flagship
Gpt 5 vs Mistral Large 3
Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.
Specifications
| Feature | Gpt 5 | Mistral Large 3 |
|---|---|---|
| Provider | openai | mistral |
| Model ID | gpt-5 | mistral/mistral-large-3 |
| Input / 1M tokens | $1.25 | $0.50 (60% cheaper) |
| Output / 1M tokens | $10.00 | $1.50 (85% cheaper) |
| Cached input / 1M | $0.13 | — |
| Context window | 272kk tokens | 262kk tokens |
| Max output | 128kk tokens | 262kk tokens |
| Vision | ✅ | ✅ |
| Function calling | ✅ | ✅ |
| Prompt caching | ✅ | ⬜ |
| Web search | ✅ | ⬜ |
| JSON schema | ✅ | ✅ |
Monthly cost comparison
No cache discount applied — pure token costs at three usage scales.
| Scale | Gpt 5 | Mistral Large 3 | Winner |
|---|---|---|---|
| Small 1M in / 0.2M out | $3.25 | $0.80 | Mistral Large 3 saves 75% |
| Medium 10M in / 2M out | $32.50 | $8.00 | Mistral Large 3 saves 75% |
| Large 100M in / 20M out | $325 | $80.00 | Mistral Large 3 saves 75% |
Category winners
Cheapest input
Mistral Large 3
$0.50/M
· 60% less than the other
Cheapest output
Mistral Large 3
$1.50/M
· 85% less than the other
Larger context
Gpt 5
272kk tokens · 4% larger window
More features
Gpt 5
5 / 5 capabilities
Better for…
High-volume RAG & repeated context
$0.13/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Gpt 5
Short interactions & high-throughput APIs
$1.50/M output — 85% cheaper on output at scale
Mistral Large 3
Agentic workflows & tool use
Supports 5 of 5 tracked capabilities (vision, function calling, caching, web search, JSON schema)
Gpt 5
Cost-sensitive production at scale
$80.00/month at 100M-token scale — 75% cheaper than the alternative
Mistral Large 3
Deep-dive on each model
Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.