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%
23.4 KB · 232 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    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },9    "parameters": { "temperature": "0-2 (accepted; Google recommends leaving 1.0; deprecated for 3.6+ per changelog 2026-07-21)", "topP": true, "topK": true, "maxTokens": true, "reasoningEffort": ["low", "medium", "high"], "thinkingBudget": "docs: legacy, replace with thinkingLevel; not probed (free-tier RPD=20 exhausted)", "stop": true, "seed": true, "frequencyPenalty": false, "presencePenalty": false },10    "pricing": { "inputPerMillion": 0.75, "cachedInputPerMillion": 0.075, "outputPerMillion": 3.75, "note": "introductory through 2026-12-31; from 2027-01-01: 1.50 / 0.15 / 7.50. >200k-token prompts not tiered." },11    "status": "active",12    "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). Thinking tokens count against maxOutputTokens (maxOutputTokens=100 gave empty text, finishReason MAX_TOKENS, 97 thought tokens)."13  },14  {15    "id": "gemini-3.7-flash",16    "displayName": "Gemini 3.7 Flash",17    "family": "gemini-3.x-flash",18    "contextTokens": 1048576,19    "maxOutputTokens": 65536,20    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },21    "parameters": { "temperature": "0-2 (deprecated, keep 1.0)", "topP": true, "topK": true, "maxTokens": true, "reasoningEffort": ["low", "medium", "high"], "thinkingBudget": "docs-only: legacy", "stop": "docs-only", "seed": "docs-only", "frequencyPenalty": false, "presencePenalty": false },22    "pricing": { "inputPerMillion": 0.75, "cachedInputPerMillion": 0.075, "outputPerMillion": 3.75, "note": "same as 3.8 Flash: introductory through 2026-12-31, then 1.50 / 0.15 / 7.50" },23    "status": "active",24    "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 'skip_thought_signature_validator' accepted); text-only multi-turn without signatures OK. Param matrix not probed (family assumed = 3.8)."25  },26  {27    "id": "gemini-3.6-flash",28    "displayName": "Gemini 3.6 Flash",29    "family": "gemini-3.x-flash",30    "contextTokens": 1048576,31    "maxOutputTokens": 65536,32    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },33    "parameters": { "temperature": "0-2 (deprecated per changelog 2026-07-21, keep 1.0)", "topP": "deprecated", "topK": "deprecated", "maxTokens": true, "reasoningEffort": ["minimal", "low", "medium", "high"], "thinkingBudget": "docs-only: legacy", "stop": "docs-only", "seed": "docs-only", "frequencyPenalty": false, "presencePenalty": false },34    "pricing": { "inputPerMillion": 0.75, "cachedInputPerMillion": 0.075, "outputPerMillion": 3.75, "note": "same as 3.8 Flash: introductory through 2026-12-31, then 1.50 / 0.15 / 7.50" },35    "status": "active",36    "status_note": "Google's recommended replacement for gemini-2.5-flash (404 message).",37    "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 trip OK; responseJsonSchema OK; codeExecution tool OK (executableCode{language:'PYTHON',code,id} + codeExecutionResult{outcome:'OUTCOME_OK',output,id}); googleSearch probe hit 429 (unverified). Param matrix not probed."38  },39  {40    "id": "gemini-3.5-flash",41    "displayName": "Gemini 3.5 Flash",42    "family": "gemini-3.x-flash",43    "contextTokens": 1048576,44    "maxOutputTokens": 65536,45    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },46    "parameters": { "temperature": "0-2 probed OK (2.5 -> 400)", "topP": true, "topK": true, "maxTokens": true, "reasoningEffort": "docs: minimal/low/medium/high (default medium); levels not probed (429)", "thinkingBudget": "0 probed OK (disables thinking); 1024/-1 not probed (429)", "stop": true, "seed": true, "frequencyPenalty": false, "presencePenalty": false },47    "pricing": { "inputPerMillion": 1.5, "cachedInputPerMillion": 0.15, "outputPerMillion": 9.0 },48    "status": "active",49    "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_...'), responseMimeType json / responseSchema / responseJsonSchema / text/x.enum OK, penalties -> 400 'Penalty is not enabled for this model', candidateCount=2 -> 400, vision OK. Free tier RPD low (~20)."50  },51  {52    "id": "gemini-3.5-flash-lite",53    "displayName": "Gemini 3.5 Flash-Lite",54    "family": "gemini-3.x-flash-lite",55    "contextTokens": 1048576,56    "maxOutputTokens": 65536,57    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },58    "parameters": { "temperature": "0-2 probed OK (deprecated per changelog 2026-07-21)", "topP": true, "topK": true, "maxTokens": true, "reasoningEffort": ["minimal", "low", "medium", "high"], "thinkingBudget": "1024 and -1 OK; 0 -> 400 'Request contains an invalid argument.' (use thinkingLevel MINIMAL to disable)", "stop": true, "seed": true, "frequencyPenalty": false, "presencePenalty": false },59    "pricing": { "inputPerMillion": 0.3, "cachedInputPerMillion": 0.03, "outputPerMillion": 2.5 },60    "status": "active",61    "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.', penalties/candidateCount/logprobs -> 400. Function calling + responseJsonSchema OK. gemini-flash-lite-latest currently resolves here (modelVersion)."62  },63  {64    "id": "gemini-3.1-flash-lite",65    "displayName": "Gemini 3.1 Flash-Lite",66    "family": "gemini-3.x-flash-lite",67    "contextTokens": 1048576,68    "maxOutputTokens": 65536,69    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },70    "parameters": { "temperature": "0-2 probed OK", "topP": true, "topK": true, "maxTokens": true, "reasoningEffort": ["minimal", "low", "medium", "high"], "thinkingBudget": "0 / 1024 / -1 all OK", "stop": true, "seed": true, "frequencyPenalty": false, "presencePenalty": false },71    "pricing": { "inputPerMillion": 0.25, "cachedInputPerMillion": null, "outputPerMillion": 1.5, "note": "audio input 0.50/M; cached price not listed on pricing page" },72    "status": "active",73    "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-lite (changelog says preview shut down 2026-05-25)."74  },75  {76    "id": "gemini-3-flash-preview",77    "displayName": "Gemini 3 Flash Preview",78    "family": "gemini-3.x-flash",79    "contextTokens": 1048576,80    "maxOutputTokens": 65536,81    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },82    "parameters": { "temperature": "0-2 probed OK", "topP": true, "topK": true, "maxTokens": true, "reasoningEffort": ["minimal", "low", "medium", "high"], "thinkingBudget": "0 / 1024 / -1 all OK (-1 produced 1436 thought tokens)", "stop": true, "seed": true, "frequencyPenalty": false, "presencePenalty": false },83    "pricing": { "inputPerMillion": 0.5, "cachedInputPerMillion": null, "outputPerMillion": 3.0, "note": "audio input 1.00/M" },84    "status": "preview",85    "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."86  },87  {88    "id": "gemini-3.1-pro-preview",89    "displayName": "Gemini 3.1 Pro Preview",90    "family": "gemini-3.x-pro",91    "contextTokens": 1048576,92    "maxOutputTokens": 65536,93    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },94    "parameters": { "temperature": "0-2 (2.5 -> 400 probed; keep 1.0)", "topP": "docs-only", "topK": "docs-only", "maxTokens": true, "reasoningEffort": ["minimal", "low", "medium", "high"], "thinkingBudget": "docs-only: legacy", "stop": "docs-only", "seed": "docs-only", "frequencyPenalty": "docs-only (family pattern: rejected)", "presencePenalty": "docs-only (family pattern: rejected)" },95    "pricing": { "inputPerMillion": 2.0, "cachedInputPerMillion": 0.2, "outputPerMillion": 12.0, "note": ">200k prompt: 4.00 in / 0.40 cached / 18.00 out; storage 4.50/M/hr" },96    "status": "preview",97    "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 gemini-2.5-pro."98  },99  {100    "id": "gemini-3.1-pro-preview-customtools",101    "displayName": "Gemini 3.1 Pro Preview (custom tools)",102    "family": "gemini-3.x-pro",103    "contextTokens": 1048576,104    "maxOutputTokens": 65536,105    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },106    "parameters": { "temperature": "0-2", "topP": "docs-only", "topK": "docs-only", "maxTokens": true, "reasoningEffort": ["low", "medium", "high"], "thinkingBudget": "docs-only", "stop": "docs-only", "seed": "docs-only", "frequencyPenalty": false, "presencePenalty": false },107    "pricing": { "inputPerMillion": 2.0, "cachedInputPerMillion": 0.2, "outputPerMillion": 12.0, "note": "assumed same as gemini-3.1-pro-preview (not separately listed)" },108    "status": "preview",109    "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."110  },111  {112    "id": "gemini-2.5-pro",113    "displayName": "Gemini 2.5 Pro",114    "family": "gemini-2.5",115    "contextTokens": 1048576,116    "maxOutputTokens": 65536,117    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },118    "parameters": { "temperature": "0-2 (2.5 -> 400 probed)", "topP": "docs-only", "topK": "docs-only", "maxTokens": true, "reasoningEffort": "docs: thinkingLevel low/medium/high accepted; OpenAI-compat maps minimal/low=1024, medium=8192, high=24576 budget", "thinkingBudget": "docs-only: 128-32768, cannot be disabled (-1 dynamic)", "stop": "docs-only", "seed": "docs-only", "frequencyPenalty": "docs-only", "presencePenalty": "docs-only" },119    "pricing": { "inputPerMillion": 1.25, "cachedInputPerMillion": 0.125, "outputPerMillion": 10.0, "note": ">200k prompt: 2.50 / 0.25 / 15.00; paid tier only" },120    "status": "deprecated",121    "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 cutoff Jan 2025. Treat as legacy/hidden in a BYOK app unless the user's key is grandfathered (detect via 404 message)."122  },123  {124    "id": "gemini-2.5-flash",125    "displayName": "Gemini 2.5 Flash",126    "family": "gemini-2.5",127    "contextTokens": 1048576,128    "maxOutputTokens": 65536,129    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },130    "parameters": { "temperature": "0-2 (2.5 -> 400 probed)", "topP": "docs-only", "topK": "docs-only", "maxTokens": true, "reasoningEffort": "docs: low/medium/high", "thinkingBudget": "docs-only: 0 (off) to 24576, -1 dynamic", "stop": "docs-only", "seed": "docs-only", "frequencyPenalty": "docs-only", "presencePenalty": "docs-only" },131    "pricing": { "inputPerMillion": 0.3, "cachedInputPerMillion": 0.03, "outputPerMillion": 2.5, "note": "audio input 1.00/M, cached audio 0.10/M" },132    "status": "deprecated",133    "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."134  },135  {136    "id": "gemini-2.5-flash-lite",137    "displayName": "Gemini 2.5 Flash-Lite",138    "family": "gemini-2.5",139    "contextTokens": 1048576,140    "maxOutputTokens": 65536,141    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },142    "parameters": { "temperature": "0-2", "topP": "docs-only", "topK": "docs-only", "maxTokens": true, "reasoningEffort": "docs: low/medium/high (default off)", "thinkingBudget": "docs-only: 512-24576, 0 off", "stop": "docs-only", "seed": "docs-only", "frequencyPenalty": "docs-only", "presencePenalty": "docs-only" },143    "pricing": { "inputPerMillion": 0.1, "cachedInputPerMillion": 0.01, "outputPerMillion": 0.4, "note": "audio input 0.30/M" },144    "status": "deprecated",145    "notes": "LISTED but 404 'no longer available to new users' -> use gemini-3.5-flash-lite (probed via chats + safetySettings probes)."146  },147  {148    "id": "gemini-flash-latest",149    "displayName": "Gemini Flash (latest alias)",150    "family": "alias",151    "contextTokens": 1048576,152    "maxOutputTokens": 65536,153    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },154    "parameters": { "temperature": "0-2", "topP": true, "topK": true, "maxTokens": true, "reasoningEffort": ["minimal", "low", "medium", "high"], "thinkingBudget": "legacy", "stop": true, "seed": true, "frequencyPenalty": false, "presencePenalty": false },155    "pricing": { "inputPerMillion": 1.5, "cachedInputPerMillion": 0.15, "outputPerMillion": 9.0, "note": "billed as the model it resolves to (currently gemini-3.5-flash per changelog May 2026); not listed on pricing page" },156    "status": "active",157    "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."158  },159  {160    "id": "gemini-flash-lite-latest",161    "displayName": "Gemini Flash-Lite (latest alias)",162    "family": "alias",163    "contextTokens": 1048576,164    "maxOutputTokens": 65536,165    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },166    "parameters": { "temperature": "0-2", "topP": true, "topK": true, "maxTokens": true, "reasoningEffort": ["minimal", "low", "medium", "high"], "thinkingBudget": "1024/-1 OK, 0 rejected (as 3.5-flash-lite)", "stop": true, "seed": true, "frequencyPenalty": false, "presencePenalty": false },167    "pricing": { "inputPerMillion": 0.3, "cachedInputPerMillion": 0.03, "outputPerMillion": 2.5, "note": "billed as gemini-3.5-flash-lite (probe modelVersion = gemini-3.5-flash-lite)" },168    "status": "active",169    "notes": "Probed: resolves to gemini-3.5-flash-lite (modelVersion). Used for the raw REST SSE probe (works)."170  },171  {172    "id": "gemini-pro-latest",173    "displayName": "Gemini Pro (latest alias)",174    "family": "alias",175    "contextTokens": 1048576,176    "maxOutputTokens": 65536,177    "capabilities": { "text": true, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": true, "structuredOutput": true, "streaming": true, "files": true, "webSearch": true },178    "parameters": { "temperature": "0-2", "topP": "docs-only", "topK": "docs-only", "maxTokens": true, "reasoningEffort": ["low", "medium", "high"], "thinkingBudget": "legacy", "stop": "docs-only", "seed": "docs-only", "frequencyPenalty": false, "presencePenalty": false },179    "pricing": { "inputPerMillion": 2.0, "cachedInputPerMillion": 0.2, "outputPerMillion": 12.0, "note": "billed as the resolved model (429 quota dimension showed model=gemini-3.1-pro -> resolves to 3.1 Pro preview)" },180    "status": "active",181    "notes": "Paid tier only (free-tier 429 limit 0, quota dimension model=gemini-3.1-pro)."182  },183  {184    "id": "gemma-4-31b-it",185    "displayName": "Gemma 4 31B (instruction-tuned)",186    "family": "gemma-4",187    "contextTokens": 262144,188    "maxOutputTokens": 32768,189    "capabilities": { "text": true, "vision": "docs: image/video/audio input supported by Gemma 4; not probed on the API", "audioInput": null, "audioOutput": false, "imageGeneration": false, "video": null, "reasoning": true, "tools": "docs: yes; not probed", "structuredOutput": true, "streaming": true, "files": null, "webSearch": false },190    "parameters": { "temperature": "0-2 accepted (2 probed OK; 0/1.5 hit transient 500s)", "topP": "probed: 500 INTERNAL x2 (transient?)", "topK": true, "maxTokens": true, "reasoningEffort": false, "thinkingBudget": false, "stop": "probed: 500 INTERNAL x2 (transient?)", "seed": true, "frequencyPenalty": false, "presencePenalty": false },191    "pricing": { "inputPerMillion": 0, "cachedInputPerMillion": null, "outputPerMillion": 0, "note": "Free tier: 'Free of charge' (data used for product improvement). Paid tier: 'Not available'." },192    "status": "active",193    "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.enum OK. ~50% of probe requests returned 500 INTERNAL 'Internal error encountered.' (flaky; retry). systemInstruction not probed. No createCachedContent / batch support (supportedGenerationMethods = generateContent, countTokens)."194  },195  {196    "id": "gemma-4-26b-a4b-it",197    "displayName": "Gemma 4 26B A4B (MoE, instruction-tuned)",198    "family": "gemma-4",199    "contextTokens": 262144,200    "maxOutputTokens": 32768,201    "capabilities": { "text": true, "vision": null, "audioInput": null, "audioOutput": false, "imageGeneration": false, "video": null, "reasoning": true, "tools": null, "structuredOutput": null, "streaming": true, "files": null, "webSearch": false },202    "parameters": { "temperature": "0-2", "topP": null, "topK": null, "maxTokens": true, "reasoningEffort": false, "thinkingBudget": false, "stop": null, "seed": null, "frequencyPenalty": false, "presencePenalty": false },203    "pricing": { "inputPerMillion": 0, "cachedInputPerMillion": null, "outputPerMillion": 0, "note": "free tier only" },204    "status": "active",205    "notes": "Probed once: 'pong' OK with 58 thought tokens. Assume same behaviour as gemma-4-31b-it (unknowns = null)."206  },207  {208    "id": "gemini-omni-1.1-flash",209    "displayName": "Gemini Omni 1.1 Flash",210    "family": "gemini-omni",211    "contextTokens": 131072,212    "maxOutputTokens": 65536,213    "capabilities": { "text": "docs: text output priced (9.00/M) but model card says output = video only", "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": null, "structuredOutput": null, "streaming": null, "files": null, "webSearch": false },214    "parameters": { "temperature": "0-2 (2.5 -> 400 probed)", "topP": null, "topK": null, "maxTokens": true, "reasoningEffort": null, "thinkingBudget": null, "stop": null, "seed": null, "frequencyPenalty": null, "presencePenalty": null },215    "pricing": { "inputPerMillion": 1.5, "cachedInputPerMillion": null, "outputPerMillion": 9.0, "note": "video output 17.50/M (~0.10/s); paid tier only" },216    "status": "active",217    "notes": "Video-generation model (GA Aug 2026; 3-10 s clips, 360p-4K). Models endpoint says inputTokenLimit 131072 (model card says 1,048,576 — 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."218  },219  {220    "id": "gemini-omni-flash-preview",221    "displayName": "Gemini Omni Flash Preview",222    "family": "gemini-omni",223    "contextTokens": 131072,224    "maxOutputTokens": 65536,225    "capabilities": { "text": null, "vision": true, "audioInput": true, "audioOutput": false, "imageGeneration": false, "video": true, "reasoning": true, "tools": null, "structuredOutput": null, "streaming": null, "files": null, "webSearch": false },226    "parameters": { "temperature": "0-2", "topP": null, "topK": null, "maxTokens": true, "reasoningEffort": null, "thinkingBudget": null, "stop": null, "seed": null, "frequencyPenalty": null, "presencePenalty": null },227    "pricing": { "inputPerMillion": 1.5, "cachedInputPerMillion": null, "outputPerMillion": 9.0, "note": "video output 17.50/M; paid tier only" },228    "status": "preview",229    "notes": "Preview predecessor of gemini-omni-1.1-flash (June 2026). Free tier 429 'limit: 0'. Not a chat model."230  }231]232