Gemini 2.5 Flash-Lite vs Sarvam 105B vs Tiny Aya Earth
Gemini 2.5 Flash-Lite comes out ahead, 84 to 31 and 15 on our weighted score, and it is the cheaper option too.
- Our pick
GoogleGemini 2.5 Flash-Lite
84/100- ECI—
- Price$0.10 / $0.40
- Context1.05M
Sarvam AI
Sarvam 105B
31/100- ECI—
- Price$0.158 / $0.632
- Context131K
CohereTiny Aya Earth
15/100- ECI—
- Price—
- Context8K
Gemini 2.5 Flash-Lite is our pick
Gemini 2.5 Flash-Lite is the better all-round choice, scoring 84/100 against Sarvam 105B (31) and Tiny Aya Earth (15). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite $0.175 · Sarvam 105B $0.276 per 1M tokens (3:1 blend) · Tiny Aya Earth unpriced
- Longest contextGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite 1,048,576 · Sarvam 105B 131,072 · Tiny Aya Earth 8,000 tokens
- Widest inputsGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite: Text, Images, PDFs, Audio, Video · Sarvam 105B: Text · Tiny Aya Earth: Text
- Self-hostingSarvam 105B and Tiny Aya EarthPublishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | Gemini 2.5 Flash-Lite | Sarvam 105B | Tiny Aya Earth |
|---|---|---|---|---|
| Inputs & features | 60% | 100 | 35 | 25 |
| Context window | 40% | 61 | 25 | 0 |
| Overall | 100% | 84/100 | 31/100 | 15/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Gemini 2.5 Flash-LiteGoogle | Sarvam 105BSarvam AI | Tiny Aya EarthCohere |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.10 (best) | $0.158 | — |
| Output | $0.40 (best) | $0.632 | — |
| Cached input | $0.01 (best) | $0.053 | — |
| Blended (3:1) | $0.175 (best) | $0.276 | — |
| Long-context rate | Same rate | Same rate | — |
| Price source | Official Google API | Official Sarvam AI API | — |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 131,072 tokens | 8,000 tokens |
| Max output | 65,536 tokens | 131,072 tokens (best) | 8,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | Yes | No | No |
| Video | Yes | No | No |
| Reasoning | Yes | Yeslow · medium · high | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | OpenCC-BY-NC-4.0 |
| API model ID | gemini-2.5-flash-lite | sarvam-105b | tiny-aya-earth |
| API providers | 24 (best) | 3 | 1 |
| Released | Jun 17, 2025 | Feb 18, 2026 | Feb 17, 2026 |
| Knowledge cutoff | Jan 2025 | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Gemini 2.5 Flash-Lite$1.80
- Sarvam 105B$2.84
- Tiny Aya Earth—
Which should you choose?
Which is better: Gemini 2.5 Flash-Lite, Sarvam 105B or Tiny Aya Earth?
Gemini 2.5 Flash-Lite is the better all-round choice, scoring 84/100 against Sarvam 105B (31) and Tiny Aya Earth (15). It leads on inputs & features and context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Gemini 2.5 Flash-Lite, Sarvam 105B or Tiny Aya Earth?
Gemini 2.5 Flash-Lite is cheaper at $0.10 input / $0.40 output per million tokens (official Google API price). Sarvam 105B costs $0.158 input / $0.632 output per million tokens (official Sarvam AI API price). At a typical mix of three input tokens to one output token, that is $0.175 per million tokens for Gemini 2.5 Flash-Lite versus $0.276 for Sarvam 105B (1.6× as much). Tiny Aya Earth has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Gemini 2.5 Flash-Lite has not been scored yet, Sarvam 105B has not been scored yet and Tiny Aya Earth has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Gemini 2.5 Flash-Lite, Sarvam 105B and Tiny Aya Earth yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Gemini 2.5 Flash-Lite has the largest context window at 1,048,576 tokens, against 131,072 for Sarvam 105B and 8,000 for Tiny Aya Earth. Maximum output per response: Gemini 2.5 Flash-Lite up to 65,536, Sarvam 105B up to 131,072, Tiny Aya Earth up to 8,000 tokens.
Which can read images, PDFs, audio or video?
Gemini 2.5 Flash-Lite accepts text, images, PDFs, audio and video; Sarvam 105B accepts text; Tiny Aya Earth accepts text. Gemini 2.5 Flash-Lite handles the widest range of inputs.
Are any of these open source?
Sarvam 105B and Tiny Aya Earth publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Gemini 2.5 Flash-Lite is proprietary.
Which is newer?
Sarvam 105B is the newest, released Feb 18, 2026. Tiny Aya Earth came out Feb 17, 2026; Gemini 2.5 Flash-Lite came out Jun 17, 2025. Knowledge cutoff: Gemini 2.5 Flash-Lite Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
