NanoGPT
Mercury 2.5 Preview
inception/mercury-2.5-preview
Prices and limits
- Input price per 1M tokens
- $0.04
- Output price per 1M tokens
- $0.15
- Cached input per 1M tokens
- $0.004
- Blended price per 1M (our estimate)
- $0.068
- Context window
- 260,000
- Max output tokens
- 65,536
- Accepts
- Text
- Produces
- Text
- Released
- Sep 1, 2026
- Last updated
- Sep 1, 2026
- Knowledge cutoff
- —
- Open weights
- No
Wrong price, or a provider that wants its listing corrected or removed? Email ceo@uniholix.com. We reply within 5 business days.
Cheapest comparable models
Other priced models that accept at least the same inputs, produce the same outputs and have at least half this context window, sorted by blended price.
- Llama-3.1-8B-InstructKilo Gateway$0.02 / $0.04131.1K
- Mistral Nemo Instruct 2407Meganova$0.02 / $0.04131.1K
- Ling 3.0 FlashVercel AI Gateway$0.021 / $0.063256K
- Llama 3.2 3b InstructNanoGPT$0.031 / $0.049131.1K
- GPT OSS 20BKilo Gateway$0.018 / $0.09131.1K
- qwen3.5-2bRequesty$0.02 / $0.10262.1K
- Granite 4.0 H MicroCloudflare Workers AI$0.017 / $0.112131K
- IBM: Granite 4.0 MicroKilo Gateway$0.017 / $0.112131K
Same model at other providers
Matched by the catalogue’s model ID. Cheapest blended price first.
None in the current catalogue.
Price changes
Models whose price changed in the catalogue, newest first. We compare prices every day.
No price changes recorded yet. When a model’s price changes, it appears here.