OPENAI VS MISTRAL
GPT-5.6 Luna vs Magistral Medium
GPT-5.6 Luna is about 6.1x cheaper than Magistral Medium on a blended 3:1 input:output rate — the same 10K-in/2K-out request costs $0.0044 vs $0.03. GPT-5.6 Luna has the larger context window (1,047,576 vs 128,000 tokens).
Pricing verified
API pricing per 1M tokens
| Model | Input / 1M tokens | Output / 1M tokens | Blended (3:1 mix) |
|---|---|---|---|
| GPT-5.6 Luna | $0.20 | $1.20 | $0.45 |
| Magistral Medium | $2.00 | $5.00 | $2.75 |
Rates from official OpenAI pricing and official Mistral pricing, checked 2026-08-11.
What a real workload costs
Example: one request with 10,000 input tokens and 2,000 output tokens, then that request at 100,000 runs per month.
| Model | Per request (10K in / 2K out) | Per month (100K requests) | Monthly delta |
|---|---|---|---|
| GPT-5.6 Luna | $0.0044 | $440 | — |
| Magistral Medium | $0.03 | $3,000 | +$2,560 |
Model your own prompt sizes and volumes in the token cost analyzer, or check caching savings with the prompt caching calculator.
Specs side by side
| Spec | GPT-5.6 Luna | Magistral Medium |
|---|---|---|
| Provider | OpenAI | Mistral |
| Context window | 1,047,576 tokens | 128,000 tokens |
| Model class | General text | Reasoning |
| Tokenizer | o200k_base (exact, public) | Proprietary (counts estimated) |
Count tokens for each model on its own page: GPT-5.6 Luna token counter and Magistral Medium token counter. All OpenAI models are on the OpenAI Token Counter. All Mistral models are on the Mistral Token Counter.
FAQ
GPT-5.6 Luna vs Magistral Medium FAQ
Which is cheaper, GPT-5.6 Luna or Magistral Medium?
GPT-5.6 Luna is cheaper. At rates checked 2026-08-11, GPT-5.6 Luna costs $0.20 input / $1.20 output per 1M tokens, while Magistral Medium costs $2.00 input / $5.00 output — about a 6.1x difference on a typical 3:1 input-heavy workload.
How much does a real request cost on GPT-5.6 Luna vs Magistral Medium?
A request with 10,000 input tokens and 2,000 output tokens costs about $0.0044 on GPT-5.6 Luna and $0.03 on Magistral Medium. At 100,000 such requests per month that is $440 vs $3,000 — a difference of $2,560 per month.
Which has the bigger context window, GPT-5.6 Luna or Magistral Medium?
GPT-5.6 Luna. It supports 1,047,576 tokens of context versus 128,000 tokens — roughly 786,000 English words in one request.
Do GPT-5.6 Luna and Magistral Medium count tokens the same way?
Not exactly. GPT-5.6 Luna uses the published o200k_base tokenizer and Magistral Medium uses a proprietary tokenizer (counts are estimates). The same prompt will tokenize differently, which shifts effective cost per word.