Google API pricing: every provider, per million tokens
The lowest blended price for a Google model is $0.0208 (₹1.96) per million tokens, for gemma-4-26B-A4B-it on PrimeIntellect at BF16, blended 3:1 input to output. The newest Google model with an API is gemma-4-26B-A4B-it, released 11 Mar 2026. Its lowest blended price is $0.0208 (₹1.96) on PrimeIntellect at BF16. We list 39 offers from 22 providers for 5 Google models.
gemma-4-26B-A4B-it
15 providers · context up to 262,144| Precision | |||||
|---|---|---|---|---|---|
| PrimeIntellectCheapest | $0.0208₹1.96 | $0.014₹1.32 | $0.041₹3.87 | 262,144 | BF16 |
| Darkbloom | $0.0675₹6.36 | $0.04₹3.77 | $0.15₹14 | 131,072 | Not listed |
| NextBit | $0.1069₹10 | $0.0675₹6.36 | $0.225₹21 | 262,144 | BF16 |
| AkashML | $0.1125₹11 | $0.07₹6.60 | $0.24₹23 | 131,072 | FP4 |
| Io Net | $0.1227₹12 | $0.067₹6.32 | $0.29₹27 | 262,142 | BF16 |
| DekaLLM | $0.1275₹12 | $0.06₹5.66 | $0.33₹31 | 262,144 | BF16 |
| DeepInfra | $0.1375₹13 | $0.07₹6.60 | $0.34₹32 | 262,144 | FP8 |
| Makora | $0.1375₹13 | $0.09₹8.49 | $0.28₹26 | 256,000 | Not listed |
| Cloudflare | $0.15₹14 | $0.10₹9.43 | $0.30₹28 | 256,000 | Not listed |
| CoreWeave | $0.15₹14 | $0.10₹9.43 | $0.30₹28 | 262,144 | BF16 |
| Novita | $0.1975₹19 | $0.13₹12 | $0.40₹38 | 262,144 | BF16 |
| Parasail | $0.1975₹19 | $0.13₹12 | $0.40₹38 | 262,144 | BF16 |
| Venice | $0.1975₹19 | $0.13₹12 | $0.40₹38 | 256,000 | BF16 |
| SiliconFlow | $0.205₹19 | $0.14₹13 | $0.40₹38 | 262,144 | FP8 |
| $0.2625₹25 | $0.15₹14 | $0.60₹57 | 262,144 | Not listed |
Run it yourself instead: will gemma-4-26B-A4B-it fit your hardware?
gemma-4-31B-it
15 providers · context up to 262,144| Precision | |||||
|---|---|---|---|---|---|
| CoreWeaveCheapest | $0.16₹15 | $0.10₹9.43 | $0.34₹32 | 262,144 | FP4 |
| KT | $0.16₹15 | $0.10₹9.43 | $0.34₹32 | 262,144 | Not listed |
| Venice | $0.18₹17 | $0.12₹11 | $0.36₹34 | 256,000 | FP4 |
| Chutes | $0.1825₹17 | $0.12₹11 | $0.37₹35 | 131,072 | FP4 |
| DeepInfra | $0.20₹19 | $0.16₹15 | $0.32₹30 | 262,144 | FP8 |
| Crusoe | $0.205₹19 | $0.14₹13 | $0.40₹38 | 262,144 | BF16 |
| DekaLLM | $0.205₹19 | $0.14₹13 | $0.40₹38 | 262,144 | Not listed |
| Friendli | $0.205₹19 | $0.14₹13 | $0.40₹38 | 262,144 | Not listed |
| Novita | $0.205₹19 | $0.14₹13 | $0.40₹38 | 262,144 | BF16 |
| NextBit | $0.2125₹20 | $0.15₹14 | $0.40₹38 | 262,144 | FP4 |
| Parasail | $0.2125₹20 | $0.15₹14 | $0.40₹38 | 262,144 | FP8 |
| DeepInfra | $0.2288₹22 | $0.135₹13 | $0.51₹48 | 262,144 | FP4 |
| PrimeIntellect | $0.2338₹22 | $0.20₹19 | $0.335₹32 | 262,144 | FP4 |
| Modal | $0.28₹26 | $0.34₹32 | $0.10₹9.43 | 131,072 | Not listed |
| SambaNova | $0.5725₹54 | $0.38₹36 | $1.15₹108 | 131,072 | Not listed |
| SiliconFlow | $0.8125₹77 | $0.75₹71 | $1.00₹94 | 262,144 | FP8 |
Run it yourself instead: will gemma-4-31B-it fit your hardware?
gemma-3-12b-it
2 providers · context up to 131,072| Precision | |||||
|---|---|---|---|---|---|
| DeepInfraCheapest | $0.06₹5.66 | $0.04₹3.77 | $0.12₹11 | 131,072 | BF16 |
| NextBit | $0.0938₹8.84 | $0.075₹7.07 | $0.15₹14 | 131,072 | INT4 |
Run it yourself instead: will gemma-3-12b-it fit your hardware?
gemma-3-27b-it
4 providers · context up to 131,072| Precision | |||||
|---|---|---|---|---|---|
| DeepInfraCheapest | $0.10₹9.43 | $0.08₹7.54 | $0.16₹15 | 131,072 | FP8 |
| NextBit | $0.1475₹14 | $0.08₹7.54 | $0.35₹33 | 131,072 | FP8 |
| Nebius | $0.15₹14 | $0.10₹9.43 | $0.30₹28 | 110,000 | FP8 |
| Parasail | $0.1725₹16 | $0.08₹7.54 | $0.45₹42 | 131,072 | FP8 |
Run it yourself instead: will gemma-3-27b-it fit your hardware?
gemma-3-4b-it
2 providers · context up to 131,072| Precision | |||||
|---|---|---|---|---|---|
| ParasailCheapest | $0.0425₹4.01 | $0.04₹3.77 | $0.05₹4.71 | 131,072 | BF16 |
| DeepInfra | $0.0625₹5.89 | $0.05₹4.71 | $0.10₹9.43 | 131,072 | BF16 |
Run it yourself instead: will gemma-3-4b-it fit your hardware?
Google API pricing questions
What is the cheapest Google model API?
The lowest blended price is $0.0208 (₹1.96) per million tokens, for gemma-4-26B-A4B-it on PrimeIntellect at BF16. That offer charges $0.014 for input and $0.041 for output per million tokens.
How many providers serve gemma-4-26B-A4B-it?
15 providers on OpenRouter serve it. The ones with the lowest blended prices are PrimeIntellect, Darkbloom, NextBit, AkashML, Io Net and 10 more. The lowest blended price is $0.0208 (₹1.96) per million tokens, on PrimeIntellect at BF16.
Is Google API pricing in INR?
Providers list prices in US dollars, so we show the rupee price beside each one at ₹94.29 per $1 (rate fetched 14 Nov 2026). For example, the lowest blended offer for gemma-4-26B-A4B-it is PrimeIntellect at ₹1.32 for input and ₹3.87 for output per million tokens. Check the provider for taxes and the rate it charges.
How we compare prices
Offers come from OpenRouter's model listing, fetched 14 Nov 2026. Blended price weights input and output tokens 3 to 1. INR is shown beside USD at ₹94.29 per $1. Prices change, so check the provider before you build on a number.