scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-09-07 08:26:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add Gemini free tier models with -free aliases

Browse source 
Add three new free tier Gemini models with 250K context windows:
- gemini-2.5-pro-free (5 RPM, 250K TPM, 100 RPD)
- gemini-2.5-flash-free (10 RPM, 250K TPM, 250 RPD)
- gemini-2.5-flash-lite-free (15 RPM, 250K TPM, 1000 RPD)

The provider maps -free aliases to base model IDs for API calls while
preserving the 250K context limit and $0 pricing in the UI.

Descriptions include rate limiting guidance for users to set appropriate
delays in provider settings (12s, 6s, 4s respectively).
This commit is contained in:
Shariq Riaz 2025-08-24 02:15:30 +05:00
parent fc70012f54
commit 64e6086f61
2 changed files with 52 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
packages/types/src/providers/gemini.ts
View file

@ -295,4 +295,47 @@ export const geminiModels = {
supportsReasoningBudget: true,
maxThinkingTokens: 24_576,
},
"gemini-2.5-pro-free": {
maxTokens: 64_000,
contextWindow: 250_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0,
outputPrice: 0,
cacheReadsPrice: 0,
cacheWritesPrice: 0,
maxThinkingTokens: 32_768,
supportsReasoningBudget: true,
requiredReasoningBudget: true,
description:
"Free tier version of Gemini 2.5 Pro with 250K context window and rate limits (5 RPM, 250K TPM, 100 RPD). Set minimum 12 seconds between requests in provider settings to avoid rate limits.",
},
"gemini-2.5-flash-free": {
maxTokens: 64_000,
contextWindow: 250_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0,
outputPrice: 0,
cacheReadsPrice: 0,
cacheWritesPrice: 0,
maxThinkingTokens: 24_576,
supportsReasoningBudget: true,
description:
"Free tier version of Gemini 2.5 Flash with 250K context window and rate limits (10 RPM, 250K TPM, 250 RPD). Set minimum 6 seconds between requests in provider settings to avoid rate limits.",
},
"gemini-2.5-flash-lite-free": {
maxTokens: 64_000,
contextWindow: 250_000,
supportsImages: true,
supportsPromptCache: true,
inputPrice: 0,
outputPrice: 0,
cacheReadsPrice: 0,
cacheWritesPrice: 0,
supportsReasoningBudget: true,
maxThinkingTokens: 24_576,
description:
"Free tier version of Gemini 2.5 Flash Lite with 250K context window and rate limits (15 RPM, 250K TPM, 1000 RPD). Set minimum 4 seconds between requests in provider settings to avoid rate limits.",
},
} as const satisfies Record<string, ModelInfo>

10
src/api/providers/gemini.ts
View file

@ -172,7 +172,15 @@ export class GeminiHandler extends BaseProvider implements SingleCompletionHandl
// reasoning model and that reasoning is required to be enabled.
// The actual model ID honored by Gemini's API does not have this
// suffix.
return { id: id.endsWith(":thinking") ? id.replace(":thinking", "") : id, info, ...params }
let apiModelId = id.endsWith(":thinking") ? id.replace(":thinking", "") : id
// The `-free` suffix indicates free tier models with rate limits.
// Map them to their corresponding paid models for API calls.
if (apiModelId.endsWith("-free")) {
apiModelId = apiModelId.replace("-free", "") as GeminiModelId
}
return { id: apiModelId, info, ...params }
}
private extractCitationsOnly(groundingMetadata?: GroundingMetadata): string | null {