Codestral 25.08 vs Gemini 2.5 Flash-Lite vs Voxtral Small 24B 2507
Gemini 2.5 Flash-Lite comes out ahead, 83 to 55 and 47 on our weighted score.
Mistral AICodestral 25.08
47/100- ECI—
- Price$0.30 / $0.90
- Context128K
- Our pick
GoogleGemini 2.5 Flash-Lite
83/100- ECI—
- Price$0.10 / $0.40
- Context1.05M
- Mistral AI
Voxtral Small 24B 2507
55/100- ECI—
- Price$0.10 / $0.40
- Context33K
Gemini 2.5 Flash-Lite is our pick
Gemini 2.5 Flash-Lite is the better all-round choice, scoring 83/100 against Voxtral Small 24B 2507 (55) and Codestral 25.08 (47). 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 priceGemini 2.5 Flash-Lite and Voxtral Small 24B 2507Gemini 2.5 Flash-Lite $0.175 · Voxtral Small 24B 2507 $0.175 · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
- Longest contextGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite 1,048,576 · Codestral 25.08 128,000 · Voxtral Small 24B 2507 32,768 tokens
- Widest inputsGemini 2.5 Flash-LiteCodestral 25.08: Text · Gemini 2.5 Flash-Lite: Text, Images, PDFs, Audio, Video · Voxtral Small 24B 2507: Text, Audio
- Self-hostingVoxtral Small 24B 2507Publishes downloadable weights (Apache 2.0)
| Measure | Weight | Codestral 25.08 | Gemini 2.5 Flash-Lite | Voxtral Small 24B 2507 |
|---|---|---|---|---|
| Price | 50% | 64 | 82 | 82 |
| Inputs & features | 30% | 35 | 100 | 45 |
| Context window | 20% | 24 | 61 | 0 |
| Overall | 100% | 47/100 | 83/100 | 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 | Codestral 25.08Mistral AI | Gemini 2.5 Flash-LiteGoogle | Voxtral Small 24B 2507Mistral AI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.30 | $0.10 (best) | $0.10 (best) |
| Output | $0.90 | $0.40 (best) | $0.40 (best) |
| Cached input | $0.03 | $0.01 (best) | — |
| Blended (3:1) | $0.45 | $0.175 (best) | $0.175 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official Google API | Official Mistral API |
| Limits | |||
| Context window | 128,000 tokens | 1,048,576 tokens (best) | 32,768 tokens |
| Max output | 8,192 tokens | 65,536 tokens (best) | 32,768 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | Yes | Yes |
| Video | No | Yes | No |
| Reasoning | No | Yes | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Proprietary | Proprietary | OpenApache 2.0 |
| API model ID | codestral-2508 | gemini-2.5-flash-lite | voxtral-small-latest |
| API providers | 11 | 24 (best) | 10 |
| Released | Jul 30, 2025 | Jun 17, 2025 | Jul 15, 2025 |
| Knowledge cutoff | — | Jan 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Codestral 25.08$4.80
- Gemini 2.5 Flash-Lite$1.80
- Voxtral Small 24B 2507$1.80
Which should you choose?
Which is better: Codestral 25.08, Gemini 2.5 Flash-Lite or Voxtral Small 24B 2507?
Gemini 2.5 Flash-Lite is the better all-round choice, scoring 83/100 against Voxtral Small 24B 2507 (55) and Codestral 25.08 (47). 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, Codestral 25.08, Gemini 2.5 Flash-Lite or Voxtral Small 24B 2507?
Gemini 2.5 Flash-Lite is cheaper at $0.10 input / $0.40 output per million tokens (official Google API price). Voxtral Small 24B 2507 costs $0.10 input / $0.40 output per million tokens (official Mistral 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 $0.175 per million tokens for Gemini 2.5 Flash-Lite versus $0.175 for Voxtral Small 24B 2507 (1× as much) and $0.45 for Codestral 25.08 (2.6× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Codestral 25.08 has not been scored yet, Gemini 2.5 Flash-Lite 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 Codestral 25.08, Gemini 2.5 Flash-Lite 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?
Gemini 2.5 Flash-Lite has the largest context window at 1,048,576 tokens, against 128,000 for Codestral 25.08 and 32,768 for Voxtral Small 24B 2507. Maximum output per response: Codestral 25.08 up to 8,192, Gemini 2.5 Flash-Lite up to 65,536, Voxtral Small 24B 2507 up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Codestral 25.08 accepts text; Gemini 2.5 Flash-Lite accepts text, images, PDFs, audio and video; Voxtral Small 24B 2507 accepts text and audio. Gemini 2.5 Flash-Lite handles the widest range of inputs.
Are any of these open source?
Voxtral Small 24B 2507 publishes its weights (Apache 2.0) and can be self-hosted; Codestral 25.08 and Gemini 2.5 Flash-Lite is proprietary.
Which is newer?
Codestral 25.08 is the newest, released Jul 30, 2025. Voxtral Small 24B 2507 came out Jul 15, 2025; Gemini 2.5 Flash-Lite came out Jun 17, 2025. Knowledge cutoff: Gemini 2.5 Flash-Lite Jan 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.
