠️ date below hit); replacement: qwen3.7-plus
347
360
  // Removed (2026-09-15): qwen3-coder-480b-a35b-instruct (Qwen3 Coder 480B) — legacy, superseded by qwen3-coder-next; replacement: qwen3-coder-next
348
- ['qwen3-coder-480b-a35b-instruct', 'Qwen3 Coder 480B', 'S', '69.6%', '256k'], // Re-added (2026-09-21) — back on the official free billing page (1M-token free quota, updated 2026-09-20); free tier did not remove it after all // ⚠️ DEPRECATED - shutdown 2026-10-10 (Alibaba notice id 1949, 2026-09-29 audit); replacement: qwen3.7-plus
361
+ // Removed (2026-10-10 audit): qwen3-coder-480b-a35b-instruct (Qwen3 Coder 480B) — the 2026-09-21 re-add ended today: retired 2026-10-10 per Alibaba decommissioning notice 1949 (the ⚠️ date below hit); replacement: qwen3.7-plus
349
362
  ['qwen3.8-27b', 'Qwen3.8 27B', 'S', '-', '1M'],
350
363
  // ── A+ tier — SWE-bench Verified 50–60% ──
351
364
  ['qwen3.7-flash', 'Qwen3.7 Flash', 'A+', '-', '1M'], // Added (2026-07-27)
352
365
  ['qwen3.6-flash', 'Qwen3.6 Flash', 'A+', '60.0%', '1M'],
353
366
  ['qwen3.5-flash', 'Qwen3.5 Flash', 'S', '64.4%', '1M'],
354
367
  ['qwen3-coder-flash', 'Qwen3 Coder Flash', 'A+', '55.0%', '1M'],
355
- ['qwen3-vl-flash', 'Qwen3 VL Flash', 'A+', '-', '256k'], // Added (2026-08-13) // ⚠️ DEPRECATED - shutdown 2026-10-10 (Alibaba notice id 1950, 2026-09-29 audit); replacement: qwen3.6-flash
368
+ // Removed (2026-10-10 audit): qwen3-vl-flash (Qwen3 VL Flash) — retired 2026-10-10 per Alibaba decommissioning notice 1950 (the ⚠️ date below hit); only qwen3-vl-plus survives in the VL tier; replacement: qwen3.6-flash
356
369
  ['qwen3-vl-plus', 'Qwen3 VL Plus', 'A+', '-', '256k'], // Added (2026-09-21) — on the official free billing page (1M-token free quota)
357
- ['qwen3-coder-30b-a3b-instruct', 'Qwen3 Coder 30B A3B', 'A+', '-', '256k'], // Added (2026-09-21) — on the official free billing page (1M-token free quota) // ⚠️ DEPRECATED - shutdown 2026-10-10 (Alibaba notice id 1949, 2026-09-29 audit); replacement: qwen3.7-plus
370
+ // Removed (2026-10-10 audit): qwen3-coder-30b-a3b-instruct (Qwen3 Coder 30B A3B) — EOL 2026-10-10 per Alibaba decommissioning notice 1949 (the ⚠️ date below hit; same EOL hit Scaleway 2026-10-01); replacement: qwen3.7-plus
358
371
  // Removed (2026-09-15): qwen3-32b (Qwen3 32B) — legacy, Oct 10 2026 shutdown (aliyun notice 118434); replacement: qwen3.8-27b
359
372
  ['qwen3.5-397b-a17b', 'Qwen3.5 397B A17B', 'S+', '76.2%', '256k'],
360
373
  ['qwen3.5-122b-a10b', 'Qwen3.5 122B A10B', 'S+', '72.0%', '256k'],
@@ -362,12 +375,12 @@ export const qwen = [
362
375
  // Removed (2026-09-15): qwen3-next-80b-a3b-thinking (Qwen3 Next 80B Thinking) — retired in 2026 legacy cleanup; replacement: qwen3.8-flash
363
376
  // Removed (2026-09-15): qwen3-next-80b-a3b-instruct (Qwen3 Next 80B Instruct) — retired in 2026 legacy cleanup; replacement: qwen3.8-flash
364
377
  ['qwen3.8-flash', 'Qwen3.8 Flash', 'A+', '-', '1M'],
365
- ['qwen3.8-flash-next', 'Qwen3.8 Flash Next', 'A+', '-', '256k'], // Added (2026-09-15) — verified via live audit
378
+ // Removed (2026-10-10 audit): qwen3.8-flash-next (Qwen3.8 Flash Next) — phantom entry: 404 detail page, absent from the Model List product index, never appears in release lifecycle or retirement notices; replacement: qwen3.8-flash
366
379
  // ── A tier — SWE-bench Verified 40–50% ──
367
380
  ['qwen3.5-27b', 'Qwen3.5 27B', 'S+', '72.4%', '256k'],
368
381
  // Removed (2026-09-15): qwen3-30b-a3b (Qwen3 30B A3B) — legacy, Oct 10 2026 shutdown; replacement: qwen3.5-35b-a3b
369
- ['qwen3.5-omni-plus', 'Qwen3.5 Omni Plus', 'B+', '-', '32k'], // Added (2026-09-15) — verified via live audit
370
- ['qwen3.8-omni-flash', 'Qwen3.8 Omni Flash', 'B+', '-', '32k'], // Added (2026-09-21) — on the official free billing page; ctx follows omni-family precedent (32k)
382
+ ['qwen3.5-omni-plus', 'Qwen3.5 Omni Plus', 'B+', '-', '256k'], // Fixed (2026-10-10 audit): ctx '32k' → '256k' (official model page; the "omni-family 32k" precedent was wrong)
383
+ ['qwen3.8-omni-flash', 'Qwen3.8 Omni Flash', 'B+', '-', '1M'], // Fixed (2026-10-10 audit): ctx '32k' → '1M' (official model page)
371
384
  ['qwen3.6-27b', 'Qwen3.6 27B', 'B+', '-', '256k'], // Added (2026-09-15) — verified via live audit
372
385
  ['qwen3.6-35b-a3b', 'Qwen3.6 35B A3B', 'B+', '-', '256k'], // Added (2026-09-15) — verified via live audit
373
386
  ]
@@ -420,7 +433,7 @@ export const ovhcloud = [
420
433
  ['Qwen3.6-27B', 'Qwen3.6 27B', 'S+', '77.2%', '262k'],
421
434
  // Removed (2026-07-27): Qwen3-Coder-30B-A3B-Instruct (Qwen3 Coder 30B MoE) — no longer in catalog
422
435
  // Removed (2026-09-21): Qwen3-Coder-30B-A3B-Instruct (Qwen3 Coder 30B A3B) — absent from the official AI Endpoints catalog page (20 models, no coder model); the 2026-09-21 morning re-add was erroneous
423
- ['Qwen3-Coder-30B-A3B-Instruct', 'Qwen3 Coder 30B A3B', 'A', '-', '262k'], // Re-added (2026-09-29 audit) — served by the live router API (oai.endpoints.kepler.ai.cloud.ovh.net/v1/models, ctx 262144) though the marketing page hides it
436
+ // Removed (2026-10-10 audit): Qwen3-Coder-30B-A3B-Instruct (Qwen3 Coder 30B A3B) — the 2026-09-29 "live router API" re-add is dead: chat endpoint returns model_not_found and the id is gone from /v1/models; replacement: Qwen3.8-27B
424
437
  ['gpt-oss-120b', 'GPT OSS 120B', 'S', '62.4%', '131k'],
425
438
  ['gpt-oss-20b', 'GPT OSS 20B', 'A+', '50.3%', '131k'],
426
439
  ['Meta-Llama-3_3-70B-Instruct', 'Llama 3.3 70B', 'B', '22.0%', '131k'],
@@ -429,7 +442,7 @@ export const ovhcloud = [
429
442
  // Removed (2026-07-27): Mistral-7B-Instruct-v0.3 (Mistral 7B Instruct) — no longer in catalog
430
443
  // Removed (2026-08-13): Mistral-Nemo-Instruct-2407 (Mistral Nemo) — no longer in OVHcloud public catalog
431
444
  // Removed (2026-09-21): Mistral-Small-3.2-24B-Instruct-2506 + Mistral-Nemo-Instruct-2407 + Mistral-7B-Instruct-v0.3 re-removed — none of the three Mistral models appear on the official AI Endpoints catalog page; the 2026-09-21 morning re-adds were erroneous
432
- ['Mistral-Small-3.2-24B-Instruct-2506', 'Mistral Small 3.2 24B','B+', '20.0%', '131k'], // Re-added (2026-09-29 audit) — served by the live router API (marketing page hides it); score 20.0% reused from the same model id on Scaleway
445
+ ['Mistral-Small-3.2-24B-Instruct-2506', 'Mistral Small 3.2 24B','B+', '20.0%', '131k', null, '2026-11-04'], // ⚠️ DEPRECATED — OVHcloud decommission 2026-11-04 (announced 2026-08-04, API 404s after that date); 7th tuple element auto-filters it from the catalog. Re-added (2026-09-29 audit) — served by the live router API (marketing page hides it); score 20.0% reused from the same model id on Scaleway
433
446
  ['Qwen3.5-9B', 'Qwen3.5 9B', 'B+', '30.0%', '262k'],
434
447
  ['Qwen2.5-VL-72B-Instruct', 'Qwen2.5-VL 72B', 'S', '-', '32k'], // Added (2026-08-13)
435
448
  // ── Embeddings ──
@@ -452,18 +465,25 @@ export const ovhcloud = [
452
465
  export const opencodeZen = [
453
466
  ['big-pickle', 'Big Pickle', 'S+', '72.0%', '200k'],
454
467
  // Removed (2026-09-29 audit): deepseek-v4-flash-free (DeepSeek V4 Flash Free) — live chat probe returns 400 "Upstream request failed: Model is unavailable" and it is gone from the docs free table; the 2026-09-21 re-add said "re-verify at next audit", verified dead
455
- ['mimo-v2.5-free', 'MiMo-V2.5 Free', 'S+', '-', '200k'],
468
+ // Removed (2026-10-10 audit): mimo-v2.5-free (MiMo-V2.5 Free) — live chat probe returns 401 ModelError "not supported" and it is absent from the /v1/models list (docs table from Oct 8 is stale on this one); replacement: mimo-v2.6-flash-free
456
469
  ['mimo-v2.6-flash-free', 'MiMo-V2.6 Flash Free', 'S+', '-', '200k'], // Added (2026-09-22) — new free promo model on the live Zen /v1/models list
470
+ // Removed (2026-10-17 audit): step-5-preview-free (Step 5 Preview Free) — live chat probe returns "Upstream request failed: Model is unavailable", deprecated in the models.dev opencode registry, absent from the docs free table; reverses the 2026-10-10 add (Step 5 stays free on NVIDIA NIM)
471
+ // Removed (2026-10-17 audit): ling-3.1-flash-free (Ling 3.1 Flash Free) — live chat probe returns "Model is unavailable", deprecated in the models.dev registry, absent from the docs free table
472
+ // Removed (2026-10-17 audit): ling-3.0-flash-fin-free (Ling 3.0 Flash Fin Free) — live chat probe returns "Model is unavailable", deprecated in the models.dev registry, absent from the docs free table
457
473
  ['nemotron-3-ultra-free', 'Nemotron 3 Ultra Free', 'S+', '71.9%', '1M'],
458
474
  // Removed (2026-09-05): hy3-free (Tencent Hy3 Free) — absent from live /v1/models (66 models checked)
459
475
  ['nemotron-3.5-lightning-free', 'Nemotron 3.5 Lightning Free', 'S+', '-', '262k'], // Added (2026-08-13)
460
476
  // Removed (2026-09-05): laguna-s-2.1-free (Laguna S 2.1 Free) - deprecated: marked status=deprecated in the models.dev registry (2026-09-05) and absent from both the Zen /v1/models endpoint and the docs free-models list; the limited-time promo ended
461
- ['ling-3.0-flash-fin-free', 'Ling 3.0 Flash Fin Free', 'B+', '-', '262k'], // Added (2026-09-05) — new id in live /v1/models (was ling-3.0-flash-free)
462
- // Removed (2026-09-29 audit): muse-spark-1.2-contributor-free (Muse Spark 1.2 Contributor Free) — dropped from the docs free-models table (only the 1.3 contributor variant remains); the 2026-09-28 "re-verify next audit" verdict
463
- ['muse-spark-1.3-contributor-free', 'Muse Spark 1.3 Contributor Free', 'S+', '-', '1M'],
477
+ // Removed (2026-10-17 audit): muse-spark-1.3-contributor-free (Muse Spark 1.3 Contributor Free) — gateway returns an explicit ModelDeprecated error; the contributor promo ended and only the paid muse-spark-1.3 ($1.25/$4.25 per 1M) remains
464
478
  ['jev-1.13-free', 'Jev 1.13 Free', 'B+', '-', '200k'], // Added (2026-09-21) — new free model on the live Zen /v1/models list (74 models checked)
465
479
  ['space-bunny-free', 'Space Bunny Free', 'S+', '-', '1M'], // Fixed (2026-09-29 audit): ctx '200k' → '1M' (models.dev opencode registry: 1048576)
466
480
  ['longcat-2.5-preview-free', 'LongCat 2.5 Preview Free', 'A+', '-', '1M'], // Fixed (2026-09-29 audit): ctx '200k' → '1M' (models.dev opencode registry: 1000000)
481
+ // Added (2026-10-17 audit) — new free promo wave on the live Zen list (verified via FreeTierError chat probes + models.dev; note /v1/models omits some still-live free ids):
482
+ ['beam-free', 'Beam Free', 'S+', '80.9%', '1M'], // Added (2026-10-17 audit) — Reflection Beam 1.0 (501B MoE), SWE-bench Verified 80.9% per reflection.ai; also free on Kilo/Vercel/Ollama
483
+ ['exo-free', 'Exo Free', 'S+', '-', '1M'], // Added (2026-10-17 audit) — new free flagship slot, 1M ctx per models.dev
484
+ ['nemotron-3.5-super-vl-free', 'Nemotron 3.5 Super VL Free', 'S+', '71.1%', '1M'], // Added (2026-10-17 audit) — 1M ctx on Zen; SWE score follows the same model on NVIDIA NIM, S+ on the documented scale
485
+ ['deepseek-v4.1-flash-free', 'DeepSeek V4.1 Flash Free', 'S+', '-', '200k'], // Added (2026-10-17 audit) — capped at 200k on Zen
486
+ ['glm-5.3-flash-free', 'GLM 5.3 Flash Free', 'A+', '-', '200k'], // Added (2026-10-17 audit) — capped at 200k on Zen; tier follows the GLM-5.3-Flash reads on other gateways
467
487
  // 2026-09-29 audit: the free-tier gate hardened since issue #181 — 403 FreeTierError even WITH the x-opencode-session header, only space-bunny-free answers plain requests; if TUI probes fail, use a real Zen key
468
488
  ]
469
489
 
@@ -474,28 +494,34 @@ export const kilo = [
474
494
  ['kilo-auto/free', 'Kilo Auto Free', 'A+', '-', '256k'],
475
495
  // Removed (2026-09-05): kilo-auto/small (Kilo Auto Small) - no longer free: gateway now lists it with isFree=false and paid pricing ($0.05/M prompt, $0.40/M completion); it routes to paid small models
476
496
  ['thinkingmachines/inkling-small:free', 'Thinking Machines Inkling Small (free)', 'S+', '80.2%', '1M'], // tier fixed: 80.2% >= 70% is S+ on the documented scale
477
- ['stepfun/step-3.7-flash:free', 'StepFun Step 3.7 Flash (free)', 'A+', '-', '262k'],
497
+ ['reflection/beam-free', 'Reflection Beam 1.0 (free)', 'S+', '80.9%', '1M'], // Added (2026-10-17 audit) — new free flagship on the live gateway (501B MoE, released ~2026-10-05), SWE-bench Verified 80.9% per reflection.ai
498
+ // Removed (2026-10-17 audit): stepfun/step-5-preview-free (StepFun Step 5 Preview (free)) — free endpoint delisted from the gateway, stepfun/step-5-preview now lists isFree:false with per-token pricing; reverses the 2026-10-10 add (Step 5 stays free on NVIDIA NIM)
499
+ // Removed (2026-10-10 audit): stepfun/step-3.7-flash:free — :free variant gone from the gateway (390 models checked), only paid step-3.7-flash remains; replacement: stepfun/step-5-preview-free
478
500
  ['poolside/laguna-s-2.1:free', 'Poolside Laguna S 2.1 (free)', 'A+', '-', '262k'],
479
501
  ['nvidia/nemotron-3-ultra-550b-a55b:free', 'NVIDIA Nemotron 3 Ultra (free)', 'A+', '-', '1M'],
502
+ ['nvidia/nemotron-3.5-super-vl:free', 'NVIDIA Nemotron 3.5 Super VL (free)', 'S+', '71.1%', '1M'], // Added (2026-10-17 audit) — new $0 entry on the live gateway, 1M ctx; SWE score follows the same model on NVIDIA NIM, S+ on the documented scale
503
+ ['xingchen-agi/xing4.0-29b-a4b:free', 'XingChen Xing4.0 29B (free)', 'S+', '75.0%', '262k'], // Added (2026-10-17 audit) — new $0 entry on the live gateway; SWE-bench Verified 75.0% per the TeleAI model card (same model is the $0 pick on SiliconFlow/OpenRouter)
480
504
  // Removed (2026-09-15): minimax/minimax-m2.7:free (MiniMax M2.7 (free)) — no longer free on Kilo gateway
481
505
  ['cohere/north-mini-code:free', 'Cohere North Mini Code (free)', 'A-', '-', '256k'],
482
506
  ['nvidia/nemotron-3-super-120b-a12b:free', 'NVIDIA Nemotron 3 Super (free)', 'A-', '-', '262k'],
483
507
  ['poolside/laguna-xs-2.1:free', 'Poolside Laguna XS 2.1 (free)', 'B+', '-', '262k'],
484
508
  ['nvidia/nemotron-3.5-lightning:free', 'NVIDIA Nemotron 3.5 Lightning (free)', 'B+', '-', '1M'],
485
509
  ['dots-studio/dots-3-note-preview:free', 'Dots Studio Dots3-Note Preview (free)', 'B+', '-', '512k'],
486
- ['openrouter/free', 'OpenRouter Free Models Router', 'B', '-', '200k'],
510
+ ['openrouter/free', 'OpenRouter Free Models Router', 'B', '-', '200k'], // Fixed (2026-10-17 audit): ctx '-' → '200k' (live gateway metadata exposes context_length again; reverses the 2026-10-10 read)
487
511
  // Removed (2026-09-15): minimax/minimax-m3:free (MiniMax M3 (free)) — free variant removed from gateway
488
512
  // Removed (2026-09-15): thinkingmachines/inkling:free (Inkling (free)) — free variant no longer exposed
489
513
  ['liquid/lfm-2.5-2.6b:free', 'LFM2.5-2.6B (free)', 'C', '-', '64k'], // Added (2026-09-15) — verified via live audit
490
514
  // Removed (2026-09-28 audit): z-ai/glm-5.2:free (GLM 5.2 (free)) — no longer free on Kilo: now billed $1.40/$4.40 per M
491
515
  // Removed (2026-09-29 audit): inclusionai/ling-3.0-flash-fin:free (Ling 3.0 Flash Fin (free)) — :free variant gone from the catalog (395 models checked), id survives only as paid ($0.075/M prompt); replacement: ling-3.0-flash-sante:free
492
- ['inclusionai/ling-3.0-flash-sante:free', 'Ling 3.0 Flash Sante (free)', 'B', '-', '262k'], // Added (2026-09-15) — verified via live audit
516
+ // Removed (2026-10-10 audit): inclusionai/ling-3.0-flash-sante:free — :free variant gone from the gateway (only paid remains), and it is a health/medicine-specialized model anyway
517
+ // Removed (2026-10-17 audit): inclusionai/ling-3.1-flash (Ling 3.1 Flash (free)) — listing now shows isFree:false with paid per-token pricing, no free variant; reverses the 2026-10-10 add
493
518
  // Removed (2026-09-28 audit): inclusionai/ling-3.0-flash-vl:free — :free variant removed from the Kilo catalog (base now billed)
494
519
  // Removed (2026-09-28 audit): nex-agi/nex-n2.5-mini:free + nex-agi/nex-n2.5-pro:free — nex-agi provider dropped from the Kilo catalog entirely
495
520
  ['nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free', 'NVIDIA Nemotron 3 Nano Omni (free)', 'A+', '-', '256k'], // Fixed (2026-09-28 audit): ctx '262k' → '256k', // Added (2026-09-21) — new in the live free gateway list
496
- ['qwen/qwen3.8-27b:free', 'Qwen3.8 27B (free)', 'S', '-', '262k'], // Added (2026-09-21) — new in the live free gateway list
497
- ['stealth/space-bunny-alpha', 'Space Bunny Alpha (stealth)', 'S', '-', '1M'], // Added (2026-09-28 audit) — new free stealth model on the live gateway
498
- ['nvidia/nemotron-3.5-content-safety:free', 'NVIDIA Nemotron 3.5 Content Safety (free)', 'C', '-', '128k'], // Added (2026-09-22) — content-safety classifier, marginal but kept for breadth (matches OpenRouter/Requesty)
521
+ // Removed (2026-10-10 audit): qwen/qwen3.8-27b:free — :free variant removed from the gateway (mirrors its OpenRouter deletion the same day); only paid qwen/qwen3.8-27b remains
522
+ ['stealth/glyph-cluster', 'Glyph Cluster (stealth, free)', 'A+', '-', '256k'], // Added (2026-10-10 audit) — new free stealth coding model, replaces the rotated-out space-bunny-alpha slot (also live on Vercel gateway)
523
+ // Removed (2026-10-10 audit): stealth/space-bunny-alpha — deleted entirely from the gateway, stealth slot replaced by glyph-cluster
524
+ // Removed (2026-10-10 audit): nvidia/nemotron-3.5-content-safety:free — moderation classifier, not a coding model (catalog hygiene; matches OpenRouter/Requesty cleanup)
499
525
  ]
500
526
 
501
527
  // 📖 LLM7 source - https://api.llm7.io/v1
@@ -503,16 +529,21 @@ export const kilo = [
503
529
  // 📖 Pro-tagged models from /v1/models are intentionally excluded.
504
530
  export const llm7 = [
505
531
  // 📖 LLM7 live /v1/models: only `turbo` tier is free (noKeyNeeded). All `pro` models are usage-based paid.
506
- // 📖 Verified live 2026-09-05: turbo tier = minimax-m2.7, gpt-oss, mistral-Nemo-Instruct-2407, codestral-latest.
532
+ // 📖 Verified live 2026-10-10 (audit): free tier = DeepSeek-V4-Flash-0731, GLM-5.3-Flash, kimi-k2.6, kimi-k2.7-code,
533
+ // 📖 gpt-oss:20b, nemotron-3-nano:30b, mistral-Nemo-Instruct-2407, codestral-latest (all turbo, usage_based_only=false).
507
534
  // Removed (2026-09-05): glm-5.3, glm-5.3-flash, gemini-3.5-flash-low, gpt-5.4, gpt-5.4-mini, gpt-5.5, gpt-5.6-sol, grok-4.5, grok-4.6 — tier=pro usage_based_only (paid) or nonexistent on /v1/models (PR #178 additions reverted)
508
535
  // ── S+ tier — SWE-bench Verified ≥70% ──
509
- ['minimax-m2.7', 'MiniMax M2.7', 'S+', '78.0%', '180k'],
510
- // Removed (2026-09-29 audit): GLM-5.3-Flash (GLM-5.3 Flash) — absent from live /v1/models (64 checked) and no-key probe returns model_unavailable; the glm-5.3 successor is pro-tier paid
536
+ // Removed (2026-10-10 audit): minimax-m2.7 (MiniMax M2.7) — gone from the live /v1/models; successor minimax-m3 is usage_based_only=true (paid), so no free MiniMax remains
537
+ ['GLM-5.3-Flash', 'GLM 5.3 Flash', 'S+', '-', '400k'], // Re-added (2026-10-10 audit) — back in live /v1/models as turbo tier, usage_based_only=false (98.8% availability, reasoning + tools); reverses the 2026-09-29 removal which was based on the same weekly rotation, ctx 400000 per live metadata
511
538
  ['DeepSeek-V4-Flash-0731', 'DeepSeek V4 Flash 0731', 'S+', '79.0%', '400k'], // Added (2026-09-29 audit) — new free no-key coding flagship (turbo tier), reasoning + tools, verified answering keyless; score 79.0% is the V4 Flash family SWE-bench Verified (0731-specific score not published)
512
539
  // ── A+ tier — SWE-bench Verified 50–60% ──
513
540
  // Removed (2026-09-05): gemini-3.1-flash-lite (Gemini 3.1 Flash Lite) — now tier=pro usage_based_only (paid) per live /v1/models
514
- // Removed (2026-09-15): gpt-oss (GPT OSS 20B) — removed from LLM7 API catalog
541
+ ['kimi-k2.7-code', 'Kimi K2.7 Code', 'A', '-', '256k'], // Added (2026-10-10 audit) — code-tuned Kimi variant, turbo tier usage_based_only=false, 100% availability; score follows the K2.7 Code family (60.4% on ollama-cloud) pending a live reading
542
+ ['kimi-k2.6', 'Kimi K2.6', 'A', '-', '256k'], // Fixed (2026-10-17 audit): ctx '262k' → '256k' (live metadata); added 2026-10-10 — turbo tier, usage_based_only=false, tools
515
543
  ['mistral-Nemo-Instruct-2407', 'Mistral Nemo 12B Instruct', 'A-', '-', '128k'], // Added (2026-08-13)
544
+ ['gpt-oss:20b', 'GPT-OSS 20B', 'B+', '-', '128k'], // Added (2026-10-10 audit) — open-weights 20B reasoning, turbo tier usage_based_only=false
545
+ ['minimax-m2.7', 'MiniMax M2.7', 'S+', '78.0%', '180k'], // Re-added (2026-10-17 audit) — back on the live /v1/models as turbo tier (free), 180k ctx; tier + score follow the same model on routeway/ollama-cloud. Reverses the 2026-10-10 removal
546
+ ['nemotron-3-nano:30b', 'Nemotron 3 Nano 30B', 'B+', '-', '1M'], // Added (2026-10-10 audit) — turbo tier, 1M ctx, 100% availability; score follows the same model on ollama-cloud (38.8%)
516
547
  // ── A tier — SWE-bench Verified 40–50% ──
517
548
  ['codestral-latest', 'Codestral Latest', 'A', '40.0%', '32k'],
518
549
  ]
@@ -555,15 +586,22 @@ export const routeway = [
555
586
  // 📖 Novita is mostly paid/trial-credit, so this catalog only includes live chat models reporting 0 input/output price.
556
587
  // 📖 Test/dev/placeholder zero-price IDs were intentionally excluded.
557
588
  export const novita = [
558
- // 📖 2026-09-29 audit: the zero-price tier is BACK (live api.novita.ai/v3/openai/models, 119 models) — it had emptied out by 2026-08-13, Novita restored free entries late September
589
+ // 📖 2026-10-17 audit: the zero-price tier collapsed again — 7 of 8 catalog models now bill per
590
+ // 📖 token on the live /v1/models (the Ling TIME LIMITED FREE promo and the GLM/Qwen/MiniMax free
591
+ // 📖 tiers all ended). Only dev/glm46 ($0, 256k) + the new apodex partner launch remain free.
559
592
  // ── S+ tier — SWE-bench Verified ≥70% ──
560
- ['qwen/qwen3.6-plus', 'Qwen3.6 Plus', 'S+', '78.8%', '1M'], // Re-added (2026-09-29 audit) — zero-price again on the live API; the 2026-09-22 removal predates Novita restoring its free tier; score from the same model on DashScope
561
- ['qwen/qwen3.5-plus', 'Qwen3.5 Plus', 'S+', '80.0%', '1M'], // Re-added (2026-09-29 audit) — zero-price again on the live API (1M ctx, multimodal); score from the same model on DashScope
593
+ // Removed (2026-10-10 audit): qwen/qwen3.6-plus + qwen/qwen3.5-plus — both gone from the live /v1/models (94 models): Novita killed the Qwen3.5/3.6 Plus tier in favor of the Qwen3.8 generation; replacements: qwen/qwen3.8-flash (cheap, 1M ctx) / qwen/qwen3.8-max (flagship)
562
594
  // ── A tier — SWE-bench Verified 40–50% ──
595
+ // Removed (2026-10-17 audit): zai-org/glm-5.3-flash (GLM 5.3 Flash) — free promo ended, API now bills $1.5/M in + $5/M out; reverses the 2026-10-10 add
596
+ // Removed (2026-10-17 audit): qwen/qwen3.8-flash (Qwen3.8 Flash) — no longer free, now bills $1.5/M in + $4.7/M out; reverses the 2026-10-10 add
563
597
  // Removed (2026-09-29 audit): inclusionai/ling-3.0-flash-fin (Ling 3.0 Flash Fin) — still listed but now billed $0.075/M in, $0.22/M out; replacement: ling-3.1-flash
564
- ['inclusionai/ling-3.0-flash-sante', 'Ling 3.0 Flash Sante', 'B+', '-', '262k'], // Fixed (2026-09-29 audit): ctx '256k' → '262k' (live context_size field); only Ling 3.0 variant still zero-price
565
- ['inclusionai/ling-3.1-flash', 'Ling 3.1 Flash', 'A', '-', '262k'], // Added (2026-09-29 audit) — new (~Sep 26) zero-price model; API description claims 1M ctx but context_size enforces 262k
566
- ['dev/glm46', 'GLM 4.6 (dev)', 'A', '-', '256k'], // Re-added (2026-09-29 audit) — zero-price again on the live API; reverses the 2026-09-22 paid-only removal
598
+ // Removed (2026-10-17 audit): inclusionai/ling-3.0-flash-sante (Ling 3.0 Flash Sante) — TIME LIMITED FREE promo ended, now $0.75/M in + $2.2/M out
599
+ // Removed (2026-10-17 audit): inclusionai/ling-3.1-flash (Ling 3.1 Flash) — no longer free, now bills $3/M in + $9/M out; reverses the 2026-09-29 add
600
+ ['dev/glm46', 'GLM 4.6 (dev)', 'A', '-', '256k'], // Re-added (2026-09-29 audit) — zero-price again on the live API; reverses the 2026-09-22 paid-only removal; 2026-10-17 audit: still the only $0 legacy model
601
+ ['apodex/apodex-1.1-mini', 'Apodex 1.1 Mini', 'B+', '-', '262k'], // Added (2026-10-17 audit) — free partner launch since 2026-10-01 (35B MoE, no stated end date), $0 on the live API; replaces its OpenRouter :free slot delisted the same day
602
+ // Removed (2026-10-17 audit): inclusionai/ling-3.0-flash (Ling 3.0 Flash) — no longer free, now bills $0.6/M in + $1.8/M out; reverses the 2026-10-10 add
603
+ // Removed (2026-10-17 audit): zai-org/glm-4.7-flash (GLM 4.7 Flash) — no longer free, now bills $0.7/M in + $4/M out; reverses the 2026-10-10 add
604
+ // Removed (2026-10-17 audit): minimax/minimax-m2.7 (MiniMax M2.7) — no longer free, now bills $3/M in + $12/M out; reverses the 2026-10-10 add
567
605
  // Notes (2026-09-29): `bunny` is also zero-price again but Novita publishes no description, coding relevance unverifiable; left out
568
606
  ]
569
607
 
@@ -599,7 +637,7 @@ export const pollinations = [
599
637
  // Removed (2026-09-28 audit): anthropic/claude-opus-5 — now paid_only in the Pollinations catalog
600
638
  // ── S tier — SWE-bench Verified 60–70% ──
601
639
  // Removed (2026-09-28 audit): anthropic/claude-sonnet-5 — now paid_only in the Pollinations catalog
602
- ['qwen-coder', 'Qwen3 Coder 30B', 'A+', '51.6%', '262k'], // Fixed (2026-09-21): alias now resolves to qwen/qwen3-coder-30b-a3b-instruct; re-scored from the 480B figure to the 30B SWE-bench Verified
640
+ // Removed (2026-10-17 audit): qwen-coder (Qwen3 Coder 30B) — flipped to paid: qwen/qwen3-coder-30b-a3b-instruct now carries paid_only=true and anonymous calls 401; still free on Scaleway
603
641
  ['deepseek', 'DeepSeek V4 Flash', 'S+', '79.0%', '1M'], // Fixed (2026-09-21): alias now resolves to deepseek/deepseek-v4-flash (V4 Flash 0731), was V3; re-scored per the V4 Flash family entry
604
642
  // Removed (2026-09-28 audit): kimi-code (Kimi K2.7 Code) — now paid_only in the Pollinations catalog
605
643
  ['openai', 'OpenAI GPT-5.4 Nano', 'B+', '-', '400k'], // Fixed (2026-09-21): alias now resolves to openai/gpt-5.4-nano (was a generic GPT alias); re-tiered to the nano class
@@ -609,19 +647,30 @@ export const pollinations = [
609
647
  ['deepseek/deepseek-v4.1-flash', 'DeepSeek V4.1 Flash', 'A+', '-', '1M'], // Added (2026-09-22) — healthy on live /v1/models, successor to V4 Flash
610
648
  // Removed (2026-09-28 audit): meituan/longcat-2.0 (LongCat 2.0) — now paid_only in the Pollinations catalog
611
649
  // Removed (2026-09-26): gemma-4-31b (Gemma 4 31B) — requires paid Pollen (embedded credits error on free-tier keys, issue #190); the free Gemma route is NVIDIA NIM
612
- ['gpt-oss', 'GPT OSS 20B', 'A+', '50.3%', '131k'],
650
+ ['gpt-oss', 'GPT OSS 20B', 'A+', '50.3%', '128k'], // Fixed (2026-10-17 audit): ctx '131k' → '128k' (live gen.pollinations.ai metadata)
613
651
  // Removed (2026-09-28 audit): qwen3.7-flash — now paid_only in the Pollinations catalog; still free on DashScope
614
652
  // Added (2026-09-28 audit) — 7 new free models on the live gen.pollinations.ai catalog:
615
653
  ['openai/gpt-6-sol', 'OpenAI GPT-6 Sol', 'S+', '-', '1M'],
616
654
  ['openai/gpt-5.3-codex', 'OpenAI GPT-5.3 Codex', 'S+', '-', '400k'],
617
655
  ['openai/gpt-6-luna', 'OpenAI GPT-6 Luna', 'S', '-', '1M'],
618
- ['z-ai/glm-5.2', 'Z.ai GLM-5.2', 'S', '-', '1M'],
656
+ // Removed (2026-10-17 audit): z-ai/glm-5.2 — flipped to paid (paid_only=true, anonymous 401); reverses the 2026-09-28 add
619
657
  ['openai/gpt-5.4-mini', 'OpenAI GPT-5.4 Mini', 'A+', '-', '400k'],
620
- ['x-ai/grok-4.20', 'xAI Grok 4.20', 'A+', '-', '262k'],
621
- ['amazon/nova-2-lite-v1', 'Amazon Nova 2 Lite', 'B+', '-', '1M'], // Fixed (2026-09-29 audit): id 'amazon/nova-2-lite' → 'amazon/nova-2-lite-v1' (delisted under the old id, live under the v1 id, same 1M ctx, healthy)
658
+ ['x-ai/grok-4.20', 'xAI Grok 4.20', 'A+', '-', '256k'], // Fixed (2026-10-17 audit): ctx '262k' → '256k' (live catalog metadata)
659
+ // Removed (2026-10-17 audit): amazon/nova-2-lite-v1 — flipped to paid (paid_only=true, anonymous 401)
660
+ // Removed (2026-10-17 audit): x-ai/grok-4.7 — flipped to paid (paid_only=true, anonymous 401); reverses the 2026-10-10 add, grok-4.6 is the free successor
661
+ // Removed (2026-10-17 audit): stepfun/step-5-preview — flipped to paid (paid_only=true, anonymous 401); reverses the 2026-10-10 add (Step 5 stays free on NVIDIA NIM)
662
+ // Added (2026-10-10 audit) — 3 new free models on live gen.pollinations.ai/v1/models (the 4 other candidates found the same day were skipped: kimi-k2.7-code, qwen3-coder-next, laguna-s-2.1, longcat-2.0 all carry a 2026-09 "paid Pollen" verdict and the audit did not sniff completions to clear it, see issue #190 note above):
663
+ ['openai/gpt-6.1-sol', 'OpenAI GPT-6.1 Sol', 'S+', '-', '1M'], // Added (2026-10-10 audit) — new in the live catalog, GPT-6 Sol successor, 1M ctx
664
+ // Added (2026-10-17 audit) — 6 new free models on live gen.pollinations.ai/v1/models (5 catalog slots flipped to paid Pollen the same day):
665
+ ['qwen/qwen3.8-2.4t-a95b', 'Qwen3.8 2.4T A95B', 'A+', '-', '256k'], // Added (2026-10-17 audit) — the DashScope 2.4T flagship, capped at 256k here; tier follows the DashScope entry
666
+ ['x-ai/grok-4.6', 'xAI Grok 4.6', 'A+', '-', '200k'], // Added (2026-10-17 audit) — free successor of the paid-flipped grok-4.7
667
+ ['openai/gpt-5.4', 'OpenAI GPT-5.4', 'S', '-', '1M'], // Added (2026-10-17 audit) — full GPT-5.4 at 1M ctx (the 'openai' alias keeps routing to gpt-5.4-nano)
668
+ ['x-ai/grok-4.3', 'xAI Grok 4.3', 'B+', '-', '200k'], // Added (2026-10-17 audit) — legacy Grok slot back on the free tier
669
+ ['nvidia/nemotron-3-ultra', 'NVIDIA Nemotron 3 Ultra', 'S+', '71.9%', '256k'], // Re-added (2026-10-17 audit) — back to paid_only=false in the live catalog; reverses the 2026-09-26 paid-Pollen removal, score follows the same model on NVIDIA
670
+ ['mistralai/mistral-large-3', 'Mistral Large 3', 'A+', '-', '256k'], // Added (2026-10-17 audit) — new free listing; tier follows mistral-large-3:675b on ollama-cloud
622
671
  // Audit (2026-09-28): text.pollinations.ai/models endpoint is down (502); catalog now read from gen.pollinations.ai
623
672
  // ── B+ tier ──
624
- ['nemotron-3.5-lightning', 'Nemotron 3.5 Lightning', 'B+', '-', '262k'],
673
+ ['nemotron-3.5-lightning', 'Nemotron 3.5 Lightning', 'B+', '-', '256k'], // Fixed (2026-10-17 audit): ctx '262k' → '256k' (live catalog metadata)
625
674
  ]
626
675
 
627
676
  // 📖 SiliconFlow source - https://api.siliconflow.cn/v1/chat/completions
@@ -639,6 +688,7 @@ export const siliconflow = [
639
688
  // Removed (2026-09-05): deepseek-ai/DeepSeek-R1-Distill-Qwen-7B (DeepSeek R1 Distill Qwen 7B) - No longer listed on SiliconFlow pricing/catalog page (0 of 184 model records); superseded by the newer R1-0528 Qwen3 distill
640
689
  // Removed (2026-09-22): Qwen/Qwen3.5-4B (Qwen3.5 4B) — absent from the official pricing page free list, remaining Qwen3.5 sizes are all paid
641
690
  ['XingChenAGI/Xing4.0-29B', 'Xing4.0 29B', 'A-', '-', '256k'], // Fixed (2026-09-28 audit): ctx '262k' → '256k', // Added (2026-09-21) — new $0 model on the official pricing page (181 records checked); engineering/coding focused
691
+ // Audit (2026-10-10): Xing4.0-29B re-confirmed 免费 on the official pricing page. The pricing page also lists Qwen3-8B, DeepSeek-R1-0528-Qwen3-8B, Qwen3.5-4B, Qwen2.5-7B-Instruct, GLM-4-9B-0414, GLM-Z1-9B-0414 as 免费 again — NOT re-added: each one carries a recorded paid/deprecated verdict from the 2026-09 audits and the API could not be cross-checked (401 token required, ctx unverified). Re-verify with a real key before re-adding.
642
692
  // Removed (2026-09-28 audit): tencent/Hunyuan-MT-7B (Hunyuan MT 7B) — delisted from the SiliconFlow marketplace; only Tencent model left is paid tencent/Hy4-preview
643
693
  // Removed (2026-09-21): Qwen/Qwen2.5-Coder-7B-Instruct (Qwen2.5 Coder 7B Instruct) — taken offline by SiliconFlow (official release note 2026-03-10, effective 2026-03-17; 0 of 181 records on today's pricing page); the 2026-09-15 re-add was erroneous. Replacement: Qwen/Qwen3-8B
644
694
  ]
@@ -655,18 +705,19 @@ export const requesty = [
655
705
  ['nvidia/nemotron-3-super-120b-a12b', 'Nemotron 3 Super', 'S', '60.5%', '1M'],
656
706
  ['poolside/laguna-m.1', 'Laguna M.1', 'S', '-', '32k'],
657
707
  // ── A+ tier — SWE-bench Verified 50–60% ──
658
- ['google/gemma-4-31b-it', 'Gemma 4 31B', 'A+', '52.0%', '262k'],
659
- ['nvidia/nemotron-3-nano-omni-30b-a3b-reasoning', 'Nemotron 3 Omni', 'A+', '52.0%', '131k'],
708
+ ['google/gemma-4-31b-it', 'Gemma 4 31B', 'A+', '52.0%', '256k'], // Fixed (2026-10-17 audit): ctx '262k' → '256k' (live context_window on router.requesty.ai)
709
+ ['nvidia/nemotron-3-nano-omni-30b-a3b-reasoning', 'Nemotron 3 Omni', 'A+', '52.0%', '128k'], // Fixed (2026-10-17 audit): ctx '131k' → '128k' (live context_window)
660
710
  // ── A tier — SWE-bench Verified 40–50% ──
661
- ['nvidia/nemotron-3-nano-30b-a3b', 'Nemotron Nano 30B', 'A-', '38.8%', '262k'],
711
+ ['nvidia/nemotron-3-nano-30b-a3b', 'Nemotron Nano 30B', 'A-', '38.8%', '256k'], // Fixed (2026-10-17 audit): ctx '262k' → '256k' (live context_window)
662
712
  // ── B+ tier — SWE-bench Verified 30–35% ──
663
713
  ['nvidia/nemotron-3.5-lightning-30b-a3b', 'Nemotron 3.5 Lightning', 'B+', '-', '1M'],
664
714
  // ── B tier — SWE-bench Verified 20–30% ──
665
- ['mistral/leanstral-1-5', 'Leanstral 1.5', 'B', '-', '262k'],
666
- ['novita/inclusionai/ling-3.0-tiny', 'Ling 3.0 Tiny', 'B', '-', '262k'],
715
+ ['mistral/leanstral-1-5', 'Leanstral 1.5', 'B', '-', '256k'], // Fixed (2026-10-17 audit): ctx '262k' → '256k' (live context_window)
716
+ ['novita/inclusionai/ling-3.0-tiny', 'Ling 3.0 Tiny', 'B', '-', '256k'], // Fixed (2026-10-17 audit): ctx '262k' → '256k' (live context_window)
717
+ ['novita/ling-3.1-flash', 'Ling 3.1 Flash', 'B+', '-', '256k'], // Fixed (2026-10-17 audit): id 'novita/inclusionai/ling-3.1-flash' → 'novita/ling-3.1-flash' (silent router rename, the inclusionai path was dropped) + ctx '262k' → '256k' (live context_window); added 2026-10-10
667
718
  // ── C tier — other zero-price models (kept for breadth) ──
668
- ['nvidia/nemotron-3.5-content-safety', 'Nemotron Content Safety', 'C', '-', '131k'],
669
- ['nvidia/muse-glimmer-30b', 'Muse Glimmer 30B', 'C', '-', '131k'],
719
+ // Removed (2026-10-10 audit): nvidia/nemotron-3.5-content-safety — moderation guardrail classifier (Gemma-3-4B fine-tune, tools:false), not a coding model (catalog hygiene; matches OpenRouter/Kilo cleanup)
720
+ ['nvidia/muse-glimmer-30b', 'Muse Glimmer 30B', 'C', '-', '128k'], // Fixed (2026-10-17 audit): ctx '131k' → '128k' (live context_window)
670
721
  ]
671
722
 
672
723
  // 📖 OrcaRouter source - https://api.orcarouter.ai/v1
@@ -706,10 +757,15 @@ export const vercelGateway = [
706
757
  // Removed (2026-09-15): minimax/minimax-m3-free (MiniMax M3 (Free)) — free variant removed, now paid-only
707
758
  // Removed (2026-09-15): minimax/minimax-m2.7-free (MiniMax M2.7 (Free)) — free variant removed, now paid-only
708
759
  ['poolside/laguna-s-2.1-free', 'Laguna S 2.1 (Free)', 'S+', '-', '256k'], // tier follows family precedent: laguna-xs-2.1 ships S+ 70.9% via NVIDIA. 2026-09-29 audit: still served $0/$0 live, the models.dev deprecation flag does not apply to the Vercel variant
760
+ ['reflection/beam-free', 'Beam 1.0 (Free)', 'S+', '80.9%', '1M'], // Added (2026-10-17 audit) — new $0/$0 flagship (Reflection Beam 1.0, 501B MoE, released 2026-10-05), SWE-bench Verified 80.9% per reflection.ai
709
761
  // ── B+ tier — vertical-tuned lightweight (coding secondary) ──
710
762
  // Removed (2026-09-28 audit): inclusionai/ling-3.0-flash-fin-free + inclusionai/ling-3.0-flash-vl-free — free variants removed from the gateway, only paid variants remain
711
- ['inclusionai/ling-3.0-flash-sante-free', 'Ling 3.0 Flash Sante (Free)', 'B+', '-', '256k'], // Added (2026-09-15) — verified via live audit; 2026-09-29 re-confirmed $0/$0
712
- ['stealth/pixel-canary', 'Pixel Canary (stealth)', 'B', '-', '262k'], // Fixed (2026-09-29 audit): ctx '256k' → '262k' (live context_length 262144)
763
+ // Removed (2026-10-10 audit): inclusionai/ling-3.0-flash-sante-free — the free slot was upgraded: gateway now serves ling-3.1-flash-free at $0/$0 (paid ling-3.0-flash-sante still listed)
764
+ // Removed (2026-10-17 audit): inclusionai/ling-3.1-flash-free — delisted from the gateway entirely, only the paid inclusionai/ling-3.1-flash remains ($0.30/$0.90 per M); reverses the 2026-10-10 add
765
+ ['nvidia/nemotron-3.5-lightning-free', 'Nemotron 3.5 Lightning (Free)', 'A+', '54.3%', '1M'], // Added (2026-10-17 audit) — new $0/$0 slot; SWE-bench Verified 54.3% per the NVIDIA model card, A+ on the documented scale (matches the NIM entry)
766
+ ['stealth/glyph-cluster', 'Glyph Cluster (stealth)', 'B', '-', '256k'], // Added (2026-10-10 audit) — new anonymous early-access model (~2026-10-07), $0/$0, 256k ctx; replaces the rotated-out pixel-canary slot
767
+ ['stealth/cat-jam', 'Cat Jam (stealth)', 'B+', '-', '1M'], // Added (2026-10-17 audit) — new stealth free model per the official Vercel changelog, $0/$0, 1M ctx
768
+ // Removed (2026-10-10 audit): stealth/pixel-canary — stealth slot rotated, id absent from the live gateway
713
769
  // 2026-09-29 audit: list stays strictly $0/$0. Credit-value alternates for the $5/30d credits (paid, NOT added): zai/glm-5.3-flash ($0.15/$0.50 per M, 1M ctx), deepseek/deepseek-v4-flash ($0.13/$0.26 per M, 1M ctx), qwen3.7-flash ($0.03/$0.13 per M, 991k ctx)
714
770
  ]
715
771
 
@@ -720,8 +776,8 @@ export const ollamaCloud = [
720
776
  // ── S+ tier — SWE-bench Verified ≥70% ──
721
777
  ['nemotron-3-ultra', 'Nemotron 3 Ultra', 'S+', '71.9%', '256k'],
722
778
  // Removed (2026-09-28 audit): glm-5.1 (GLM 5.1) — no longer in the Ollama Cloud catalog (glm-5.2/5.3/5.3-flash remain)
723
- ['glm-5.2', 'GLM 5.2', 'S+', '82.8%', '976k'], // Fixed (2026-07-27): ctx '128k' → '1M'
724
- ['minimax-m2.7', 'MiniMax M2.7', 'S+', '78.0%', '200k'],
779
+ ['glm-5.2', 'GLM 5.2', 'S+', '82.8%', '1M'], // Fixed (2026-10-17 audit): ctx '976k' → '1M' (live /v1/models reports the full 1048576); ctx first fixed 2026-07-27
780
+ ['minimax-m2.7', 'MiniMax M2.7', 'S+', '78.0%', '192k'], // Fixed (2026-10-17 audit): ctx '200k' → '192k' (exact live value)
725
781
  ['minimax-m3', 'MiniMax M3', 'S+', '78.4%', '512k'], // Fixed (2026-07-27): ctx '512k' → '1M'
726
782
  // Removed (2026-08-23): minimax-m2.5 (MiniMax M2.5) — no longer in ollama.com/v1/models (19 models live)
727
783
  ['kimi-k2.6', 'Kimi K2.6', 'S+', '80.2%', '256k'], // Fixed (2026-07-27): ctx '262k' → '256k'
@@ -741,15 +797,17 @@ export const ollamaCloud = [
741
797
  ['gemma4:31b', 'Gemma 4 31B', 'A+', '52.0%', '256k'], // Fixed (2026-07-27): ctx '256k' → '128k'
742
798
  ['gpt-oss:20b', 'GPT OSS 20B', 'A+', '50.3%', '128k'],
743
799
  ['mistral-large-3:675b', 'Mistral Large 3 675B Cloud', 'A+', '-', '256k'], // Fixed (2026-08-23): ID 'mistral-large-3:675b-cloud' → 'mistral-large-3:675b' (tag renamed upstream)
800
+ ['mistral-large-4', 'Mistral Large 4', 'A+', '-', '1M'], // Added (2026-10-10 audit) — new cloud model (~Oct 4, 1.05T MoE, 1M ctx, thinking + tools); tier follows the Mistral Large family precedent
744
801
  // Removed (2026-09-28 audit): qwen3.5:397b (Qwen 3.5 Cloud) — qwen3.5 is not flagged cloud on ollama.com and is absent from the cloud catalog/pricing page
745
- ['nemotron-3-nano:30b', 'Nemotron 3 Nano 30B', 'A-', '38.8%', '1M'],
802
+ ['nemotron-3-nano:30b', 'Nemotron 3 Nano 30B', 'A-', '38.8%', '256k'], // Fixed (2026-10-17 audit): ctx '1M' → '256k' (live /v1/models downgraded the context)
803
+ ['beam', 'Beam', 'S+', '81.6%', '1M'], // Added (2026-10-17 audit) — Reflection Beam free on Ollama Cloud for a limited time per the 2026-10-16 blog; SWE-bench Verified 81.6% per Ollama's post
746
804
  ]
747
805
 
748
806
  // 📖 onomeo source - https://onomeo.com/docs
749
807
  // 📖 OpenAI-compatible gateway: https://onomeo.com/v1/chat/completions (streaming + tool calls)
750
808
  // 📖 Public beta: not every feature is guaranteed to work; feedback is welcome at https://onomeo.com/feedback.
751
809
  // 📖 The models listed here are free models: they spend no credits and are limited by calls instead.
752
- // 📖 Limits: 12 req/min per key, 60 calls per 5 hours per account (a long request counts as several),
810
+ // 📖 Limits: 12 req/min per key, 30 calls per 5 hours per account (a long request counts as several, reduced from 60 in Oct 2026),
753
811
  // 📖 120 per 5 hours per IP, and a site-wide pool of 450 per 5 hours shared by all accounts.
754
812
  // 📖 Premium models are not listed; they spend credits from a daily check-in (no card: 20,000 on day 1,
755
813
  // 📖 rising to 50,000/day from day 7 of a streak), and each account that has not paid can spend up to
@@ -761,48 +819,36 @@ export const onomeo = [
761
819
  // ── S+ tier — SWE-bench Verified ≥70% ──
762
820
  ['deepseek-v4-flash', 'DeepSeek V4 Flash', 'S+', '79.0%', '1M'],
763
821
  ['glm-5.2', 'GLM 5.2', 'S+', '82.8%', '1M'],
764
- ['gemini-3.8-flash', 'Gemini 3.8 Flash', 'S+', '-', '1M'], // Added (2026-09-29 audit) — in the free pool since 2026-09-23; tier follows the same model on googleai
765
- ['gemini-3.7-flash', 'Gemini 3.7 Flash', 'S+', '-', '1M'], // Added (2026-09-29 audit) — in the free pool since 2026-09-23; tier follows the same model on googleai
822
+ // Removed (2026-10-17 audit): gemini-3.8-flash (Gemini 3.8 Flash) — delisted, absent from the current models page (neither free nor paid listing); gemini-3.7-flash remains the free Gemini slot
823
+ ['gemini-3.7-flash', 'Gemini 3.7 Flash', 'S+', '-', '1M'], // Added (2026-09-29 audit) — in the free pool since 2026-09-23; tier follows the same model on googleai; 2026-10-10 audit: still listed but upstream-paused
824
+ ['gemini-3.6-flash', 'Gemini 3.6 Flash', 'S+', '-', '1M'], // Added (2026-10-10 audit) — new free model on the live catalog (model page); tier follows the same model on googleai
766
825
  ['gemini-3.5-flash', 'Gemini 3.5 Flash', 'S+', '78.0%', '1M'], // Added (2026-09-29 audit) — in the free pool since 2026-09-23; score from the same model on googleai
767
826
  // ── S tier — SWE-bench Verified 60–70% ──
768
827
  ['gemini-3.1-flash-lite', 'Gemini 3.1 Flash Lite', 'S', '62.8%', '1M'],
769
- ['@cf/openai/gpt-oss-120b', 'GPT OSS 120B', 'S', '62.4%', '128k'],
770
- ['nvidia/nemotron-3-super-120b-a12b', 'Nemotron 3 Super', 'S', '60.5%', '256k'], // Fixed (2026-09-28 audit): ctx '262k' → '256k'
828
+ // Removed (2026-10-10 audit): @cf/openai/gpt-oss-120b (GPT OSS 120B) — absent from the entire live catalog (active rows, paused rows, provider removed list and specs map); gpt-oss-20b is the only OSS model left
829
+ // Removed (2026-10-10 audit): nvidia/nemotron-3-super-120b-a12b (Nemotron 3 Super) — in the provider's own removed list
771
830
  // ── A+ tier — SWE-bench Verified 50–60% ──
772
- ['openai/gpt-oss-20b', 'GPT OSS 20B', 'A+', '50.3%', '128k'],
773
- ['z-ai/glm-5.3-flash-free', 'GLM-5.3 Flash', 'A+', '-', '1M'],
774
- ['stepfun/step-3.7-flash:free', 'Step 3.7 Flash', 'A+', '-', '256k'],
775
- ['glm-4.7-flash', 'GLM 4.7 Flash', 'A+', '59.2%', '200k'], // Added (2026-09-29 audit) — in the free pool since 2026-09-28; score from the same Zhipu model on cloudflare (@cf/zai-org/glm-4.7-flash)
831
+ ['gpt-oss-20b', 'GPT OSS 20B', 'A+', '50.3%', '131k'], // Fixed (2026-10-10 audit): id 'openai/gpt-oss-20b' → 'gpt-oss-20b' (first-party id rename in the live catalog) + ctx '128k' → '131k'
832
+ // Removed (2026-10-17 audit): glm-5.3-flash (GLM-5.3 Flash) — officially removed this week per the site's own changelog (the paid glm-5.3 remains); free GLM-5.3-Flash lives on NVIDIA NIM / Pollinations / OrcaRouter
833
+ // Removed (2026-10-17 audit): stepfun/step-3.7-flash:free (Step 3.7 Flash) — in the provider's removed list; no step-5-preview on onomeo either
834
+ // Removed (2026-10-17 audit): glm-4.7-flash (GLM 4.7 Flash) — delisted, absent from the current models page; free route is @cf/zai-org/glm-4.7-flash on Cloudflare
776
835
  ['gemini-3.5-flash-lite', 'Gemini 3.5 Flash Lite', 'S', '-', '1M'], // Added (2026-09-29 audit) — in the free pool since 2026-09-23; tier follows the same model on googleai
777
836
  // ── A tier — SWE-bench Verified 40–50% ──
778
837
  ['codestral-latest', 'Codestral Latest', 'A', '40.0%', '256k'],
779
838
  ['glm-4.5-flash', 'GLM 4.5 Flash', 'A', '-', '131k'], // Added (2026-09-29 audit) — in the free pool since 2026-09-28
780
- ['glm-4.6v-flash', 'GLM 4.6V Flash', 'A', '-', '128k'], // Added (2026-09-29 audit) — in the free pool since 2026-09-28; vision model
839
+ // Removed (2026-10-17 audit): glm-4.6v-flash (GLM 4.6V Flash) — delisted, absent from the current models page; no other free GLM vision model offered
781
840
  ['ministral-14b-latest', 'Ministral 3 14B', 'A', '-', '262k'], // Added (2026-09-29 audit) — in the free pool since 2026-09-23
782
- // Added (2026-09-28 audit) — 16 new free models, catalog grown to 25 on https://onomeo.com/api/info:
783
- // ── S tier ──
784
- ['inclusionai/ling-3.0-flash-sante:free', 'Ling 3.0 Flash Sante', 'S', '-', '256k'],
785
- // ── A+ tier ──
786
- ['dots-studio/dots-3-note-preview:free', 'Dots 3 Note Preview', 'A+', '-', '512k'],
787
- ['sensenova-6.8-flash-lite', 'SenseNova 6.8 Flash Lite', 'A+', '-', '256k'],
788
- ['minimax-m2.7', 'MiniMax M2.7', 'A+', '-', '200k'],
789
- ['inclusionai/ling-3.0-flash-fin:free', 'Ling 3.0 Flash Fin', 'A+', '-', '256k'],
790
- // ── A tier ──
791
- ['meta/muse-glimmer-30b', 'Muse Glimmer 30B', 'A', '-', '128k'],
792
- ['gemini-3-flash-preview', 'Gemini 3 Flash Preview', 'A', '-', '1M'],
793
- ['mimo-v2.5:free', 'MiMo v2.5', 'A', '-', '1M'],
794
- ['stealth/space-bunny-alpha', 'Space Bunny Alpha', 'A', '-', '1M'],
841
+ ['muse-glimmer-30b', 'Muse Glimmer 30B', 'A', '-', '131k'], // Fixed (2026-10-10 audit): id 'meta/muse-glimmer-30b' → 'muse-glimmer-30b' (first-party rename) + ctx '128k' → '131k'
842
+ ['minimax-m2.7', 'MiniMax M2.7', 'A+', '-', '205k'], // Fixed (2026-10-10 audit): ctx '200k' → '205k' (live catalog); still listed but upstream-paused
843
+ ['stealth/glyph-cluster', 'Glyph Cluster', 'A+', '-', '-'], // Added (2026-10-17 audit) — new stealth free model replacing the delisted space-bunny-alpha; tier follows the same stealth model on kilo/vercel-gateway, ctx unpublished on onomeo
844
+ // Removed (2026-10-17 audit): stealth/space-bunny-alpha — delisted, replaced by the new stealth/glyph-cluster slot
845
+ // Removed (2026-10-10 audit): inclusionai/ling-3.0-flash-sante:free + inclusionai/ling-3.0-flash-fin:free — sante in the provider's removed list (successor ling-3.1-flash also removed upstream), fin absent from the live catalog entirely
846
+ // Removed (2026-10-10 audit): dots-studio/dots-3-note-preview:free + sensenova-6.8-flash-lite + gemini-3-flash-preview + mimo-v2.5:free — dots-3/gemini-3-flash-preview/mimo in the provider's removed list (gemini superseded by the 3.5/3.6/3.8 flash family), sensenova zero occurrences in the live catalog payload
847
+ // Removed (2026-10-10 audit): nex-agi/nex-n2.5-mini:free + nex-agi/nex-n2.5-pro:free + Shanghai_AI_Laboratory/Intern-S2-Preview — all three in the provider's removed list (they were the modelsPaused re-verify set of the 2026-09-29 audit: verdict is now removal)
795
848
  // ── A- tier ──
796
- ['nex-agi/nex-n2.5-mini:free', 'Nex N2.5 Mini', 'A-', '-', '256k'], // Fixed (2026-09-29 audit): ctx '-' → '256k' (modelFacts 262144)
797
- ['Shanghai_AI_Laboratory/Intern-S2-Preview', 'Intern S2 Preview', 'A-', '-', '-'],
798
- ['nex-agi/nex-n2.5-pro:free', 'Nex N2.5 Pro', 'A-', '-', '256k'], // Fixed (2026-09-29 audit): ctx '-' → '256k' (modelFacts 262144)
799
- // 2026-09-29 audit note: 7 catalog models are in onomeo's modelsPaused list (gpt-oss-120b, ling-fin, mimo-v2.5, nex pair, Intern-S2, hy3-free) but still tracked by the API - kept, re-verify next audit
800
- // ── B+ tier ──
801
- ['tencent/hy3-free', 'Hunyuan 3 Free', 'B+', '-', '256k'],
802
- ['nvidia/nemotron-3.5-lightning-30b-a3b', 'Nemotron 3.5 Lightning 30B', 'B+', '-', '256k'],
803
- ['poolside/laguna-s-2.1:free', 'Laguna S 2.1', 'B+', '-', '1M'],
804
- // ── B tier ──
805
- ['cohere/north-mini-code:free', 'North Mini Code', 'B', '-', '256k'],
849
+ ['hy4-preview', 'Hunyuan 4 Preview', 'A-', '-', '1M'], // Added (2026-10-10 audit) — new free model (~Oct 4) on the live catalog; replaces the removed hy3-free slot; 1M ctx
850
+ // Removed (2026-10-10 audit): tencent/hy3-free (Hunyuan 3 Free) — in the provider's removed list; replacement: hy4-preview
851
+ // Removed (2026-10-10 audit): nvidia/nemotron-3.5-lightning-30b-a3b + poolside/laguna-s-2.1:free + cohere/north-mini-code:free — all three in the provider's removed list
806
852
  ]
807
853
 
808
854
  // 📖 All sources combined - used by the main script
@@ -832,8 +878,8 @@ export const sources = {
832
878
  cerebras: {
833
879
  name: 'Cerebras',
834
880
  url: 'https://api.cerebras.ai/v1/chat/completions',
835
- quota: 'Free · generous dev tier',
836
- quotaCode: 'free',
881
+ quota: 'Free trial · $5 credits / 30 days · card required',
882
+ quotaCode: 'limited',
837
883
  models: cerebras,
838
884
  },
839
885
  googleai: {
@@ -895,13 +941,16 @@ export const sources = {
895
941
  quotaCode: 'free',
896
942
  models: codestral,
897
943
  },
898
- zai: {
899
- name: 'ZAI',
900
- url: 'https://api.z.ai/api/coding/paas/v4/chat/completions',
901
- quota: 'Free · Flash models only',
902
- quotaCode: 'free',
903
- models: zai,
904
- },
944
+ // 'zai': REMOVED 2026-10-17 — GLM Coding Plan free window ended 2026-10-07, plan is
945
+ // paid-only now (no free model left on the coding endpoint). Provider metadata and
946
+ // ZAI_API_KEY support stay in src/core for backwards compat with existing configs.
947
+ // 'zai': {
948
+ // name: 'ZAI',
949
+ // url: 'https://api.z.ai/api/coding/paas/v4/chat/completions',
950
+ // quota: 'Free · Flash models only',
951
+ // quotaCode: 'free',
952
+ // models: zai,
953
+ // },
905
954
  scaleway: {
906
955
  name: 'Scaleway',
907
956
  url: 'https://api.scaleway.ai/v1/chat/completions',
@@ -951,7 +1000,7 @@ export const sources = {
951
1000
  novita: {
952
1001
  name: 'Novita AI',
953
1002
  url: 'https://api.novita.ai/openai/v1/chat/completions',
954
- quota: 'Free tier is back · 5 zero-price models · 2026-09-29',
1003
+ quota: 'Free tier shrank · 2 zero-price models left',
955
1004
  quotaCode: 'limited',
956
1005
  models: novita,
957
1006
  },
@@ -1000,7 +1049,7 @@ export const sources = {
1000
1049
  onomeo: {
1001
1050
  name: 'onomeo',
1002
1051
  url: 'https://onomeo.com/v1/chat/completions',
1003
- quota: 'Free models, no credits · 12 RPM · 60 req/5h',
1052
+ quota: 'Free models, no credits · 12 RPM · 30 req/5h',
1004
1053
  quotaCode: 'limited',
1005
1054
  models: onomeo,
1006
1055
  },