GPT-6 Luna Pro vs Mistral Large 4
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on October 23, 2026· 222 models
GPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.
- Reasoning estimated
- Speed estimated
- ▲
- Input
- Output
- Context
- ▲1.1 M tokens
- Max output
- 128 K
- Input, $ per 1M tokens
- ▲$0.100
- Output, $ per 1M tokens
- ▲$0.500
- Cache read, $ per 1M
- $0.010
- Batch (input / output)
- $0.050 / $0.250
- Tool calling
- Yes
- Released
- 09/22/2026
- Knowledge cutoff
- —
- API id
- openai/gpt-6-luna-pro
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.
- Reasoning estimated
- Speed estimated
- Input
- Output
- Context
- 1 M tokens
- Max output
- ▲262 K
- Input, $ per 1M tokens
- $1.36
- Output, $ per 1M tokens
- $4.18
- Cache read, $ per 1M
- $0.140
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- ▲10/06/2026
- Knowledge cutoff
- —
- API id
- mistralai/mistral-large-4-0
Which is the better API choice: GPT-6 Luna Pro vs Mistral Large 4?
- GPT-6 Luna Pro: cheapest input (93% less than Mistral Large 4)
- GPT-6 Luna Pro: cheapest output
- GPT-6 Luna Pro: largest context (1.1 M)
- Mistral Large 4: the newest (10/06/2026)
- GPT-6 Luna Pro: the fastest (estimated)
GPT-6 Luna Pro costs 93% less on input and 88% less on output than Mistral Large 4 ($0.100 / $0.500 versus $1.36 / $4.18 per million tokens). GPT-6 Luna Pro accepts more context (1.1 M). GPT-6 Luna Pro offers a batch tier at half price for jobs that do not need an immediate answer.
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
With GPT-6 Luna Pro you save $33.62 a month versus Mistral Large 4 (91% less).
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Pro Preview Google$0.00
- 2Lyria 3 Clip Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4Ministral 3 3B 2512 Mistral$1.90
- 5Qwen3.5-Flash Qwen$2.02
- 6DeepSeek V4 Flash 0423 DeepSeek$2.09
Paste your prompt: tokens and cost per model
Rough estimate (about 4 characters per token). Nothing is sent to any server.
Cost of sending it 1,000 times (input only)
- 1GPT-6 Luna Pro OpenAI$0.008
- 2Claude Haiku 5.5 Anthropic$0.008
- 3Mistral Large 4 Mistral$0.103
- 4Claude Sonnet 5.5 Anthropic$0.152
- 5Claude Sonnet 5 Anthropic$0.152
- 6Claude Opus 5.5 Anthropic$0.304
- 7Claude Opus 5 Anthropic$0.380
- 8Claude Fable 5.1 Anthropic$0.760
Popular comparisons
- Claude Haiku 5.5 vs GPT-6.1 Sol Pro
- Claude Haiku 5.5 vs Gemini 4 Argon
- Claude Haiku 5.5 vs DeepSeek V4.1 Flash 1017
- Claude Haiku 5.5 vs Grok 4.7
- GPT-6.1 Sol Pro vs Gemini 4 Argon
- GPT-6.1 Sol Pro vs DeepSeek V4.1 Flash 1017
- GPT-6.1 Sol Pro vs Grok 4.7
- Gemini 4 Argon vs DeepSeek V4.1 Flash 1017
- Gemini 4 Argon vs Grok 4.7
- DeepSeek V4.1 Flash 1017 vs Grok 4.7
Frequently asked questions
Which is the better API choice: GPT-6 Luna Pro vs Mistral Large 4?
GPT-6 Luna Pro costs 93% less on input and 88% less on output than Mistral Large 4 ($0.100 / $0.500 versus $1.36 / $4.18 per million tokens). GPT-6 Luna Pro accepts more context (1.1 M). GPT-6 Luna Pro offers a batch tier at half price for jobs that do not need an immediate answer.
Which is cheaper: GPT-6 Luna Pro and Mistral Large 4?
GPT-6 Luna Pro is cheaper: $0.100 per million input tokens and $0.500 per million output tokens, versus $1.36 / $4.18 for Mistral Large 4.
Which has more context: GPT-6 Luna Pro and Mistral Large 4?
GPT-6 Luna Pro accepts 1.1 M tokens of context; Mistral Large 4 accepts 1 M.
Which is newer: GPT-6 Luna Pro and Mistral Large 4?
Mistral Large 4 was released on 10/06/2026; GPT-6 Luna Pro on 09/22/2026.
What would 10,000 requests a month cost with GPT-6 Luna Pro and Mistral Large 4?
With 1,500 input and 400 output tokens per request: GPT-6 Luna Pro: $3.50; Mistral Large 4: $37.12 a month, at list price.
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.