Tokenando
BETA
Subscribe
← Back to prices·All Fireworks AI models
Fireworks AI
Fireworks AIEfficientAUTO PROFILELIVE PRICING

Mercury 2.5 Preview

text->text

Mercury 2.5 Preview is a general-purpose chat-tuned model. Available via Fireworks AI. 260,000-token context. Budget pricing. Currently in preview — capabilities and pricing may shift.

Mercury 2.5 Preview is a efficient AI model from Fireworks AI. It costs $0.040 per million input tokens and $0.150 per million output tokens (blended $0.073/M), with a 260,000-token context window.

Modalities textProvider pricing ↗API docs ↗Pricing source ↗Compare with another model →Estimate monthly cost →
INPUT
$0.040/M
per million input tokens
OUTPUT
$0.150/M
per million output tokens
BLENDED 70/30
$0.073/M
unchanged
default reference rate · how it is calculated →
CONTEXT
260,000
tokens
What it is good at
  • Solid general chat performance
  • Reasonable instruction following
Typical use cases
  • General chat
  • Drafting and rewriting
  • Personal productivity

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Fireworks AI

See all 7 →
Llama 3.1 405B (fw)
Serverless · 131,000 ctx
in $3.000/Mout $3.000/M
Mixtral 8x7B (fw)
Serverless · 32,000 ctx
in $0.200/Mout $0.200/M
DeepSeek-R1 (fw)
Reasoning · 64,000 ctx
in $3.000/Mout $8.000/M
Qwen2.5-72B (fw)
Balanced · 32,000 ctx
in $0.900/Mout $0.900/M
Llama 3.1 8B (fw)
Nano · 131,000 ctx
in $0.100/Mout $0.100/M
Yi-34B (fw)
Open · 4,000 ctx
in $0.900/Mout $0.900/M

Frequently asked questions

How much does Mercury 2.5 Preview cost?

Mercury 2.5 Preview costs $0.040 per million input tokens and $0.150 per million output tokens, for a blended reference rate of $0.073 per million tokens.

What is Mercury 2.5 Preview's context window?

Mercury 2.5 Preview supports up to 260,000 tokens of context in a single request.

What is Mercury 2.5 Preview best for?

Mercury 2.5 Preview is well suited to Solid general chat performance, Reasonable instruction following and General chat.

Who makes Mercury 2.5 Preview?

Mercury 2.5 Preview is developed and served by Fireworks AI.

Terms used on this page

Full glossary →
TokenInput tokensOutput tokensPrice per million tokensContext windowPrompt cachingBatch APIBlended cost