Mercury 2.5
Mercury 2.5Alternatives?
CheaperGLM 5.3 FlashunstatedOpen×10.4-30%$0.15 / $0.50Defaults to max · Self-hosted+4
BetterClaude Haiku 4.5thinking×2.4+493%$0.23Context: 260K → 200KOpenGLM 5.3unstated×11.3+537%$1.40 / $4.40Reasoning cannot be disabled+3CheaperClaude Haiku 5.5unstated×10-41%$0.10 / $0.50Remove sampling parameters+5
CheaperMiMo v2.6 FlashunstatedOpen×8.8-48%$0.14 / $0.28Pass back reasoning_content+3GLM 5.3 FlashunstatedOpen×10.4-30%$0.15 / $0.50Defaults to max · Self-hosted+4Claude Haiku 5.5unstated×10-41%$0.10 / $0.50Remove sampling parameters+5MiMo v2.6 FlashunstatedOpen×8.8-48%$0.14 / $0.28Pass back reasoning_content+3
MiniMax M3.1 Flashunstated×7.9-22%$0.15 / $0.60No strict JSON+1
GPT-6 Lunaunstated×7-41%$0.10 / $0.50Function calling only with none · Chat Completions+3Claude Haiku 4.5thinking×2.4+493%$0.23Context: 260K → 200K
Muse Spark 1.3max×12.8+493%$3.69Only auto tool_choice is supported+5Claude Fable 5.1unstated×12.8+5,826%$10 / $50Replace forced tool_choice+5Claude Opus 5unstated×12.8+2,863%$5 / $25
Gemini 4 Argonunstated×12.7+1,085%*$2 / $10Synchronous output stops at 65,536+2GLM 5.3unstatedOpen×11.3+537%$1.40 / $4.40Reasoning cannot be disabled+3MiMo v2.6 ProunstatedOpen×10.9+61%$0.43 / $0.87Pass back reasoning_content+3
Kimi K3unstatedOpen×10.7+1,678%$3 / $15Sampling parameters are fixed+3
DeepSeek V4.1 Flash 1017unstatedOpen×10.4+56%$0.30 / $1.20Pass back reasoning_content · Chat Completions+4
Hy4 previewOpen×10.4+271%$0.83 / $2.50Mercury 3×6.7—$0.10 / $0.35Mercury 2highn/a—$0.089Context: 260K → 128KAll inception models →Benchmarks
in Chat & KnowledgeFAQ
How much does Mercury 2.5 cost?›
$0.20 per 1M input tokens and $0.75 per 1M output tokens; cached input $0.02 per 1M. A typical benchmark task costs about $0.1 at default effort.
Is Mercury 2.5 free to use?›
There is no free API; the cheapest paid price is $0.20 per 1M input tokens.
How good is Mercury 2.5, and what is it best at?›
#167 of 336 in Chat & Knowledge, #77 of 134 in Coding, #97 of 135 in Agents & Tool Use, #99 of 135 in Vision & Documents.
Is Mercury 2.5 better than GPT-5.4 Nano?›
On Vals Legal Research Bench, Mercury 2.5 scores 4.3 vs 6.3 — lower.
How can I use Mercury 2.5?›
Through the inception API.
What is the context window of Mercury 2.5?›
260K tokens, with up to 66K output tokens.
When was Mercury 2.5 released? Is there a newer version?›
Released 2026-09-08. It is the current version in its line.
Is Mercury 2.5 open source?›
No, Mercury 2.5 is a closed model available through an API. The closest open-weights option here is GLM 5.3.
Can Mercury 2.5 read images?›
No, it accepts text only.
What is Mercury 2.5?›
Mercury 2.5 is a closed language model from inception, released Sep 2026, the successor to Mercury 2.
What are the best alternatives to Mercury 2.5?›
GLM 5.3 Flash (cheaper), Claude Haiku 4.5 (better), GLM 5.3 (open weights).