SPB Git forge

spb/polyllm

Public
15commits 1branches 0releases
2.2 MBsize
maindefault branch
13 days agolast push
TypeScript 97.4% SQL 1% JavaScript 0.9% CSS 0.6%
19.5 KB · 727 lines json
Raw Blame History
1[2 {3  "id": "gemini-3.8-flash",4  "displayName": "Gemini 3.8 Flash",5  "family": "gemini-3.x-flash",6  "contextTokens": 1048576,7  "maxOutputTokens": 65536,8  "thinking": true,9  "status": "active",10  "capabilities": {11   "text": true,12   "vision": true,13   "audioInput": true,14   "audioOutput": false,15   "imageGeneration": false,16   "video": true,17   "reasoning": true,18   "tools": true,19   "structuredOutput": true,20   "streaming": true,21   "files": true,22   "webSearch": true23  },24  "pricing": {25   "inputPerMillion": 0.75,26   "cachedInputPerMillion": 0.075,27   "outputPerMillion": 3.7528  },29  "pricingNote": "introductory through 2026-12-31; from 2027-01-01: 1.50 / 0.15 / 7.50. >200k-token prompts not tiered.",30  "thinkingProfile": {31   "mode": "level",32   "levels": [33    "low",34    "medium",35    "high"36   ],37   "none": null38  },39  "chat": true,40  "notes": "Stable, released 2026-09-02. Probed: generateContent+systemInstruction OK, vision OK (2x2 PNG = 1089 image tokens), temperature 0/1.5/2 OK, candidateCount=2 -> 400, logprobs -> 400. Default thinkingLevel medium; 'minimal' returns an error (docs). Free tier: 20 requests/day (quotaValue=20 seen in 429"41 },42 {43  "id": "gemini-3.7-flash",44  "displayName": "Gemini 3.7 Flash",45  "family": "gemini-3.x-flash",46  "contextTokens": 1048576,47  "maxOutputTokens": 65536,48  "thinking": true,49  "status": "active",50  "capabilities": {51   "text": true,52   "vision": true,53   "audioInput": true,54   "audioOutput": false,55   "imageGeneration": false,56   "video": true,57   "reasoning": true,58   "tools": true,59   "structuredOutput": true,60   "streaming": true,61   "files": true,62   "webSearch": true63  },64  "pricing": {65   "inputPerMillion": 0.75,66   "cachedInputPerMillion": 0.075,67   "outputPerMillion": 3.7568  },69  "pricingNote": "same as 3.8 Flash: introductory through 2026-12-31, then 1.50 / 0.15 / 7.50",70  "thinkingProfile": {71   "mode": "level",72   "levels": [73    "low",74    "medium",75    "high"76   ],77   "none": null78  },79  "chat": true,80  "notes": "Stable, Aug 2026. Probed: generateContent+systemInstruction OK; stream 3 chunks with full usageMetadata on every chunk; function call round trip OK; thought signature on functionCall part is MANDATORY (400 'Function call is missing a thought_signature in functionCall parts...' when omitted; dummy 's"81 },82 {83  "id": "gemini-3.6-flash",84  "displayName": "Gemini 3.6 Flash",85  "family": "gemini-3.x-flash",86  "contextTokens": 1048576,87  "maxOutputTokens": 65536,88  "thinking": true,89  "status": "active",90  "capabilities": {91   "text": true,92   "vision": true,93   "audioInput": true,94   "audioOutput": false,95   "imageGeneration": false,96   "video": true,97   "reasoning": true,98   "tools": true,99   "structuredOutput": true,100   "streaming": true,101   "files": true,102   "webSearch": true103  },104  "pricing": {105   "inputPerMillion": 0.75,106   "cachedInputPerMillion": 0.075,107   "outputPerMillion": 3.75108  },109  "pricingNote": "same as 3.8 Flash: introductory through 2026-12-31, then 1.50 / 0.15 / 7.50",110  "thinkingProfile": {111   "mode": "level",112   "levels": [113    "minimal",114    "low",115    "medium",116    "high"117   ],118   "none": "MINIMAL"119  },120  "chat": true,121  "notes": "Stable, July 2026. Probed: generateContent OK; stream 4 chunks (thought summary chunk first when includeThoughts, last chunk = empty text part carrying thoughtSignature + finishReason STOP); function call streaming (1 chunk with functionCall+thoughtSignature+id, then final empty chunk) and round tri"122 },123 {124  "id": "gemini-3.5-flash",125  "displayName": "Gemini 3.5 Flash",126  "family": "gemini-3.x-flash",127  "contextTokens": 1048576,128  "maxOutputTokens": 65536,129  "thinking": true,130  "status": "active",131  "capabilities": {132   "text": true,133   "vision": true,134   "audioInput": true,135   "audioOutput": false,136   "imageGeneration": false,137   "video": true,138   "reasoning": true,139   "tools": true,140   "structuredOutput": true,141   "streaming": true,142   "files": true,143   "webSearch": true144  },145  "pricing": {146   "inputPerMillion": 1.5,147   "cachedInputPerMillion": 0.15,148   "outputPerMillion": 9.0149  },150  "pricingNote": null,151  "thinkingProfile": {152   "mode": "level",153   "levels": [154    "minimal",155    "low",156    "medium",157    "high"158   ],159   "none": "budget0"160  },161  "chat": true,162  "notes": "GA May 2026; current target of gemini-flash-latest per changelog. Probed: systemInstruction OK, stream 3 chunks (first chunk usage has only promptTokenCount; later chunks full), includeThoughts -> parts with thought:true, function call streaming + round trip OK (functionCall has id 'call_...'), resp"163 },164 {165  "id": "gemini-3.5-flash-lite",166  "displayName": "Gemini 3.5 Flash-Lite",167  "family": "gemini-3.x-flash-lite",168  "contextTokens": 1048576,169  "maxOutputTokens": 65536,170  "thinking": true,171  "status": "active",172  "capabilities": {173   "text": true,174   "vision": true,175   "audioInput": true,176   "audioOutput": false,177   "imageGeneration": false,178   "video": true,179   "reasoning": true,180   "tools": true,181   "structuredOutput": true,182   "streaming": true,183   "files": true,184   "webSearch": true185  },186  "pricing": {187   "inputPerMillion": 0.3,188   "cachedInputPerMillion": 0.03,189   "outputPerMillion": 2.5190  },191  "pricingNote": null,192  "thinkingProfile": {193   "mode": "level",194   "levels": [195    "minimal",196    "low",197    "medium",198    "high"199   ],200   "none": "omit"201  },202  "chat": true,203  "notes": "Stable, July 2026; default thinking OFF (thoughtsTokenCount 0 unless thinkingLevel/thinkingBudget set). Full param matrix probed: all thinkingLevel values OK (minimal=0 thoughts), thinkingLevel+thinkingBudget together -> 400 'You can only set only one of thinking budget and thinking level.', penalti"204 },205 {206  "id": "gemini-3.1-flash-lite",207  "displayName": "Gemini 3.1 Flash-Lite",208  "family": "gemini-3.x-flash-lite",209  "contextTokens": 1048576,210  "maxOutputTokens": 65536,211  "thinking": true,212  "status": "active",213  "capabilities": {214   "text": true,215   "vision": true,216   "audioInput": true,217   "audioOutput": false,218   "imageGeneration": false,219   "video": true,220   "reasoning": true,221   "tools": true,222   "structuredOutput": true,223   "streaming": true,224   "files": true,225   "webSearch": true226  },227  "pricing": {228   "inputPerMillion": 0.25,229   "cachedInputPerMillion": null,230   "outputPerMillion": 1.5231  },232  "pricingNote": "audio input 0.50/M; cached price not listed on pricing page",233  "thinkingProfile": {234   "mode": "level",235   "levels": [236    "minimal",237    "low",238    "medium",239    "high"240   ],241   "none": "budget0"242  },243  "chat": true,244  "notes": "GA May 2026; default thinkingLevel minimal (thinking off). Full param matrix probed: same acceptance pattern as 3.5-flash-lite except thinkingBudget 0 is accepted. Function calling + responseJsonSchema OK. gemini-3.1-flash-lite-preview alias still answers and reports modelVersion gemini-3.1-flash-li"245 },246 {247  "id": "gemini-3-flash-preview",248  "displayName": "Gemini 3 Flash Preview",249  "family": "gemini-3.x-flash",250  "contextTokens": 1048576,251  "maxOutputTokens": 65536,252  "thinking": true,253  "status": "preview",254  "capabilities": {255   "text": true,256   "vision": true,257   "audioInput": true,258   "audioOutput": false,259   "imageGeneration": false,260   "video": true,261   "reasoning": true,262   "tools": true,263   "structuredOutput": true,264   "streaming": true,265   "files": true,266   "webSearch": true267  },268  "pricing": {269   "inputPerMillion": 0.5,270   "cachedInputPerMillion": null,271   "outputPerMillion": 3.0272  },273  "pricingNote": "audio input 1.00/M",274  "thinkingProfile": {275   "mode": "level",276   "levels": [277    "minimal",278    "low",279    "medium",280    "high"281   ],282   "none": "budget0"283  },284  "chat": true,285  "notes": "Dec 2025 preview; superseded by gemini-3.5-flash (stable). Default thinking high (dynamic). Param matrix probed except thinkingLevel low / logprobs (429). No shutdown date published."286 },287 {288  "id": "gemini-3.1-pro-preview",289  "displayName": "Gemini 3.1 Pro Preview",290  "family": "gemini-3.x-pro",291  "contextTokens": 1048576,292  "maxOutputTokens": 65536,293  "thinking": true,294  "status": "preview",295  "capabilities": {296   "text": true,297   "vision": true,298   "audioInput": true,299   "audioOutput": false,300   "imageGeneration": false,301   "video": true,302   "reasoning": true,303   "tools": true,304   "structuredOutput": true,305   "streaming": true,306   "files": true,307   "webSearch": true308  },309  "pricing": {310   "inputPerMillion": 2.0,311   "cachedInputPerMillion": 0.2,312   "outputPerMillion": 12.0313  },314  "pricingNote": ">200k prompt: 4.00 in / 0.40 cached / 18.00 out; storage 4.50/M/hr",315  "thinkingProfile": {316   "mode": "level",317   "levels": [318    "low",319    "medium",320    "high"321   ],322   "none": null323  },324  "chat": true,325  "notes": "PAID TIER ONLY: free-tier quota is 0 (429 RESOURCE_EXHAUSTED 'limit: 0', quotaId GenerateRequestsPerDayPerProjectPerModel-FreeTier). Not probed beyond that. Default thinkingLevel high. gemini-pro-latest currently resolves here (also 429 limit 0 on free tier). Google's recommended replacement for gem"326 },327 {328  "id": "gemini-3.1-pro-preview-customtools",329  "displayName": "Gemini 3.1 Pro Preview (custom tools)",330  "family": "gemini-3.x-pro",331  "contextTokens": 1048576,332  "maxOutputTokens": 65536,333  "thinking": true,334  "status": "preview",335  "capabilities": {336   "text": true,337   "vision": true,338   "audioInput": true,339   "audioOutput": false,340   "imageGeneration": false,341   "video": true,342   "reasoning": true,343   "tools": true,344   "structuredOutput": true,345   "streaming": true,346   "files": true,347   "webSearch": true348  },349  "pricing": {350   "inputPerMillion": 2.0,351   "cachedInputPerMillion": 0.2,352   "outputPerMillion": 12.0353  },354  "pricingNote": "assumed same as gemini-3.1-pro-preview (not separately listed)",355  "thinkingProfile": {356   "mode": "level",357   "levels": [358    "low",359    "medium",360    "high"361   ],362   "none": null363  },364  "chat": true,365  "notes": "Variant that prioritises custom (function) tools over built-ins in agentic/bash workflows; 'may see quality fluctuations'. Paid tier only (429 limit 0 on free tier). Not probed."366 },367 {368  "id": "gemini-2.5-pro",369  "displayName": "Gemini 2.5 Pro",370  "family": "gemini-2.5",371  "contextTokens": 1048576,372  "maxOutputTokens": 65536,373  "thinking": true,374  "status": "deprecated",375  "capabilities": {376   "text": true,377   "vision": true,378   "audioInput": true,379   "audioOutput": false,380   "imageGeneration": false,381   "video": true,382   "reasoning": true,383   "tools": true,384   "structuredOutput": true,385   "streaming": true,386   "files": true,387   "webSearch": true388  },389  "pricing": {390   "inputPerMillion": 1.25,391   "cachedInputPerMillion": 0.125,392   "outputPerMillion": 10.0393  },394  "pricingNote": ">200k prompt: 2.50 / 0.25 / 15.00; paid tier only",395  "thinkingProfile": {396   "mode": "budget"397  },398  "chat": true,399  "notes": "LISTED by /v1beta/models but generateContent returns 404 NOT_FOUND: 'This model models/gemini-2.5-pro is no longer available to new users. Please update your code to use models/gemini-3.1-pro-preview ... We recommend you to use the Interactions API.' Only pre-existing users can call it. Knowledge cu"400 },401 {402  "id": "gemini-2.5-flash",403  "displayName": "Gemini 2.5 Flash",404  "family": "gemini-2.5",405  "contextTokens": 1048576,406  "maxOutputTokens": 65536,407  "thinking": true,408  "status": "deprecated",409  "capabilities": {410   "text": true,411   "vision": true,412   "audioInput": true,413   "audioOutput": false,414   "imageGeneration": false,415   "video": true,416   "reasoning": true,417   "tools": true,418   "structuredOutput": true,419   "streaming": true,420   "files": true,421   "webSearch": true422  },423  "pricing": {424   "inputPerMillion": 0.3,425   "cachedInputPerMillion": 0.03,426   "outputPerMillion": 2.5427  },428  "pricingNote": "audio input 1.00/M, cached audio 0.10/M",429  "thinkingProfile": {430   "mode": "budget"431  },432  "chat": true,433  "notes": "LISTED by /v1beta/models but generateContent, streamGenerateContent, cachedContents.create all return 404 'no longer available to new users' -> use gemini-3.6-flash. Only grandfathered keys can use it. Knowledge cutoff Jan 2025."434 },435 {436  "id": "gemini-2.5-flash-lite",437  "displayName": "Gemini 2.5 Flash-Lite",438  "family": "gemini-2.5",439  "contextTokens": 1048576,440  "maxOutputTokens": 65536,441  "thinking": true,442  "status": "deprecated",443  "capabilities": {444   "text": true,445   "vision": true,446   "audioInput": true,447   "audioOutput": false,448   "imageGeneration": false,449   "video": true,450   "reasoning": true,451   "tools": true,452   "structuredOutput": true,453   "streaming": true,454   "files": true,455   "webSearch": true456  },457  "pricing": {458   "inputPerMillion": 0.1,459   "cachedInputPerMillion": 0.01,460   "outputPerMillion": 0.4461  },462  "pricingNote": "audio input 0.30/M",463  "thinkingProfile": {464   "mode": "budget"465  },466  "chat": true,467  "notes": "LISTED but 404 'no longer available to new users' -> use gemini-3.5-flash-lite (probed via chats + safetySettings probes)."468 },469 {470  "id": "gemini-flash-latest",471  "displayName": "Gemini Flash (latest alias)",472  "family": "alias",473  "contextTokens": 1048576,474  "maxOutputTokens": 65536,475  "thinking": true,476  "status": "active",477  "capabilities": {478   "text": true,479   "vision": true,480   "audioInput": true,481   "audioOutput": false,482   "imageGeneration": false,483   "video": true,484   "reasoning": true,485   "tools": true,486   "structuredOutput": true,487   "streaming": true,488   "files": true,489   "webSearch": true490  },491  "pricing": {492   "inputPerMillion": 1.5,493   "cachedInputPerMillion": 0.15,494   "outputPerMillion": 9.0495  },496  "pricingNote": "billed as the model it resolves to (currently gemini-3.5-flash per changelog May 2026); not listed on pricing page",497  "thinkingProfile": {498   "mode": "level",499   "levels": [500    "minimal",501    "low",502    "medium",503    "high"504   ],505   "none": "budget0"506  },507  "chat": true,508  "notes": "Hot-swapped alias; Google gives 2 weeks' email notice before re-pointing. Probe returned 503 'high demand' (transient) so resolution not confirmed live; changelog says gemini-3.5-flash. Avoid as default in a registry: pin explicit ids and show alias as convenience."509 },510 {511  "id": "gemini-flash-lite-latest",512  "displayName": "Gemini Flash-Lite (latest alias)",513  "family": "alias",514  "contextTokens": 1048576,515  "maxOutputTokens": 65536,516  "thinking": true,517  "status": "active",518  "capabilities": {519   "text": true,520   "vision": true,521   "audioInput": true,522   "audioOutput": false,523   "imageGeneration": false,524   "video": true,525   "reasoning": true,526   "tools": true,527   "structuredOutput": true,528   "streaming": true,529   "files": true,530   "webSearch": true531  },532  "pricing": {533   "inputPerMillion": 0.3,534   "cachedInputPerMillion": 0.03,535   "outputPerMillion": 2.5536  },537  "pricingNote": "billed as gemini-3.5-flash-lite (probe modelVersion = gemini-3.5-flash-lite)",538  "thinkingProfile": {539   "mode": "level",540   "levels": [541    "minimal",542    "low",543    "medium",544    "high"545   ],546   "none": "omit"547  },548  "chat": true,549  "notes": "Probed: resolves to gemini-3.5-flash-lite (modelVersion). Used for the raw REST SSE probe (works)."550 },551 {552  "id": "gemini-pro-latest",553  "displayName": "Gemini Pro (latest alias)",554  "family": "alias",555  "contextTokens": 1048576,556  "maxOutputTokens": 65536,557  "thinking": true,558  "status": "active",559  "capabilities": {560   "text": true,561   "vision": true,562   "audioInput": true,563   "audioOutput": false,564   "imageGeneration": false,565   "video": true,566   "reasoning": true,567   "tools": true,568   "structuredOutput": true,569   "streaming": true,570   "files": true,571   "webSearch": true572  },573  "pricing": {574   "inputPerMillion": 2.0,575   "cachedInputPerMillion": 0.2,576   "outputPerMillion": 12.0577  },578  "pricingNote": "billed as the resolved model (429 quota dimension showed model=gemini-3.1-pro -> resolves to 3.1 Pro preview)",579  "thinkingProfile": {580   "mode": "level",581   "levels": [582    "low",583    "medium",584    "high"585   ],586   "none": null587  },588  "chat": true,589  "notes": "Paid tier only (free-tier 429 limit 0, quota dimension model=gemini-3.1-pro)."590 },591 {592  "id": "gemma-4-31b-it",593  "displayName": "Gemma 4 31B (instruction-tuned)",594  "family": "gemma-4",595  "contextTokens": 262144,596  "maxOutputTokens": 32768,597  "thinking": true,598  "status": "active",599  "capabilities": {600   "text": true,601   "vision": "docs: image/video/audio input supported by Gemma 4; not probed on the API",602   "audioInput": null,603   "audioOutput": false,604   "imageGeneration": false,605   "video": null,606   "reasoning": true,607   "tools": "docs: yes; not probed",608   "structuredOutput": true,609   "streaming": true,610   "files": null,611   "webSearch": false612  },613  "pricing": {614   "inputPerMillion": 0,615   "cachedInputPerMillion": null,616   "outputPerMillion": 0617  },618  "pricingNote": "Free tier: 'Free of charge' (data used for product improvement). Paid tier: 'Not available'.",619  "thinkingProfile": {620   "mode": "none"621  },622  "chat": true,623  "notes": "Open model served on Gemini API. Thinks by default (thoughtsTokenCount 47-430) but thinkingConfig is rejected: thinkingBudget -> 400 'Thinking budget is not supported for this model.'; thinkingLevel -> 400 'Thinking level is not supported for this model.' responseSchema / responseJsonSchema / text/x"624 },625 {626  "id": "gemma-4-26b-a4b-it",627  "displayName": "Gemma 4 26B A4B (MoE, instruction-tuned)",628  "family": "gemma-4",629  "contextTokens": 262144,630  "maxOutputTokens": 32768,631  "thinking": true,632  "status": "active",633  "capabilities": {634   "text": true,635   "vision": null,636   "audioInput": null,637   "audioOutput": false,638   "imageGeneration": false,639   "video": null,640   "reasoning": true,641   "tools": null,642   "structuredOutput": null,643   "streaming": true,644   "files": null,645   "webSearch": false646  },647  "pricing": {648   "inputPerMillion": 0,649   "cachedInputPerMillion": null,650   "outputPerMillion": 0651  },652  "pricingNote": "free tier only",653  "thinkingProfile": {654   "mode": "none"655  },656  "chat": true,657  "notes": "Probed once: 'pong' OK with 58 thought tokens. Assume same behaviour as gemma-4-31b-it (unknowns = null)."658 },659 {660  "id": "gemini-omni-1.1-flash",661  "displayName": "Gemini Omni 1.1 Flash",662  "family": "gemini-omni",663  "contextTokens": 131072,664  "maxOutputTokens": 65536,665  "thinking": true,666  "status": "active",667  "capabilities": {668   "text": "docs: text output priced (9.00/M) but model card says output = video only",669   "vision": true,670   "audioInput": true,671   "audioOutput": false,672   "imageGeneration": false,673   "video": true,674   "reasoning": true,675   "tools": null,676   "structuredOutput": null,677   "streaming": null,678   "files": null,679   "webSearch": false680  },681  "pricing": {682   "inputPerMillion": 1.5,683   "cachedInputPerMillion": null,684   "outputPerMillion": 9.0685  },686  "pricingNote": "video output 17.50/M (~0.10/s); paid tier only",687  "thinkingProfile": {688   "mode": "none"689  },690  "chat": false,691  "notes": "Video-generation model (GA Aug 2026; 3-10 s clips, 360p-4K). Models endpoint says inputTokenLimit 131072 (model card says 1,048,576 \u2014 endpoint value preferred). PAID TIER ONLY: free tier 429 'limit: 0'. Not usable for chat; exclude from the chat model picker or gate behind paid-tier detection."692 },693 {694  "id": "gemini-omni-flash-preview",695  "displayName": "Gemini Omni Flash Preview",696  "family": "gemini-omni",697  "contextTokens": 131072,698  "maxOutputTokens": 65536,699  "thinking": true,700  "status": "preview",701  "capabilities": {702   "text": null,703   "vision": true,704   "audioInput": true,705   "audioOutput": false,706   "imageGeneration": false,707   "video": true,708   "reasoning": true,709   "tools": null,710   "structuredOutput": null,711   "streaming": null,712   "files": null,713   "webSearch": false714  },715  "pricing": {716   "inputPerMillion": 1.5,717   "cachedInputPerMillion": null,718   "outputPerMillion": 9.0719  },720  "pricingNote": "video output 17.50/M; paid tier only",721  "thinkingProfile": {722   "mode": "none"723  },724  "chat": false,725  "notes": "Preview predecessor of gemini-omni-1.1-flash (June 2026). Free tier 429 'limit: 0'. Not a chat model."726 }727]