Mistral Medium 3.5 vs GPT-5.4
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
| Specification |
by Mistral
|
by OpenAI
|
|---|---|---|
| Overview | ||
| Status | Current mid tier | Current flagship |
| Released | Sep 1, 2025 | Aug 15, 2025 |
| Pricing per million tokens | ||
| Input | $1.50/Mtok | $2.50/Mtok |
| Output | $7.50/Mtok | $15.00/Mtok |
| Blended avg | $3.00/Mtok | $5.63/Mtok |
| Cached input | — | $0.250/Mtok |
| Specifications | ||
| Context window | 128K tokens | 1M tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
textimage
|
| Benchmarks sources: Artificial Analysis / OpenAI model card, Artificial Analysis | ||
| Independent composite scores measured for both models — each on its own scale | ||
| AA Intelligence Index | 30.4 | 53.1 |
| AA Agentic Index | 19.2 | 44.2 |
| AA-Omniscience Index (−100–100) | -36.8 | 5.8 |
| LMSYS Chatbot Arena | 1427.2 ELO | 1465.5 ELO |
| GDPval-AA v2 | 932.9 ELO | — |
| Per-benchmark results published for GPT-5.4 only — no independent per-benchmark scores exist for Mistral Medium 3.5 yet | ||
| Avg benchmark score | — | 78.7 |
| Perf / dollar | — | 14 |
| GPQA Diamond | — | 88 |
| SWE-Bench Verified | — | 75 |
| Humanity's Last Exam | — | 40.2 |
| ARC-AGI 2 | — | 50 |
| AIME 2025 | — | 95.5 |
| MMMLU | — | 88 |
| BFCL | — | 85 |
| HumanEval | — | 94.5 |
| MATH 500 | — | 92 |
| Providers | ||
| Available from |
Mistral — $1.50/$7.50/Mtok
|
OpenAI — $2.50/$15.00/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Mistral Medium 3.5 | GPT-5.4 | Savings |
|---|---|---|---|
| 1M tokens | $3 | $5.63 | $2.63 (46.8%) |
| 10M tokens | $30 | $56.25 | $26.25 (46.7%) |
| 100M tokens | $300 | $562.5 | $262.5 (46.7%) |
| 1000M tokens | $3000 | $5625 | $2625 (46.7%) |
When to pick which
distilled from the pricing and spec data above- cost dominates: $3.00/Mtok blended vs $5.63 — 46.7% less on the same 50/50 token mix
- your workload re-reads context (agents, RAG, long chats): cached input costs $0.250/Mtok — 90% off its list input price, a discount Mistral Medium 3.5 doesn't offer
- you need the longer context: 1M tokens vs 128K (7.8×)
The cheaper option here — Mistral Medium 3.5 costs $3.00/Mtok blended on Mistral.
Summary
Mistral Medium 3.5 by Mistral costs $1.50/Mtok input and $7.50/Mtok output, with a 128K-token context window. It supports text input.
GPT-5.4 by OpenAI costs $2.50/Mtok input and $15.00/Mtok output, with a 1M-token context window. It supports text, image input.
On a blended cost basis, Mistral Medium 3.5 is 46.7% cheaper than GPT-5.4.
The two aren't directly comparable on average benchmark score: GPT-5.4 has published per-benchmark results, while Mistral Medium 3.5 does not yet — it is measured today on independent composites (see the table above).
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.