Codestral vs Qwen Plus Character (Japanese) vs SOLAR 10.7B Instruct v1.0
Codestral comes out ahead, 35 to 0 and 0 on our weighted score, and it is the cheaper option too.
- Our pick
Mistral AICodestral
35/100- ECI—
- Price$0.30 / $0.90
- Context256K
Alibaba (Qwen)Qwen Plus Character (Japanese)
0/100- ECI—
- Price$0.50 / $1.40
- Context8K
UpstageSOLAR 10.7B Instruct v1.0
0/100- ECI—
- Price—
- Context4K
Codestral is our pick
Codestral is the better all-round choice, scoring 35/100 against Qwen Plus Character (Japanese) (0) and SOLAR 10.7B Instruct v1.0 (0). 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 · Qwen Plus Character (Japanese) $0.725 per 1M tokens (3:1 blend) · SOLAR 10.7B Instruct v1.0 unpriced
- Longest contextCodestralCodestral 256,000 · Qwen Plus Character (Japanese) 8,192 · SOLAR 10.7B Instruct v1.0 4,096 tokens
- Widest inputsSame inputsCodestral: Text · Qwen Plus Character (Japanese): Text · SOLAR 10.7B Instruct v1.0: Text
- Self-hostingCodestral and SOLAR 10.7B Instruct v1.0Publishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | Codestral | Qwen Plus Character (Japanese) | SOLAR 10.7B Instruct v1.0 |
|---|---|---|---|---|
| Inputs & features | 60% | 35 | 0 | 0 |
| Context window | 40% | 36 | 0 | 0 |
| Overall | 100% | 35/100 | 0/100 | 0/100 |
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 | Qwen Plus Character (Japanese)Alibaba (Qwen) | SOLAR 10.7B Instruct v1.0Upstage |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 (best) | $0.50 | — |
| Output | $0.90 (best) | $1.40 | — |
| Cached input | $0.03 | — | — |
| Blended (3:1) | $0.45 (best) | $0.725 | — |
| Long-context rate | Same rate | Same rate | — |
| Price source | Official Mistral API | Official Alibaba API | — |
| Limits | |||
| Context window | 256,000 tokens (best) | 8,192 tokens | 4,096 tokens |
| Max output | 4,096 tokens (best) | 512 tokens | 4,096 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | No | No |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Open | Proprietary | OpenCC-BY-NC-4.0 |
| API model ID | codestral-latest | qwen-plus-character-ja | — |
| API providers | 4 (best) | 1 | — |
| Released | May 29, 2024 | Jan 2024 | Dec 12, 2023 |
| Knowledge cutoff | Oct 2024 | Apr 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
- Qwen Plus Character (Japanese)$7.80
- SOLAR 10.7B Instruct v1.0—
Which should you choose?
Which is better: Codestral, Qwen Plus Character (Japanese) or SOLAR 10.7B Instruct v1.0?
Codestral is the better all-round choice, scoring 35/100 against Qwen Plus Character (Japanese) (0) and SOLAR 10.7B Instruct v1.0 (0). 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, Qwen Plus Character (Japanese) or SOLAR 10.7B Instruct v1.0?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen Plus Character (Japanese) costs $0.50 input / $1.40 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus $0.725 for Qwen Plus Character (Japanese) (1.6× as much). SOLAR 10.7B Instruct v1.0 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, Qwen Plus Character (Japanese) has not been scored yet and SOLAR 10.7B Instruct v1.0 has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral, Qwen Plus Character (Japanese) and SOLAR 10.7B Instruct v1.0 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Qwen Plus Character (Japanese) and SOLAR 10.7B Instruct v1.0 does not support tool calling, which most coding agents need.
Which has the bigger context window?
Codestral has the largest context window at 256,000 tokens, against 8,192 for Qwen Plus Character (Japanese) and 4,096 for SOLAR 10.7B Instruct v1.0. Maximum output per response: Codestral up to 4,096, Qwen Plus Character (Japanese) up to 512, SOLAR 10.7B Instruct v1.0 up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Codestral accepts text; Qwen Plus Character (Japanese) accepts text; SOLAR 10.7B Instruct v1.0 accepts text. They handle the same number of input types.
Are any of these open source?
Codestral and SOLAR 10.7B Instruct v1.0 publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Qwen Plus Character (Japanese) is proprietary.
Which is newer?
Codestral is the newest, released May 29, 2024. Qwen Plus Character (Japanese) came out Jan 2024; SOLAR 10.7B Instruct v1.0 came out Dec 12, 2023. Knowledge cutoff: Codestral Oct 2024, Qwen Plus Character (Japanese) Apr 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 Nov 2, 2026.
