Nova 2 Lite vs Voxtral Small 24B 2507 vs Mistral Large 3
Nova 2 Lite comes out ahead, 62 to 55 and 50 on our weighted score, though Voxtral Small 24B 2507 is 6.2× cheaper per token.
- Our pick
AmazonNova 2 Lite
62/100- ECI—
- Price$0.33 / $2.75
- Context1M
Mistral AIVoxtral Small 24B 2507
55/100- ECI—
- Price$0.10 / $0.30
- Context33K
- Mistral AI
Mistral Large 3
50/100- ECI—
- Price$0.50 / $1.50
- Context262K
Nova 2 Lite is our pick
Nova 2 Lite is the better all-round choice, scoring 62/100 against Voxtral Small 24B 2507 (55) and Mistral Large 3 (50). It leads on inputs & features and context window. Voxtral Small 24B 2507 wins on price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceVoxtral Small 24B 2507Voxtral Small 24B 2507 $0.15 · Mistral Large 3 $0.75 · Nova 2 Lite $0.935 per 1M tokens (3:1 blend)
- Longest contextNova 2 LiteNova 2 Lite 1,000,000 · Mistral Large 3 262,144 · Voxtral Small 24B 2507 32,768 tokens
- Widest inputsNova 2 LiteNova 2 Lite: Text, Images, PDFs, Video · Voxtral Small 24B 2507: Text, Audio · Mistral Large 3: Text, Images
- Self-hostingVoxtral Small 24B 2507 and Mistral Large 3Publishes downloadable weights (Apache 2.0)
| Measure | Weight | Nova 2 Lite | Voxtral Small 24B 2507 | Mistral Large 3 |
|---|---|---|---|---|
| Price | 50% | 51 | 89 | 56 |
| Inputs & features | 30% | 80 | 35 | 50 |
| Context window | 20% | 60 | 0 | 37 |
| Overall | 100% | 62/100 | 55/100 | 50/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Nova 2 LiteAmazon | Voxtral Small 24B 2507Mistral AI | Mistral Large 3Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.33 | $0.10 (best) | $0.50 |
| Output | $2.75 | $0.30 (best) | $1.50 |
| Cached input | $0.083 | — | $0.05 (best) |
| Blended (3:1) | $0.935 | $0.15 (best) | $0.75 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Amazon Bedrock API | Official Mistral API | Official Mistral API |
| Limits | |||
| Context window | 1,000,000 tokens (best) | 32,768 tokens | 262,144 tokens |
| Max output | 65,536 tokens | 32,768 tokens | 262,144 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | Yes | No | No |
| Audio | No | Yes | No |
| Video | Yes | No | No |
| Reasoning | Yeslow · medium · high | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenApache 2.0 | Open |
| API model ID | amazon.nova-2-lite-v1:0 | voxtral-small-latest | mistral-large-2512 |
| API providers | 2 | 7 | 13 (best) |
| Released | Dec 2, 2025 | Jul 15, 2025 | Dec 2, 2025 |
| Knowledge cutoff | Oct 2025 | — | Nov 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Nova 2 Lite$8.80
- Voxtral Small 24B 2507$1.60
- Mistral Large 3$8.00
Which should you choose?
Which is better: Nova 2 Lite, Voxtral Small 24B 2507 or Mistral Large 3?
Nova 2 Lite is the better all-round choice, scoring 62/100 against Voxtral Small 24B 2507 (55) and Mistral Large 3 (50). It leads on inputs & features and context window. Voxtral Small 24B 2507 wins on price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Nova 2 Lite, Voxtral Small 24B 2507 or Mistral Large 3?
Voxtral Small 24B 2507 is cheaper at $0.10 input / $0.30 output per million tokens (official Mistral API price). Mistral Large 3 costs $0.50 input / $1.50 output per million tokens (official Mistral API price); Nova 2 Lite costs $0.33 input / $2.75 output per million tokens (official Amazon Bedrock API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Voxtral Small 24B 2507 versus $0.75 for Mistral Large 3 (5× as much) and $0.935 for Nova 2 Lite (6.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Nova 2 Lite has not been scored yet, Voxtral Small 24B 2507 has not been scored yet and Mistral Large 3 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Nova 2 Lite, Voxtral Small 24B 2507 and Mistral Large 3 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?
Nova 2 Lite has the largest context window at 1,000,000 tokens, against 262,144 for Mistral Large 3 and 32,768 for Voxtral Small 24B 2507. Maximum output per response: Nova 2 Lite up to 65,536, Voxtral Small 24B 2507 up to 32,768, Mistral Large 3 up to 262,144 tokens.
Which can read images, PDFs, audio or video?
Nova 2 Lite accepts text, images, PDFs and video; Voxtral Small 24B 2507 accepts text and audio; Mistral Large 3 accepts text and images. Nova 2 Lite handles the widest range of inputs.
Are any of these open source?
Voxtral Small 24B 2507 and Mistral Large 3 publishes its weights (Apache 2.0) and can be self-hosted; Nova 2 Lite is proprietary.
Which is newer?
Nova 2 Lite is the newest, released Dec 2, 2025. Mistral Large 3 came out Dec 2, 2025; Voxtral Small 24B 2507 came out Jul 15, 2025. Knowledge cutoff: Nova 2 Lite Oct 2025, Mistral Large 3 Nov 2024.
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.
