Enter opens the highlighted result. Esc closes.

Codestral 2508 vs Nano Banana 2.1

Codestral 2508 costs 8.3x less per output token than Nano Banana 2.1 ($0.90 vs $7.50 per million). Updated October 22, 2026; no benchmark has tested both models yet.

Replace Codestral 2508 Replace Nano Banana 2.1
Codestral 2508Mistral AI
Coding
No data
Overall
No data
Output $/M
$0.90
Nano Banana 2.1Google
Coding
No data
Overall
No data
Output $/M
$7.50
vs $0.90 vs $7.50 per 1M output tokens. Codestral 2508 is 8.3x cheaper.

Codestral 2508 or Nano Banana 2.1: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick Codestral 2508 for output tokens 8.3x cheaper ($0.90 vs $7.50 per million) and a larger context window (256K against 66K tokens).

Model ACodestral 2508Mistral AINot benchmarkedNo coding benchmarkNo cost per solved taskModel BNano Banana 2.1GoogleNot benchmarkedNo coding benchmarkNo cost per solved task

No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Kagi LLM Benchmark and Design Arena: websites; Nano Banana 2.1 on Design Arena: images, Design Arena: graphic design and Design Arena: logos. Compare them on price and context instead.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Codestral 2508 not benchmarked, Nano Banana 2.1 not benchmarked.
Widest category
None yet: no category has been tested on both models.
Widest single gap
None yet: no benchmark has tested both models.
Output price
Codestral 2508 $0.90 against Nano Banana 2.1 $7.50 per million output tokens, 8.3x apart.
Context window
Codestral 2508 takes 256K tokens, Nano Banana 2.1 66K.

Benchmark by benchmark

Every board either model has a result on, a category to a fold; bars are each result on a 0 to 100 scale. Only one model is measured on each, so no row names a leader.

CodingDirectional onlySix of these boards feed the Vibe Coding Index1 board measured
Coding benchmarks for Codestral 2508 and Nano Banana 2.1
BenchmarkCodestral 2508Nano Banana 2.1Leader
ALE-Bench137.8Not measuredOnly Codestral 2508 measured
Neither model has a result on the other 38 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board measured
Reasoning benchmarks for Codestral 2508 and Nano Banana 2.1
BenchmarkCodestral 2508Nano Banana 2.1Leader
Kagi LLM Benchmark32.5%Not measuredOnly Codestral 2508 measured
Neither model has a result on the other 21 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards measured
Web design benchmarks for Codestral 2508 and Nano Banana 2.1
BenchmarkCodestral 2508Nano Banana 2.1Leader
Design Arena: websites1012Not measuredOnly Codestral 2508 measured
Design Arena: UI components1014Not measuredOnly Codestral 2508 measured
Design Arena: game dev967Not measuredOnly Codestral 2508 measured
Design Arena: data viz1017Not measuredOnly Codestral 2508 measured
Design Arena: 3D1019Not measuredOnly Codestral 2508 measured
Design Arena: all code categories1007Not measuredOnly Codestral 2508 measured
Neither model has a result on the other 3 boards here
Image generationDirectional onlyPublic boards, shown as published, kept out of the index5 boards measured
Image generation benchmarks for Codestral 2508 and Nano Banana 2.1
BenchmarkCodestral 2508Nano Banana 2.1Leader
Design Arena: imagesNot measured1293Only Nano Banana 2.1 measured
Design Arena: graphic designNot measured1333Only Nano Banana 2.1 measured
Design Arena: logosNot measured1277Only Nano Banana 2.1 measured
LMArena Text to ImageNot measured1328Only Nano Banana 2.1 measured
LMArena Image EditNot measured1426Only Nano Banana 2.1 measured

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Codestral 2508$0.0008Fits in one request
Nano Banana 2.1$0.0053Fits in one request

Codestral 2508 costs less

Repository review

50K input + 3K output tokens

Codestral 2508$0.018Fits in one request
Nano Banana 2.1$0.098Fits in one request

Codestral 2508 costs less

Agent loop

200K input + 10K output tokens

Codestral 2508$0.069Fits in one request
Nano Banana 2.1$0.375Exceeds the context window

Codestral 2508 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Codestral 2508 and Nano Banana 2.1
SpecificationMistral Codestral 2508Google Nano Banana 2.1
MakerMistral AIGoogle
WeightsNo public weights listedNo public weights listed
ReleasedAugust 1, 2025October 6, 2026
Context window256K66K
Input $/Mtok$0.30$1.50
Output $/Mtok$0.90$7.50
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Codestral 2508 better than Nano Banana 2.1 for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Codestral 2508 for output tokens 8.3x cheaper ($0.90 vs $7.50 per million) and a larger context window (256K against 66K tokens).

Which is cheaper, Codestral 2508 or Nano Banana 2.1?

Codestral 2508 costs $0.30 per million input tokens and $0.90 per million output tokens; Nano Banana 2.1 costs $1.50 and $7.50. Cost per solved task is known for neither of them.

Which has the bigger context window, Codestral 2508 or Nano Banana 2.1?

Codestral 2508, with 256K tokens against 66K.

Has any benchmark tested both Codestral 2508 and Nano Banana 2.1?

No benchmark has tested both yet. Codestral 2508 has results on ALE-Bench, Kagi LLM Benchmark and Design Arena: websites; Nano Banana 2.1 on Design Arena: images, Design Arena: graphic design and Design Arena: logos. Compare them on price and context instead. Data as of October 22, 2026.

Compare next