ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

Codestral vs Relace Apply 3

Side-by-side comparison of API pricing, specs, benchmarks, and capabilities

Codestral is 50% cheaper on blended cost ($0.450 vs $0.900/Mtok)
Specification
Overview
StatusCurrent coding Current coding
Released May 29, 2024 Oct 29, 2025
Pricing per million tokens
Input $0.300/Mtok $0.800/Mtok
Output $0.900/Mtok $1.20/Mtok
Blended avg $0.450/Mtok $0.900/Mtok
Specifications
Context window 256K tokens 256K tokens
Parameters 22B Proprietary
Speed (TPS)
Modalities
Input
text
text
Benchmarks sources: Mistral model card / n/a
SWE-Bench Verified 38 vendor
HumanEval 85 vendor
Providers
Available from
Mistral — $0.300/$0.900/Mtok
Relace — $0.800/$1.20/Mtok

Cost at scale

1M tokens · 50/50 input/output
Projected cost of Codestral vs Relace Apply 3 at increasing token volumes
VolumeCodestralRelace Apply 3Savings
1M tokens $0.45 $0.9 $0.45 (50%)
10M tokens $4.5 $9 $4.5 (50%)
100M tokens $45 $90 $45 (50%)
1000M tokens $450 $900 $450 (50%)

When to pick which

distilled from the pricing and spec data above
Pick Codestral if…
  • cost dominates: $0.450/Mtok blended vs $0.900 — 50% less on the same 50/50 token mix
Pick Relace Apply 3 if…
  • this pairing gives Relace Apply 3 no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
Try Codestral on Mistral

The cheaper option here — Codestral costs $0.450/Mtok blended on Mistral.

Get API key →

Summary

Codestral by Mistral costs $0.300/Mtok input and $0.900/Mtok output, with a 256K-token context window. It supports text input.

Relace Apply 3 by Relace costs $0.800/Mtok input and $1.20/Mtok output, with a 256K-token context window. It supports text input.

On a blended cost basis, Codestral is 50% cheaper than Relace Apply 3.

Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.

More comparisons

pairs sharing a model with this page