As of August 25, 2026, Phi 4 Mini is 57% cheaper per million tokens than Mercury 2. Mercury 2 is $0.25 / $0.75 per million input/output tokens versus Phi 4 Mini at $0.08 / $0.35. Sources: https://anotherwrapper.com/tools/llm-pricing and https://openrouter.ai/api/v1/models
Sources: AnotherWrapper LLM pricing (https://anotherwrapper.com/tools/llm-pricing); OpenRouter pricing (https://openrouter.ai/api/v1/models)
Mercury 2
Inception
Input
$0.25
Output
$0.75
Phi 4 Mini
Microsoft
Input
$0.08
Output
$0.35
Token pricing, specs, and benchmarks side by side
Each bar is share of the current leader on that eval. Click a row to open the board.
GPQA. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price.
Mercury 2Phi 4 MiniVerdict
Phi 4 Mini offers significantly lower pricing, while Mercury 2 leads on benchmark performance. Your choice depends on whether cost efficiency or raw capability matters more for your use case.
As of August 25, 2026, Phi 4 Mini is 57% cheaper on blended LLM API pricing. Phi 4 Mini costs $0.08 per million input tokens and $0.35 per million output tokens ($0.43 blended 1M-in + 1M-out). Mercury 2 costs $0.25 / $0.75 per million tokens ($1.00 blended). Sources: https://anotherwrapper.com/tools/llm-pricing and https://openrouter.ai/api/v1/models. The cheapest LLM for your app still depends on how many output tokens you generate.
Mercury 2 Inception API pricing is $0.25 input and $0.75 output per million tokens via Inception. Phi 4 Mini OpenRouter API pricing is $0.08 input and $0.35 output per million tokens via OpenRouter. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
Mercury 2 has a published LiveCodeBench score of 67%. Phi 4 Mini does not have that eval on this page yet.
Mercury 2 supports a 128K token context window, while Phi 4 Mini supports 131K tokens. Phi 4 Mini offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
Mercury 2 leads on 1 of 1 shared benchmarks versus Phi 4 Mini's 0 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Both Mercury 2 and Phi 4 Mini are production API models. For cost-sensitive production traffic, Phi 4 Mini has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Yes. Call Mercury 2 through Inception and Phi 4 Mini through OpenRouter with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
List rates are the latest published Inception API pricing and OpenRouter API pricing, quoted per million tokens. Official rate sheets: https://anotherwrapper.com/tools/llm-pricing and https://openrouter.ai/api/v1/models. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
Mercury 2 supports up to 8K output tokens per request, while Phi 4 Mini supports up to an unspecified number of output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
Mercury 2 has a measured throughput of approximately 1009 tokens/second. Throughput data for Phi 4 Mini is not yet available. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open Mercury 2 or Phi 4 Mini from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. Mercury 2 costs $0.25/M input and $0.75/M output. Phi 4 Mini costs $0.08/M input and $0.35/M output via OpenRouter.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
280 models across 33 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
