LLMs with the longest maximum output
Pricing updated daily · Last refreshed Oct 29, 2026Models that can generate the most tokens in a single response, with their prices.
How this list is made
All models in the catalogue, ordered by maximum output tokens per response, largest first. It ranks by listed price and specifications only. It says nothing about output quality, which this site does not measure, so test candidates on your own task before choosing.
| Model | Provider | Max output | Context | Input $/1M | Output $/1M |
|---|---|---|---|---|---|
| Gemini 4 Argon | 944K tokens | 1.05M | $2.00 | $10.00 | |
| Mistral Large 4 | Mistral | 262K tokens | 1.05M | $0.70 | $2.10 |
| Ministral 3 14B 2512 | Mistral | 210K tokens | 262K | $0.20 | $0.20 |
| Mistral Small 4 | Mistral | 210K tokens | 262K | $0.15 | $0.60 |
| Devstral 2 2512 | Mistral | 210K tokens | 262K | $0.40 | $2.00 |
| Mistral Medium 3.5 | Mistral | 210K tokens | 262K | $1.50 | $7.50 |
| Claude Haiku 5.5 | Anthropic | 128K tokens | 1M | $0.10 | $0.50 |
| GPT-6 Luna Pro | OpenAI | 128K tokens | 1.05M | $0.10 | $0.50 |
| GPT-6.1 Terra | OpenAI | 128K tokens | 1.05M | $1.00 | $5.00 |
| GPT-6.1 Terra Pro | OpenAI | 128K tokens | 1.05M | $1.00 | $5.00 |
Showing the top 10 of 30 models in the catalogue. Prices are those OpenRouter charges and can differ from a provider’s own list price. Want to sort or filter differently? Use the model comparison tool.