ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

CodestralvsMiniMax M2.7

Codestral and MiniMax M2.7 do not yet share a public benchmark, so quality cannot be compared apples-to-apples. Codestral is 1.3x cheaper per token. Codestral has the larger context window (256K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0
no overlap yet
Cheaper per token
Codestral
1.3x cheaper, input + output
Larger context
Codestral
256K tokens
Provider uptime (30d)
100% · 100%
Mistral AI · MiniMax
Codestral
Mistral AI · released 2025-01-13
text
Context
256K
Max out
Input /1M
$0.3
Output /1M
$0.9
Cached /1M
$0.03
Scores
1 · 1 core
MiniMax M2.7
MiniMax · released 2026-03-18
text
Context
205K
Max out
Input /1M
$0.3
Output /1M
$1.2
Cached /1M
$0.06
Scores
1 · 1 core
Quality

Benchmark matrix

BenchmarkCodestralMiniMax M2.7ΔEdge
Reported by both · 0
No public benchmark is reported for both models yet.
Only Codestral reports · 1
HumanEval86.6% not reported
Only MiniMax M2.7 reports · 1
LMArena Elonot reported1404.6
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Codestral minus MiniMax M2.7 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecCodestralMiniMax M2.7Edge
Context window256K tokens205K tokensCodestral
Max output
Input price / 1M$0.3 $0.3 Tie
Output price / 1M$0.9 $1.2 Codestral
Cached input / 1M$0.03 $0.06 Codestral
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$1.2$1.5Codestral
ModalitiestexttextTie
Released2025-01-132026-03-18
Cited benchmark scores11
Reliability

Provider status

All providers
More matchups

Codestral vs …

More matchups

MiniMax M2.7 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Codestral and MiniMax M2.7 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.