Codestral-22B-v0.1 vs Gemma 2 2B IT vs solar-mini
solar-mini comes out ahead, 15 to 0 and 0 on our weighted score, and it is the cheaper option too.
Mistral AICodestral-22B-v0.1
0/100- ECI—
- Price—
- Context33K
GoogleGemma 2 2B IT
0/100- ECI—
- Price—
- Context8K
- Our pick
Upstagesolar-mini
15/100- ECI—
- Price$0.15 / $0.15
- Context33K
solar-mini is our pick
solar-mini is the better all-round choice, scoring 15/100 against Codestral-22B-v0.1 (0) and Gemma 2 2B IT (0). It leads 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 pricesolar-minisolar-mini $0.15 per 1M tokens (3:1 blend) · Codestral-22B-v0.1 and Gemma 2 2B IT unpriced
- Longest contextCodestral-22B-v0.1 and solar-miniCodestral-22B-v0.1 32,768 · solar-mini 32,768 · Gemma 2 2B IT 8,192 tokens
- Widest inputsSame inputsCodestral-22B-v0.1: Text · Gemma 2 2B IT: Text · solar-mini: Text
- Self-hostingCodestral-22B-v0.1 and Gemma 2 2B ITPublishes downloadable weights (Mistral AI Non-Production License and Gemma Terms of Use)
| Measure | Weight | Codestral-22B-v0.1 | Gemma 2 2B IT | solar-mini |
|---|---|---|---|---|
| Inputs & features | 60% | 0 | 0 | 25 |
| Context window | 40% | 0 | 0 | 0 |
| Overall | 100% | 0/100 | 0/100 | 15/100 |
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 | Codestral-22B-v0.1Mistral AI | Gemma 2 2B ITGoogle | solar-miniUpstage |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | — | — | $0.15 |
| Output | — | — | $0.15 |
| Cached input | — | — | — |
| Blended (3:1) | — | — | $0.15 |
| Long-context rate | — | — | Same rate |
| Price source | — | — | Official Upstage API |
| Limits | |||
| Context window | 32,768 tokens (best) | 8,192 tokens | 32,768 tokens (best) |
| Max output | 8,192 tokens (best) | 8,192 tokens (best) | 4,096 tokens |
| 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 | No | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenMistral AI Non-Production License | OpenGemma Terms of Use | Proprietary |
| API model ID | — | — | solar-mini |
| API providers | — | — | 1 |
| Released | May 29, 2024 | Jul 31, 2024 | Jun 12, 2024 |
| Knowledge cutoff | — | — | Sep 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-22B-v0.1—
- Gemma 2 2B IT—
- solar-mini$1.80
Which should you choose?
Which is better: Codestral-22B-v0.1, Gemma 2 2B IT or solar-mini?
solar-mini is the better all-round choice, scoring 15/100 against Codestral-22B-v0.1 (0) and Gemma 2 2B IT (0). It leads 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, Codestral-22B-v0.1, Gemma 2 2B IT or solar-mini?
solar-mini is cheaper at $0.15 input / $0.15 output per million tokens (official Upstage API price). . At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for solar-mini versus . Codestral-22B-v0.1 and Gemma 2 2B IT has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral-22B-v0.1 has not been scored yet, Gemma 2 2B IT has not been scored yet and solar-mini has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Codestral-22B-v0.1, Gemma 2 2B IT and solar-mini yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Codestral-22B-v0.1 and Gemma 2 2B IT does not support tool calling, which most coding agents need.
Which has the bigger context window?
Codestral-22B-v0.1 and solar-mini have the largest context windows (32,768 and 32,768 tokens), against 8,192 for Gemma 2 2B IT. Maximum output per response: Codestral-22B-v0.1 up to 8,192, Gemma 2 2B IT up to 8,192, solar-mini up to 4,096 tokens.
Which can read images, PDFs, audio or video?
Codestral-22B-v0.1 accepts text; Gemma 2 2B IT accepts text; solar-mini accepts text. They handle the same number of input types.
Are any of these open source?
Codestral-22B-v0.1 and Gemma 2 2B IT publishes its weights (Mistral AI Non-Production License and Gemma Terms of Use) and can be self-hosted; solar-mini is proprietary.
Which is newer?
Gemma 2 2B IT is the newest, released Jul 31, 2024. solar-mini came out Jun 12, 2024; Codestral-22B-v0.1 came out May 29, 2024. Knowledge cutoff: solar-mini Sep 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.
