Head-to-head showdown: Codestral 2501 ($0.30 in / $0.90 out per 1M) vs Codestral 2508 (OpenRouter) ($0.30 in / $0.90 out per 1M). Codestral 2501 is 1.0× cheaper across standard token mixes, with 256K vs 256K context windows.
codestral-2501 · mistral
codestral-2508 · mistral
Benchmark
| Workload Scenario | Codestral 2501 | Codestral 2508 (OpenRouter) | Price Delta |
|---|---|---|---|
| 1M input tokens (raw text) | $0.30 | $0.30 | — |
| 1M output tokens (generation) | $0.90 | $0.90 | — |
| 1M tokens · 70% input / 30% output mix | $0.48 | $0.48 | — |
| Standard chat turn (4K in / 800 out, 50% cached) | $0.00138 | $0.00138 | — |
| Monthly scale (10K requests / day) | $414.00 | $414.00 | — |
Negative difference = Codestral 2501 is cheaper. Positive = Codestral 2508 (OpenRouter) is cheaper.
Scaling Curve
Total cost of a token volume at 70/30 input/output split (uncached). Log-log scale.
Verdict
Codestral 2508 (OpenRouter) is cheaper on both input and output rates, so it costs less at every input/output mix. Price alone still isn't the whole decision: capability, latency and context limits (Codestral 2501: 256K, Codestral 2508 (OpenRouter): 256K) may justify the premium for your task.
FAQ
On input, Codestral 2508 (OpenRouter) is cheaper ($0.30/M vs $0.30/M). On output, Codestral 2501 is cheaper ($0.90/M vs $0.90/M). The same model is cheaper on both sides, so it wins at every mix.
A chat-style request (4,000 input + 800 output tokens, 50% cached) costs $0.00138 on Codestral 2501 and $0.00138 on Codestral 2508 (OpenRouter) — Codestral 2501 is equal for that workload.
Codestral 2501 supports 256,000 tokens (8.2K max output); Codestral 2508 (OpenRouter) supports 256,000 (204.8K max output). They are equal.