ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Codestral vs Gemini 2.5 Flash-Lite vs Solar Pro 2

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Mistral AI

    Codestral

    Released May 29, 2024

    51/100
    • ECI—
    • Price$0.30 / $0.90
    • Context256K
  2. Google

    Gemini 2.5 Flash-Lite

    Released Jun 17, 2025

    84/100
    • ECI—
    • Price$0.10 / $0.40
    • Context1.05M
  3. Upstage

    Solar Pro 2

    Released May 20, 2025

    52/100
    • ECI—
    • Price$0.25 / $0.25
    • Context66K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Flash-Lite 84/100, Solar Pro 2 52/100, Codestral 51/100) compare the available specifications and price. 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-LiteGemini 2.5 Flash-Lite $0.175 · Solar Pro 2 $0.25 · Codestral $0.45 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite 1,048,576 · Codestral 256,000 · Solar Pro 2 65,536 tokens
  • Widest inputsGemini 2.5 Flash-LiteCodestral: Text · Gemini 2.5 Flash-Lite: Text, Images, PDFs, Audio, Video · Solar Pro 2: Text
  • Self-hostingCodestralPublishes downloadable weights
How the score is built
MeasureWeightCodestralGemini 2.5 Flash-LiteSolar Pro 2
Price50%638275
Inputs & features30%3510035
Context window20%436522
Specs & price only100%51/10084/10052/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Codestral vs Gemini 2.5 Flash-Lite vs Solar Pro 2 specifications side by side
SpecificationCodestralMistral AIGemini 2.5 Flash-LiteGoogleSolar Pro 2Upstage
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.10 (best)$0.25
Output$0.90$0.40$0.25 (best)
Cached input$0.03$0.01 (best)—
Blended (3:1)$0.45$0.175 (best)$0.25
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Google APIOfficial Upstage API
Limits
Context window256,000 tokens1,048,576 tokens (best)65,536 tokens
Max output4,096 tokens65,536 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoYesNo
AudioNoYesNo
VideoNoYesNo
ReasoningNoYesYesminimal · high
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsOpenProprietaryProprietary
API model IDcodestral-latestgemini-2.5-flash-litesolar-pro2
API providers423 (best)2
ReleasedMay 29, 2024Jun 17, 2025May 20, 2025
Knowledge cutoffOct 2024Jan 2025Mar 2025
03 — Cost

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
  • Gemini 2.5 Flash-Lite$1.80
  • Solar Pro 2$3.00
04 — Questions

Which should you choose?

Which is better: Codestral, Gemini 2.5 Flash-Lite or Solar Pro 2?

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Flash-Lite 84/100, Solar Pro 2 52/100, Codestral 51/100) compare the available specifications and price. 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, Gemini 2.5 Flash-Lite or Solar Pro 2?

Gemini 2.5 Flash-Lite is cheaper at $0.10 input / $0.40 output per million tokens (official Google API price). Solar Pro 2 costs $0.25 input / $0.25 output per million tokens (official Upstage API price); Codestral 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 $0.25 for Solar Pro 2 (1.4× as much) and $0.45 for Codestral (2.6× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Gemini 2.5 Flash-Lite has not been scored yet and Solar Pro 2 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Codestral, Gemini 2.5 Flash-Lite and Solar Pro 2 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 256,000 for Codestral and 65,536 for Solar Pro 2. Maximum output per response: Codestral up to 4,096, Gemini 2.5 Flash-Lite up to 65,536, Solar Pro 2 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Codestral accepts text; Gemini 2.5 Flash-Lite accepts text, images, PDFs, audio and video; Solar Pro 2 accepts text. Gemini 2.5 Flash-Lite handles the widest range of inputs.

Are any of these open source?

Codestral publishes its weights and can be self-hosted; Gemini 2.5 Flash-Lite and Solar Pro 2 is proprietary.

Which is newer?

Gemini 2.5 Flash-Lite is the newest, released Jun 17, 2025. Solar Pro 2 came out May 20, 2025; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, Gemini 2.5 Flash-Lite Jan 2025, Solar Pro 2 Mar 2025.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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 18, 2026.