Codestral vs Mistral Large 2.1 vs Vision Large
Vision Large comes out ahead, 84 to 29 and 25 on our weighted score.
Mistral AICodestral
29/100- ECI—
- Price$0.30 / $0.90
- Context256K
- Mistral AI
Mistral Large 2.1
25/100- ECI128.5
- Price$2.00 / $6.00
- Context131K
- Our pick
VisparkVision Large
84/100- ECI—
- Price—
- Context1M
Vision Large is our pick
Vision Large is the better all-round choice, scoring 84/100 against Codestral (29) and Mistral Large 2.1 (25). 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 priceCodestralCodestral $0.45 · Mistral Large 2.1 $3.00 per 1M tokens (3:1 blend) · Vision Large unpriced
- Longest contextVision LargeVision Large 1,000,000 · Codestral 256,000 · Mistral Large 2.1 131,072 tokens
- Widest inputsVision LargeCodestral: Text · Mistral Large 2.1: Text · Vision Large: Text, Images, PDFs, Audio, Video
- Self-hostingCodestral and Mistral Large 2.1Publishes downloadable weights
| Measure | Weight | Codestral | Mistral Large 2.1 | Vision Large |
|---|---|---|---|---|
| Inputs & features | 60% | 25 | 25 | 100 |
| Context window | 40% | 36 | 24 | 60 |
| Overall | 100% | 29/100 | 25/100 | 84/100 |
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 | CodestralMistral AI | Mistral Large 2.1Mistral AI | Vision LargeVispark |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 128.5 | — |
| ECI rank | — | #130 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 51.3% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 7.8% | — |
| Price per million tokens | |||
| Input | $0.30 (best) | $2.00 | — |
| Output | $0.90 (best) | $6.00 | — |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 (best) | $3.00 | — |
| Long-context rate | Same rate | Same rate | — |
| Price source | Official Mistral API | Official Mistral API | — |
| Limits | |||
| Context window | 256,000 tokens | 131,072 tokens | 1,000,000 tokens (best) |
| Max output | 4,096 tokens | 16,384 tokens | 65,536 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | codestral-latest | mistral-large-2411 | — |
| API providers | 3 (best) | 2 | — |
| Released | May 29, 2024 | Nov 18, 2024 | May 15, 2024 |
| Knowledge cutoff | Oct 2024 | 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.
- Codestral$4.80
- Mistral Large 2.1$32.00
- Vision Large—
Which should you choose?
Which is better: Codestral, Mistral Large 2.1 or Vision Large?
Vision Large is the better all-round choice, scoring 84/100 against Codestral (29) and Mistral Large 2.1 (25). 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, Codestral, Mistral Large 2.1 or Vision Large?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Mistral Large 2.1 costs $2.00 input / $6.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus $3.00 for Mistral Large 2.1 (6.7× as much). Vision Large has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Mistral Large 2.1 has an ECI of 128.5 and Vision Large has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral, Mistral Large 2.1 and Vision Large 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?
Vision Large has the largest context window at 1,000,000 tokens, against 256,000 for Codestral and 131,072 for Mistral Large 2.1. Maximum output per response: Codestral up to 4,096, Mistral Large 2.1 up to 16,384, Vision Large up to 65,536 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Mistral Large 2.1 accepts text; Vision Large accepts text, images, PDFs, audio and video. Vision Large handles the widest range of inputs.
Are any of these open source?
Codestral and Mistral Large 2.1 publishes its weights and can be self-hosted; Vision Large is proprietary.
Which is newer?
Mistral Large 2.1 is the newest, released Nov 18, 2024. Codestral came out May 29, 2024; Vision Large came out May 15, 2024. Knowledge cutoff: Codestral Oct 2024, Mistral Large 2.1 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.
