Ministral 3 8B vs Rnj-1 Instruct vs Voxtral Small 24B 2507
Ministral 3 8B comes out ahead, 68 to 55 and 50 on our weighted score.
- Our pick
Mistral AIMinistral 3 8B
68/100- ECI—
- Price$0.15 / $0.15
- Context262K
Essential AI
Rnj-1 Instruct
50/100- ECI—
- Price$0.15 / $0.15
- Context33K
- Mistral AI
Voxtral Small 24B 2507
55/100- ECI—
- Price$0.10 / $0.40
- Context33K
Ministral 3 8B is our pick
Ministral 3 8B is the better all-round choice, scoring 68/100 against Voxtral Small 24B 2507 (55) and Rnj-1 Instruct (50). It leads on inputs & features and context window. 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 priceMinistral 3 8B and Rnj-1 InstructMinistral 3 8B $0.15 · Rnj-1 Instruct $0.15 · Voxtral Small 24B 2507 $0.175 per 1M tokens (3:1 blend)
- Longest contextMinistral 3 8BMinistral 3 8B 262,144 · Rnj-1 Instruct 32,768 · Voxtral Small 24B 2507 32,768 tokens
- Widest inputsMinistral 3 8B and Voxtral Small 24B 2507Ministral 3 8B: Text, Images · Rnj-1 Instruct: Text · Voxtral Small 24B 2507: Text, Audio
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Ministral 3 8B | Rnj-1 Instruct | Voxtral Small 24B 2507 |
|---|---|---|---|---|
| Price | 50% | 85 | 85 | 82 |
| Inputs & features | 30% | 60 | 25 | 45 |
| Context window | 20% | 37 | 0 | 0 |
| Overall | 100% | 68/100 | 50/100 | 55/100 |
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 | Ministral 3 8BMistral AI | Rnj-1 InstructEssential AI | Voxtral Small 24B 2507Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.15 | $0.15 | $0.10 (best) |
| Output | $0.15 (best) | $0.15 (best) | $0.40 |
| Cached input | $0.015 | — | — |
| Blended (3:1) | $0.15 (best) | $0.15 (best) | $0.175 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Median of 1 providers | Official Mistral API |
| Limits | |||
| Context window | 262,144 tokens (best) | 32,768 tokens | 32,768 tokens |
| Max output | 262,144 tokens (best) | 32,768 tokens | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | Yes |
| Availability | |||
| Weights | OpenApache 2.0 | OpenApache 2.0 | OpenApache 2.0 |
| API model ID | ministral-8b-2512 | — | voxtral-small-latest |
| API providers | 11 (best) | 1 | 10 |
| Released | Dec 2, 2025 | Dec 4, 2025 | Jul 15, 2025 |
| 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.
- Ministral 3 8B$1.80
- Rnj-1 Instruct$1.80
- Voxtral Small 24B 2507$1.80
Which should you choose?
Which is better: Ministral 3 8B, Rnj-1 Instruct or Voxtral Small 24B 2507?
Ministral 3 8B is the better all-round choice, scoring 68/100 against Voxtral Small 24B 2507 (55) and Rnj-1 Instruct (50). It leads on inputs & features and context window. 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, Ministral 3 8B, Rnj-1 Instruct or Voxtral Small 24B 2507?
Ministral 3 8B is cheaper at $0.15 input / $0.15 output per million tokens (official Mistral API price). Rnj-1 Instruct costs $0.15 input / $0.15 output per million tokens (median across 1 API provider); Voxtral Small 24B 2507 costs $0.10 input / $0.40 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Ministral 3 8B versus $0.15 for Rnj-1 Instruct (1× as much) and $0.175 for Voxtral Small 24B 2507 (1.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Ministral 3 8B has not been scored yet, Rnj-1 Instruct has not been scored yet and Voxtral Small 24B 2507 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Ministral 3 8B, Rnj-1 Instruct and Voxtral Small 24B 2507 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?
Ministral 3 8B has the largest context window at 262,144 tokens, against 32,768 for Rnj-1 Instruct and 32,768 for Voxtral Small 24B 2507. Maximum output per response: Ministral 3 8B up to 262,144, Rnj-1 Instruct up to 32,768, Voxtral Small 24B 2507 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Ministral 3 8B accepts text and images; Rnj-1 Instruct accepts text; Voxtral Small 24B 2507 accepts text and audio. Ministral 3 8B handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights (Apache 2.0), so you can self-host them.
Which is newer?
Rnj-1 Instruct is the newest, released Dec 4, 2025. Ministral 3 8B came out Dec 2, 2025; Voxtral Small 24B 2507 came out Jul 15, 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.
