DeepSeek OCR 2 vs Sarvam 105B vs Trinity Large Preview
Trinity Large Preview comes out ahead, 34 to 31 and 15 on our weighted score.
DeepSeekDeepSeek OCR 2
15/100- ECI—
- Price$0.89 / $1.47
- Context8K
Sarvam AI
Sarvam 105B
31/100- ECI—
- Price$0.047 / $0.186
- Context131K
- Our pick
Arcee AITrinity Large Preview
34/100- ECI—
- Price—
- Context524K
Trinity Large Preview is our pick
Trinity Large Preview is the better all-round choice, scoring 34/100 against Sarvam 105B (31) and DeepSeek OCR 2 (15). It leads on context window. Sarvam 105B wins on inputs & features. 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 priceSarvam 105BSarvam 105B $0.082 · DeepSeek OCR 2 $1.03 per 1M tokens (3:1 blend) · Trinity Large Preview unpriced
- Longest contextTrinity Large PreviewTrinity Large Preview 524,288 · Sarvam 105B 131,072 · DeepSeek OCR 2 8,192 tokens
- Widest inputsDeepSeek OCR 2DeepSeek OCR 2: Text, Images · Sarvam 105B: Text · Trinity Large Preview: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | DeepSeek OCR 2 | Sarvam 105B | Trinity Large Preview |
|---|---|---|---|---|
| Inputs & features | 60% | 25 | 35 | 25 |
| Context window | 40% | 0 | 24 | 49 |
| Overall | 100% | 15/100 | 31/100 | 34/100 |
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 | DeepSeek OCR 2DeepSeek | Sarvam 105BSarvam AI | Trinity Large PreviewArcee AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.89 | $0.047 (best) | — |
| Output | $1.47 | $0.186 (best) | — |
| Cached input | — | — | — |
| Blended (3:1) | $1.03 | $0.082 (best) | — |
| Long-context rate | Same rate | Same rate | — |
| Price source | Median of 1 providers | Median of 2 providers | — |
| Limits | |||
| Context window | 8,192 tokens | 131,072 tokens | 524,288 tokens (best) |
| Max output | 8,192 tokens | 131,072 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | Yes · low · medium · high | No |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | OpenOpenMDW-1.1 |
| API model ID | — | sarvam-105b | — |
| API providers | 2 | 3 (best) | 1 |
| Released | Jan 27, 2026 | Sep 1, 2025 | Jan 27, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- DeepSeek OCR 2$11.83
- Sarvam 105B$0.842
- Trinity Large Preview—
Which should you choose?
Which is better: DeepSeek OCR 2, Sarvam 105B or Trinity Large Preview?
Trinity Large Preview is the better all-round choice, scoring 34/100 against Sarvam 105B (31) and DeepSeek OCR 2 (15). It leads on context window. Sarvam 105B wins on inputs & features. 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, DeepSeek OCR 2, Sarvam 105B or Trinity Large Preview?
Sarvam 105B is cheaper at $0.047 input / $0.186 output per million tokens (median across 2 API providers). DeepSeek OCR 2 costs $0.89 input / $1.47 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.082 per million tokens for Sarvam 105B versus $1.03 for DeepSeek OCR 2 (13× as much). Trinity Large Preview has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. DeepSeek OCR 2 has not been scored yet, Sarvam 105B has not been scored yet and Trinity Large Preview has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for DeepSeek OCR 2, Sarvam 105B and Trinity Large Preview yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that DeepSeek OCR 2 does not support tool calling, which most coding agents need.
Which has the bigger context window?
Trinity Large Preview has the largest context window at 524,288 tokens, against 131,072 for Sarvam 105B and 8,192 for DeepSeek OCR 2. Maximum output per response: DeepSeek OCR 2 up to 8,192, Sarvam 105B up to 131,072, Trinity Large Preview up to 262,144 tokens.
Which can read images, PDFs, audio or video?
DeepSeek OCR 2 accepts text and images; Sarvam 105B accepts text; Trinity Large Preview accepts text. DeepSeek OCR 2 handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (OpenMDW-1.1), so you can self-host them.
Which is newer?
DeepSeek OCR 2 is the newest, released Jan 27, 2026. Trinity Large Preview came out Jan 27, 2026; Sarvam 105B came out Sep 1, 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 Oct 4, 2026.
