Mercury 2.5
text->text
Mercury 2.5 is a general-purpose chat-tuned model. Available via Fireworks AI. 260,000-token context. Budget pricing.
Mercury 2.5 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.
INPUT
$0.040/M
per million input tokens
OUTPUT
$0.150/M
per million output tokens
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 cost?
Mercury 2.5 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's context window?
Mercury 2.5 supports up to 260,000 tokens of context in a single request.
What is Mercury 2.5 best for?
Mercury 2.5 is well suited to Solid general chat performance, Reasonable instruction following and General chat.
Who makes Mercury 2.5?
Mercury 2.5 is developed and served by Fireworks AI.