Home › Compare › GPT-6 Luna vs Mistral Small
GPT-6 Luna vs Mistral Small
A straight cost comparison of GPT-6 Luna (OpenAI) and Mistral Small (Mistral AI), per 1,000,000 tokens, verified November 2026.
Rate-by-rate comparison
| Metric | GPT-6 Luna | Mistral Small | Winner |
|---|---|---|---|
| Input / 1M | $0.10 | $0.10 | Tie |
| Cached input / 1M | $0.01 | $0.01 | Tie |
| Cache write / 1M | $0.125 |  | Mistral Small |
| Output / 1M | $0.50 | $0.30 | Mistral Small |
| Context window | 1,050,000 | 32,000 | GPT-6 Luna |
| Batch API | Yes | Yes | Tie |
| Long-context tier | > 272,000 | None |  |
For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.
Blended cost: 1M input + 250K output
| Model | Blended cost | Difference |
|---|---|---|
| GPT-6 Luna | $0.225 | +$0.05 |
| Mistral Small | $0.175 | Cheaper |
Ten workloads, two bills
The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes  no retries, no system prompt, no middleware.
| Workload | GPT-6 Luna | Mistral Small | Winner |
|---|---|---|---|
| Classification 100K reqs · 500 in / 10 out | $5.50 | $5.30 | Mistral Small |
| Data extraction 10K reqs · 2K in / 200 out | $3 | $2.60 | Mistral Small |
| Support chat 1K reqs · 4K in / 600 out | $0.70 | $0.58 | Mistral Small |
| Code review 2K reqs · 8K in / 1.5K out | $3.10 | $2.50 | Mistral Small |
| Summarisation 1K reqs · 20K in / 1K out | $2.50 | $2.30 | Mistral Small |
| Agent loop 5K reqs · 12K in / 2K out | $11 | $9 | Mistral Small |
| Translation 500 reqs · 15K in / 15K out | $4.50 | $3 | Mistral Small |
| Long-document QA 200 reqs · 120K in / 800 out | $2.48 | $2.45 | Mistral Small |
| Cached RAG 1K reqs · 50K in (45K cached) / 1K out | $1.46 | $1.25 | Mistral Small |
| Nightly batch 10K reqs · 10K in / 2K out | $10 | $8 | Mistral Small |
GPT-6 Luna wins 0 of 10, Mistral Small wins 10 of 10. The winner is set by the token mix, not by the headline rate.
Where the two bills cross over
The two are priced identically on one side of the token mix ($0.10 input, $0.50 output), so the crossover is decided entirely by the other side  the cheaper model on that side wins at every ratio.
Cost at four scales
The same support-chat workload (4K input, 600 output per request) at four monthly volumes.
| Requests / month | GPT-6 Luna | Mistral Small | Difference |
|---|---|---|---|
| 100 | $0.07 | $0.058 | Mistral Small cheaper by $0.012 |
| 1,000 | $0.70 | $0.58 | Mistral Small cheaper by $0.12 |
| 10,000 | $7 | $5.80 | Mistral Small cheaper by $1.20 |
| 100,000 | $70 | $58 | Mistral Small cheaper by $12 |
What caching does to each bill
Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.
| Cached share of the prompt | GPT-6 Luna | Mistral Small | Winner |
|---|---|---|---|
| 0% | $0.70 | $0.58 | Mistral Small |
| 50% | $0.52 | $0.40 | Mistral Small |
| 80% | $0.412 | $0.292 | Mistral Small |
| 95% | $0.358 | $0.238 | Mistral Small |
Both models publish a cached-read rate, so the discount is comparable: GPT-6 Luna reads cache at $0.01 per million, Mistral Small at $0.01.
Which one should you pick?
GPT-6 Luna wins on none of the ten workloads above, while Mistral Small wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, long-document qa, cached rag, nightly batch.
Beyond price, the two differ on output rate ($0.50 vs $0.30); cache-write rate ($0.125 vs â€â€); context window (1,050,000 vs 32,000); long-context tier (yes, above 272,000 vs none).
Batch mode is available on GPT-6 Luna and Mistral Small, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.
FAQ
Is GPT-6 Luna cheaper than Mistral Small?
On a blended 1M-input-plus-250K-output workload, Mistral Small is cheaper by 22% ($0.175 vs $0.225). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.
Which handles longer prompts, GPT-6 Luna or Mistral Small?
Mistral Small has the larger context window (1,050,000 vs 32,000 tokens). Watch the long-context threshold on GPT-6 Luna: rates rise once input passes it.
Do both models support prompt caching?
GPT-6 Luna bills cached reads at $0.01 per 1M; Mistral Small at $0.01.
Related comparisons
- GPT-6 Luna vs GPT-5.6 Luna
- Mistral Small vs Mistral Nemo
- GPT-6 Luna vs Claude Haiku 4.5
- All OpenAI pricing
- All Mistral AI pricing