API PRICES
Google · gemini-3.1-pro-preview-customtools
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 2 / output 12 USD/million tokensGoogle ·
- Lowest inference provider (cash)
- Input 2.1 / output 12.6 USD/million tokensOpenRouter · Aggregator · Via OpenRouter with 5% fee, original price × 1.05 ·
- Lowest relay (credit)
- 11.25 USD credit/million total tokensapi.chatgpt-code.com "Gemini_T3" ·
Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.
All official and inference price observations
Google · gemini-3.1-pro-preview-customtools official price: input 2, output 12 USD per million tokens (Google, observed 2026-11-13). Cheapest inference provider: OpenRouter, input 2.1, output 12.6 USD per million tokens. This is the price via OpenRouter with a 5% fee added, original price × 1.05. Original price: input 2, output 12. Cheapest relay: api.chatgpt-code.com, group "Gemini_T3" 11.25 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-11-14). 52 sites have comparable prices; 154 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: Context tier: PROMPT_LE_200K · Standard processing · section: Gemini 3.1 Pro Preview · tier: Standard · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $12.00, prompts <= 200k tokens $18.00, prompts > 200k Context caching price | Not available | $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | No · Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional image price 0.000002 USD (per unit as declared by OpenRouter) · Additional web_search price 0.014 USD (per unit as declared by OpenRouter) · Additional internal_reasoning price 0.000012 USD (per unit as declared by OpenRouter)
Price ranges per million tokens
Official cash prices · Lowest 4.5 · median 4.5 · highest 4.5 · 1 quotes USD / per million tokens · 1 of these are priced by context length; each counts once, at its lowest tier
Inference provider cash prices · Lowest 4.725 · median 4.725 · highest 4.725 · 1 quotes USD / per million tokens
Relay USD credit prices · Lowest 11.25 · median 11.25 · highest 11.25 · 1 quotes USD / per million tokens, site credit
Each quote is blended into one price by this workload: ordinary input 75% · cache read 0% · output 25% · cache write 0%. Only prices in effect now are counted.
Official price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| Standard | 2 | 12 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Standard processing · section: Gemini 3.1 Pro Preview · tier: Standard · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $12.00, prompts <= 200k tokens $18.00, prompts > 200k Context caching price | Not available | $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_200K",
"processingMode": "standard",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"tier: Standard",
"cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $2.00, prompts <= 200k tokens \n$4.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $12.00, prompts <= 200k tokens \n$18.00, prompts > 200k\nContext caching price | Not available | $0.20, prompts <= 200k tokens \n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free search requests per ",
"month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to imp",
"rove our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Standard | 4 | 18 | 0.4 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Standard processing · section: Gemini 3.1 Pro Preview · tier: Standard · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $12.00, prompts <= 200k tokens $18.00, prompts > 200k Context caching price | Not available | $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_GT_200K",
"processingMode": "standard",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"tier: Standard",
"cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $2.00, prompts <= 200k tokens \n$4.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $12.00, prompts <= 200k tokens \n$18.00, prompts > 200k\nContext caching price | Not available | $0.20, prompts <= 200k tokens \n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free search requests per ",
"month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to imp",
"rove our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.
Inference providers
For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.
| Provider | Tariff | Input | Output | Cache read | Cache write | Via OpenRouter with 5% fee | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | Standard | 2 | 12 | 0.2 | 0.375 | Input 2.1 Output 12.6 Cache read 0.21 Cache write 0.39375 Original price × 1.05 | USD / 1M tokens | Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional image price 0.000002 USD (per unit as declared by OpenRouter) · Additional web_search price 0.014 USD (per unit as declared by OpenRouter) · Additional internal_reasoning price 0.000012 USD (per unit as declared by OpenRouter)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000002",
"cacheWrite": "0.000000375",
"input": "0.000002",
"output": "0.000012"
},
"conditions": [],
"contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE",
"processingMode": null,
"conditionNotes": [
"Additional image price 0.000002 USD (per unit as declared by OpenRouter)",
"Additional web_search price 0.014 USD (per unit as declared by OpenRouter)",
"Additional internal_reasoning price 0.000012 USD (per unit as declared by OpenRouter)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Other tariffs and prices to review
Official price
For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.
| Provider | Tariff | Input | Output | Cache read | Cache write | Via OpenRouter with 5% fee | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|---|
| Batch | 2 | 9 | 0.4 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Batch processing · tier: Batch · section: Gemini 3.1 Pro Preview · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k Context caching price | Not available | *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k … · rch requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | … · ries. Used to improve our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Batch"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "batch",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k\nContext caching price | Not available | *Same as Standard* \n$0.20, prompts <= 200k tokens\n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free sea",
"rch requests per month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch que",
"ries.\nUsed to improve our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |||
| Batch | 1 | 6 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Batch processing · tier: Batch · section: Gemini 3.1 Pro Preview · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k Context caching price | Not available | *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k … · rch requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | … · ries. Used to improve our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Batch"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "batch",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k\nContext caching price | Not available | *Same as Standard* \n$0.20, prompts <= 200k tokens\n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free sea",
"rch requests per month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch que",
"ries.\nUsed to improve our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |||
| Other tariff | 2 | 9 | 0.4 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Flex processing · tier: Flex · section: Gemini 3.1 Pro Preview · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k Context caching price | Not available | *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k … · rch requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | … · ries. Used to improve our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Flex"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "flex",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k\nContext caching price | Not available | *Same as Standard* \n$0.20, prompts <= 200k tokens\n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free sea",
"rch requests per month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch que",
"ries.\nUsed to improve our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |||
| Other tariff | 1 | 6 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Flex processing · tier: Flex · section: Gemini 3.1 Pro Preview · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k Context caching price | Not available | *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k … · rch requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | … · ries. Used to improve our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Flex"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "flex",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k\nContext caching price | Not available | *Same as Standard* \n$0.20, prompts <= 200k tokens\n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free sea",
"rch requests per month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch que",
"ries.\nUsed to improve our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |||
| Other tariff | 7.2 | 32.4 | 0.72 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Priority processing · tier: Priority · section: Gemini 3.1 Pro Preview · cache storage per 1M tokens per hour: $8.10 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $21.60, prompts <= 200k tokens $32.40, prompts > 200k Context caching price | Not available | $0.36, prompts <= 200k tokens $0.72, prompts > 200k $8.10 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Priority"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "priority",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"cache storage per 1M tokens per hour: $8.10 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $3.60, prompts <= 200k tokens \n$7.20, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $21.60, prompts <= 200k tokens \n$32.40, prompts > 200k\nContext caching price | Not available | $0.36, prompts <= 200k tokens \n$0.72, prompts > 200k\n$8.10 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free search requests per ",
"month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to imp",
"rove our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |||
| Other tariff | 3.6 | 21.6 | 0.36 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Priority processing · tier: Priority · section: Gemini 3.1 Pro Preview · cache storage per 1M tokens per hour: $8.10 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $21.60, prompts <= 200k tokens $32.40, prompts > 200k Context caching price | Not available | $0.36, prompts <= 200k tokens $0.72, prompts > 200k $8.10 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Priority"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "priority",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"cache storage per 1M tokens per hour: $8.10 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $3.60, prompts <= 200k tokens \n$7.20, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $21.60, prompts <= 200k tokens \n$32.40, prompts > 200k\nContext caching price | Not available | $0.36, prompts <= 200k tokens \n$0.72, prompts > 200k\n$8.10 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free search requests per ",
"month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to imp",
"rove our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |||
| Other tariff | 2 | 9 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Processing mode: contributor · tier: Contributor · The Gemini API Contributor Tier is offered as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be in… · section: Gemini 3.1 Pro Preview · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · ed as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be invited by email and see a callout in AI S… · | $1.00, prompts <= 200k tokens $2.00, prompts > 200k tokens Output price (including thinking tokens) | Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k tokens … · ,000,000 tokens per hour (storage price) Used to improve our products | Not available | YesFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Contributor",
"The Gemini API Contributor Tier is offered as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be invited by email and see a callout in AI Studio."
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "contributor",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n The Gemini API Contributor Tier is offer",
"ed as a private preview on an\n invite-only basis. Speed and reliability are equivalent to\n Standard Tier inference. Eligible users will be invited by\n email and see a callout in AI Studio.\n\n \n\n \n\n * Discounts and model availability are subject to change.\nInput price | Not available",
" | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) | Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k tokens\nContext caching price | Not available | $0.10, prompts <= 200k tokens \n$0.20, prompts > 200k tokens\n$4.50 / 1",
",000,000 tokens per hour (storage price)\nUsed to improve our products | Not available | Yes"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |||
| Other tariff | 1 | 6 | 0.1 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Processing mode: contributor · tier: Contributor · The Gemini API Contributor Tier is offered as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be in… · section: Gemini 3.1 Pro Preview · cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · ed as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be invited by email and see a callout in AI S… · | $1.00, prompts <= 200k tokens $2.00, prompts > 200k tokens Output price (including thinking tokens) | Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k tokens … · ,000,000 tokens per hour (storage price) Used to improve our products | Not available | YesFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Contributor",
"The Gemini API Contributor Tier is offered as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be invited by email and see a callout in AI Studio."
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "contributor",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"cache storage per 1M tokens per hour: $4.50 / 1,000,000 tokens per hour",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n The Gemini API Contributor Tier is offer",
"ed as a private preview on an\n invite-only basis. Speed and reliability are equivalent to\n Standard Tier inference. Eligible users will be invited by\n email and see a callout in AI Studio.\n\n \n\n \n\n * Discounts and model availability are subject to change.\nInput price | Not available",
" | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) | Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k tokens\nContext caching price | Not available | $0.10, prompts <= 200k tokens \n$0.20, prompts > 200k tokens\n$4.50 / 1",
",000,000 tokens per hour (storage price)\nUsed to improve our products | Not available | Yes"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |||
| Google AI Studio | Standard | 2 | 12 | 0.2 | 0.375 | Input 2.1 Output 12.6 Cache read 0.21 Cache write 0.39375 Original price × 1.05 | USD / 1M tokens | Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale) · Additional image price 0.000002 USD (per unit as declared by OpenRouter) · Additional web_search price 0.014 USD (per unit as declared by OpenRouter) · Additional internal_reasoning price 0.000012 USD (per unit as declared by OpenRouter) · price listed by OpenRouter for this provider (endpoint google-ai-studio)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000002",
"cacheWrite": "0.000000375",
"input": "0.000002",
"output": "0.000012"
},
"conditions": [
"Served through OpenRouter by the model vendor or a major cloud at its own price (first-tier resale)"
],
"contextTier": null,
"processingMode": null,
"conditionNotes": [
"Additional image price 0.000002 USD (per unit as declared by OpenRouter)",
"Additional web_search price 0.014 USD (per unit as declared by OpenRouter)",
"Additional internal_reasoning price 0.000012 USD (per unit as declared by OpenRouter)",
"price listed by OpenRouter for this provider (endpoint google-ai-studio)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Inference providers
For prices via OpenRouter, comparisons and order use the price with a 5% fee added, original price × 1.05. The original price is listed too.
| Provider | Tariff | Input | Output | Cache read | Cache write | Via OpenRouter with 5% fee | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|---|
| OpenRouter · Aggregator | Standard | 4 | 18 | 0.4 | — | Input 4.2 Output 18.9 Cache read 0.42 Original price × 1.05 | USD / 1M tokens | Context tier: OPENROUTER_MIN_PROMPT_TOKENS_200000 · OpenRouter override for prompts from 200000 tokens (boundary inclusivity not stated) · Additional image price 0.000002 USD (per unit as declared by OpenRouter) · Additional web_search price 0.014 USD (per unit as declared by OpenRouter) · Additional internal_reasoning price 0.000012 USD (per unit as declared by OpenRouter)Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000004",
"input": "0.000004",
"output": "0.000018"
},
"conditions": [
"OpenRouter override for prompts from 200000 tokens (boundary inclusivity not stated)"
],
"contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_200000",
"processingMode": null,
"conditionNotes": [
"Additional image price 0.000002 USD (per unit as declared by OpenRouter)",
"Additional web_search price 0.014 USD (per unit as declared by OpenRouter)",
"Additional internal_reasoning price 0.000012 USD (per unit as declared by OpenRouter)"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Older official and inference provider prices
Earlier price observations and their original conditions
Official price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| Batch | 1 | 6 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Batch processing · tier: Batch · section: Gemini 3.1 Pro Preview · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k Context caching price | Not available | *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k … · rch requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | … · ries. Used to improve our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Batch"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "batch",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k\nContext caching price | Not available | *Same as Standard* \n$0.20, prompts <= 200k tokens\n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free sea",
"rch requests per month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch que",
"ries.\nUsed to improve our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 1 | 6 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Flex processing · tier: Flex · section: Gemini 3.1 Pro Preview · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k Context caching price | Not available | *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k … · rch requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | … · ries. Used to improve our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Flex"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "flex",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k\nContext caching price | Not available | *Same as Standard* \n$0.20, prompts <= 200k tokens\n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free sea",
"rch requests per month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch que",
"ries.\nUsed to improve our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 1 | 6 | 0.1 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Processing mode: contributor · tier: Contributor · The Gemini API Contributor Tier is offered as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be in… · section: Gemini 3.1 Pro Preview · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · ed as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be invited by email and see a callout in AI S… · | $1.00, prompts <= 200k tokens $2.00, prompts > 200k tokens Output price (including thinking tokens) | Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k tokens … · ,000,000 tokens per hour (storage price) Used to improve our products | Not available | YesFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Contributor",
"The Gemini API Contributor Tier is offered as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be invited by email and see a callout in AI Studio."
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "contributor",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n The Gemini API Contributor Tier is offer",
"ed as a private preview on an\n invite-only basis. Speed and reliability are equivalent to\n Standard Tier inference. Eligible users will be invited by\n email and see a callout in AI Studio.\n\n \n\n \n\n * Discounts and model availability are subject to change.\nInput price | Not available",
" | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) | Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k tokens\nContext caching price | Not available | $0.10, prompts <= 200k tokens \n$0.20, prompts > 200k tokens\n$4.50 / 1",
",000,000 tokens per hour (storage price)\nUsed to improve our products | Not available | Yes"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Batch | 2 | 9 | 0.4 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Batch processing · tier: Batch · section: Gemini 3.1 Pro Preview · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k Context caching price | Not available | *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k … · rch requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | … · ries. Used to improve our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Batch"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "batch",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k\nContext caching price | Not available | *Same as Standard* \n$0.20, prompts <= 200k tokens\n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free sea",
"rch requests per month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch que",
"ries.\nUsed to improve our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 2 | 9 | 0.4 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Flex processing · tier: Flex · section: Gemini 3.1 Pro Preview · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k Context caching price | Not available | *Same as Standard* $0.20, prompts <= 200k tokens $0.40, prompts > 200k … · rch requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | … · ries. Used to improve our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Flex"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "flex",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k\nContext caching price | Not available | *Same as Standard* \n$0.20, prompts <= 200k tokens\n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free sea",
"rch requests per month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch que",
"ries.\nUsed to improve our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 2 | 9 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Processing mode: contributor · tier: Contributor · The Gemini API Contributor Tier is offered as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be in… · section: Gemini 3.1 Pro Preview · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · ed as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be invited by email and see a callout in AI S… · | $1.00, prompts <= 200k tokens $2.00, prompts > 200k tokens Output price (including thinking tokens) | Not available | $6.00, prompts <= 200k tokens $9.00, prompts > 200k tokens … · ,000,000 tokens per hour (storage price) Used to improve our products | Not available | YesFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Contributor",
"The Gemini API Contributor Tier is offered as a private preview on an invite-only basis. Speed and reliability are equivalent to Standard Tier inference. Eligible users will be invited by email and see a callout in AI Studio."
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "contributor",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n The Gemini API Contributor Tier is offer",
"ed as a private preview on an\n invite-only basis. Speed and reliability are equivalent to\n Standard Tier inference. Eligible users will be invited by\n email and see a callout in AI Studio.\n\n \n\n \n\n * Discounts and model availability are subject to change.\nInput price | Not available",
" | $1.00, prompts <= 200k tokens \n$2.00, prompts > 200k tokens\nOutput price (including thinking tokens) | Not available | $6.00, prompts <= 200k tokens \n$9.00, prompts > 200k tokens\nContext caching price | Not available | $0.10, prompts <= 200k tokens \n$0.20, prompts > 200k tokens\n$4.50 / 1",
",000,000 tokens per hour (storage price)\nUsed to improve our products | Not available | Yes"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Standard | 2 | 12 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Standard processing · section: Gemini 3.1 Pro Preview · tier: Standard · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $12.00, prompts <= 200k tokens $18.00, prompts > 200k Context caching price | Not available | $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_200K",
"processingMode": "standard",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"tier: Standard",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $2.00, prompts <= 200k tokens \n$4.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $12.00, prompts <= 200k tokens \n$18.00, prompts > 200k\nContext caching price | Not available | $0.20, prompts <= 200k tokens \n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free search requests per ",
"month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to imp",
"rove our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Standard | 4 | 18 | 0.4 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Standard processing · section: Gemini 3.1 Pro Preview · tier: Standard · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $12.00, prompts <= 200k tokens $18.00, prompts > 200k Context caching price | Not available | $0.20, prompts <= 200k tokens $0.40, prompts > 200k $4.50 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_GT_200K",
"processingMode": "standard",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"tier: Standard",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $2.00, prompts <= 200k tokens \n$4.00, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $12.00, prompts <= 200k tokens \n$18.00, prompts > 200k\nContext caching price | Not available | $0.20, prompts <= 200k tokens \n$0.40, prompts > 200k\n$4.50 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free search requests per ",
"month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to imp",
"rove our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 3.6 | 21.6 | 0.36 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Priority processing · tier: Priority · section: Gemini 3.1 Pro Preview · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $21.60, prompts <= 200k tokens $32.40, prompts > 200k Context caching price | Not available | $0.36, prompts <= 200k tokens $0.72, prompts > 200k $8.10 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Priority"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "priority",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $3.60, prompts <= 200k tokens \n$7.20, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $21.60, prompts <= 200k tokens \n$32.40, prompts > 200k\nContext caching price | Not available | $0.36, prompts <= 200k tokens \n$0.72, prompts > 200k\n$8.10 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free search requests per ",
"month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to imp",
"rove our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 7.2 | 32.4 | 0.72 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Priority processing · tier: Priority · section: Gemini 3.1 Pro Preview · declared scoped context: *gemini-3.1-pro-preview and gemini-3.1-pro-preview-customtools* Try it in Google AI Studio Our 3rd generation Pro model, built for multimodal understandin… · i may result in one or more queries to Google Search. You will be charged for each individual search query performed. Can be tested in Google AI Studio. Input price | Not availabl… · Not available | $21.60, prompts <= 200k tokens $32.40, prompts > 200k Context caching price | Not available | $0.36, prompts <= 200k tokens $0.72, prompts > 200k $8.10 / 1,000,000… · month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5… · rove our products | Not available | NoFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Priority"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "priority",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"declared scoped context: *gemini-3.1-pro-preview and\n gemini-3.1-pro-preview-customtools*\n\n \n\n \n \n Try it in Google AI Studio\n\n \n\n \n\n\n\n\n\nOur 3rd generation Pro model, built for multimodal understanding, agentic\ncapabilities, and vibe-coding.\n\n\n\n\n \n\n * A customer-submitted request to Gemin",
"i may result in one or\n more queries to Google Search. You will be charged for each individual search\n query performed.\n\n Can be tested in Google AI Studio.\nInput price | Not available | $3.60, prompts <= 200k tokens \n$7.20, prompts > 200k tokens\nOutput price (including thinking tokens) |",
" Not available | $21.60, prompts <= 200k tokens \n$32.40, prompts > 200k\nContext caching price | Not available | $0.36, prompts <= 200k tokens \n$0.72, prompts > 200k\n$8.10 / 1,000,000 tokens per hour (storage price)\nGrounding with Google Search* | Not available | 5,000 free search requests per ",
"month (shared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to imp",
"rove our products | Not available | No"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Batch | 1 | 6 | — | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Batch processing · tier: Batch · section: Gemini 3.1 Pro PreviewFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Batch"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "batch",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 1 | 6 | — | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Flex processing · tier: Flex · section: Gemini 3.1 Pro PreviewFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Flex"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "flex",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 1 | 6 | 0.1 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Processing mode: contributor · tier: Contributor · section: Gemini 3.1 Pro PreviewFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Contributor"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "contributor",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Batch | 2 | 9 | — | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Batch processing · tier: Batch · section: Gemini 3.1 Pro PreviewFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Batch"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "batch",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 2 | 9 | — | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Flex processing · tier: Flex · section: Gemini 3.1 Pro PreviewFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Flex"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "flex",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 2 | 9 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Processing mode: contributor · tier: Contributor · section: Gemini 3.1 Pro PreviewFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Contributor"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "contributor",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Standard | 2 | 12 | 0.2 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Standard processing · section: Gemini 3.1 Pro Preview · tier: StandardFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_200K",
"processingMode": "standard",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"tier: Standard"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Standard | 4 | 18 | 0.4 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Standard processing · section: Gemini 3.1 Pro Preview · tier: StandardFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_GT_200K",
"processingMode": "standard",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview",
"tier: Standard"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 3.6 | 21.6 | 0.36 | — | USD / 1M tokens | Context tier: PROMPT_LE_200K · Priority processing · tier: Priority · section: Gemini 3.1 Pro PreviewFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Priority"
],
"contextTier": "PROMPT_LE_200K",
"processingMode": "priority",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Other tariff | 7.2 | 32.4 | 0.72 | — | USD / 1M tokens | Context tier: PROMPT_GT_200K · Priority processing · tier: Priority · section: Gemini 3.1 Pro PreviewFull price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [
"tier: Priority"
],
"contextTier": "PROMPT_GT_200K",
"processingMode": "priority",
"conditionNotes": [
"section: Gemini 3.1 Pro Preview"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 11.25 · median 11.25 · highest 11.25 (1 quotes, USD credits per million total tokens)
Relays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑USD credits / 1M | Output USD credits / 1M | Cache readUSD credits / 1M | BlendedUSD credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | api.chatgpt-code.comAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected: Collected this cycle View 1 plans | Gemini_T3 Gemini api Operator pending verification | 5 | 30 | 0.5 | 11.25About the median price | Details |
Special groups · 2 rows · not ranked
These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.
- test or debug group: 2 rows
- test-api.apiqik.online · vertex/sp/gemini · gemini-3.1-pro-preview-customtools · Input 0.68 / Output 4.08 USD credits / 1M
- test-api.apiqik.online · gemini · gemini-3.1-pro-preview-customtools · Input 1 / Output 6 USD credits / 1M
How this ranking works
All per-token prices: 128,524 prices from 1,383 sites (about 1,275 companies). 109,485 are ranked, from 1,349 sites (about 1,244 companies); 19,039 more are listed separately and not ranked. Prices collected up to 2026-11-15.
This model has 344 recorded prices; 107 can be compared directly (104 ranked, 3 listed separately). Not comparable yet: price not parsed yet 90, ratio looks unset 36, scope of the official doc price not confirmed 12, new price under review; showing the previous one 7. 91 more are tiered by rules and compared on the Tiered prices board
1 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table.
Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.
“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for Google · gemini-3.1-pro-preview-customtools?
api.chatgpt-code.com, group "Gemini_T3", 11.25 USD credit per million total tokens, observed 2026-11-14. 52 sites have comparable prices.
What is the official price for Google · gemini-3.1-pro-preview-customtools?
Input 2, output 12 USD per million tokens, checked 2026-11-13. Lowest inference provider: OpenRouter, input 2.1, output 12.6 USD per million tokens. This is the price via OpenRouter with a 5% fee added, original price × 1.05. Original price: input 2, output 12.
How do I use Google · gemini-3.1-pro-preview-customtools in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest Google · gemini-3.1-pro-preview-customtools API to Claude Code for me". Install Skill →