solar-mini vs Codestral 25.08 vs Hermes 2 Pro Llama 3 8B
Too close to call on our weighted score (Hermes 2 Pro Llama 3 8B 51, solar-mini 50, Codestral 25.08 47). The right pick depends on what you value most.
Upstagesolar-mini
50/100- ECI—
- Price$0.15 / $0.15
- Context33K
Mistral AICodestral 25.08
47/100- ECI—
- Price$0.30 / $0.90
- Context128K
Nous ResearchHermes 2 Pro Llama 3 8B
51/100- ECI—
- Price$0.14 / $0.14
- Context8K
Too close to call
It is close. Our weighted score puts them within a point (Hermes 2 Pro Llama 3 8B 51/100, solar-mini 50/100, Codestral 25.08 47/100), so choose by what matters most for your work: Hermes 2 Pro Llama 3 8B on price and Codestral 25.08 for long inputs. 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 priceHermes 2 Pro Llama 3 8BHermes 2 Pro Llama 3 8B $0.14 · solar-mini $0.15 · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
- Longest contextCodestral 25.08Codestral 25.08 128,000 · solar-mini 32,768 · Hermes 2 Pro Llama 3 8B 8,192 tokens
- Widest inputsSame inputssolar-mini: Text · Codestral 25.08: Text · Hermes 2 Pro Llama 3 8B: Text
- Self-hostingHermes 2 Pro Llama 3 8BPublishes downloadable weights (Llama 3 Community License)
| Measure | Weight | solar-mini | Codestral 25.08 | Hermes 2 Pro Llama 3 8B |
|---|---|---|---|---|
| Price | 50% | 85 | 64 | 87 |
| Inputs & features | 30% | 25 | 35 | 25 |
| Context window | 20% | 0 | 24 | 0 |
| Overall | 100% | 50/100 | 47/100 | 51/100 |
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 | solar-miniUpstage | Codestral 25.08Mistral AI | Hermes 2 Pro Llama 3 8BNous Research |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.15 | $0.30 | $0.14 (best) |
| Output | $0.15 | $0.90 | $0.14 (best) |
| Cached input | — | $0.03 | — |
| Blended (3:1) | $0.15 | $0.45 | $0.14 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Upstage API | Official Mistral API | Median of 2 providers |
| Limits | |||
| Context window | 32,768 tokens | 128,000 tokens (best) | 8,192 tokens |
| Max output | 4,096 tokens | 8,192 tokens (best) | 8,192 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 | Yes | Yes |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Proprietary | Proprietary | OpenLlama 3 Community License |
| API model ID | solar-mini | codestral-2508 | — |
| API providers | 1 | 11 (best) | 2 |
| Released | Jun 12, 2024 | Jul 30, 2025 | Apr 30, 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.
- solar-mini$1.80
- Codestral 25.08$4.80
- Hermes 2 Pro Llama 3 8B$1.68
Which should you choose?
Which is better: solar-mini, Codestral 25.08 or Hermes 2 Pro Llama 3 8B?
It is close. Our weighted score puts them within a point (Hermes 2 Pro Llama 3 8B 51/100, solar-mini 50/100, Codestral 25.08 47/100), so choose by what matters most for your work: Hermes 2 Pro Llama 3 8B on price and Codestral 25.08 for long inputs. 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, solar-mini, Codestral 25.08 or Hermes 2 Pro Llama 3 8B?
Hermes 2 Pro Llama 3 8B is cheaper at $0.14 input / $0.14 output per million tokens (median across 2 API providers). solar-mini costs $0.15 input / $0.15 output per million tokens (official Upstage API price); Codestral 25.08 costs $0.30 input / $0.90 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.14 per million tokens for Hermes 2 Pro Llama 3 8B versus $0.15 for solar-mini (1.1× as much) and $0.45 for Codestral 25.08 (3.2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. solar-mini has not been scored yet, Codestral 25.08 has not been scored yet and Hermes 2 Pro Llama 3 8B has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for solar-mini, Codestral 25.08 and Hermes 2 Pro Llama 3 8B 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?
Codestral 25.08 has the largest context window at 128,000 tokens, against 32,768 for solar-mini and 8,192 for Hermes 2 Pro Llama 3 8B. Maximum output per response: solar-mini up to 4,096, Codestral 25.08 up to 8,192, Hermes 2 Pro Llama 3 8B up to 8,192 tokens.
Which can read images, PDFs, audio or video?
solar-mini accepts text; Codestral 25.08 accepts text; Hermes 2 Pro Llama 3 8B accepts text. They handle the same number of input types.
Are any of these open source?
Hermes 2 Pro Llama 3 8B publishes its weights (Llama 3 Community License) and can be self-hosted; solar-mini and Codestral 25.08 is proprietary.
Which is newer?
Codestral 25.08 is the newest, released Jul 30, 2025. solar-mini came out Jun 12, 2024; Hermes 2 Pro Llama 3 8B came out Apr 30, 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.
