As of August 25, 2026, GPT OSS 20B is 75% cheaper per million tokens than Mercury 2. GPT OSS 20B is $0.05 / $0.20 per million input/output tokens versus Mercury 2 at $0.25 / $0.75. Sources: https://developers.openai.com/api/docs/pricing and https://anotherwrapper.com/tools/llm-pricing
Sources: OpenAI API pricing (https://developers.openai.com/api/docs/pricing); AnotherWrapper LLM pricing (https://anotherwrapper.com/tools/llm-pricing)
GPT OSS 20B
OpenAI
Input
$0.05
Output
$0.20
Mercury 2
Inception
Input
$0.25
Output
$0.75
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.
AIME 2025. Left is cheaper. Up is a higher score. The line is the best score you can buy at each price.
GPT OSS 20BMercury 2Verdict
GPT OSS 20B 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, GPT OSS 20B is 75% cheaper on blended LLM API pricing. GPT OSS 20B costs $0.05 per million input tokens and $0.20 per million output tokens ($0.25 blended 1M-in + 1M-out). Mercury 2 costs $0.25 / $0.75 per million tokens ($1.00 blended). Sources: https://developers.openai.com/api/docs/pricing and https://anotherwrapper.com/tools/llm-pricing. The cheapest LLM for your app still depends on how many output tokens you generate.
GPT OSS 20B OpenAI API pricing is $0.05 input and $0.20 output per million tokens via OpenAI. Mercury 2 Inception API pricing is $0.25 input and $0.75 output per million tokens via Inception. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
GPT OSS 20B leads on LiveCodeBench: GPT OSS 20B at 80.4% vs Mercury 2 at 67%. SWE-bench measures real GitHub fixes; LiveCodeBench measures contest programming.
GPT OSS 20B supports a 131K token context window, while Mercury 2 supports 128K tokens. GPT OSS 20B 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 2 of 3 shared benchmarks versus GPT OSS 20B's 1 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 GPT OSS 20B and Mercury 2 are production API models. For cost-sensitive production traffic, GPT OSS 20B 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 GPT OSS 20B through OpenAI and Mercury 2 through Inception 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 OpenAI API pricing and Inception API pricing, quoted per million tokens. Official rate sheets: https://developers.openai.com/api/docs/pricing and https://anotherwrapper.com/tools/llm-pricing. 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.
GPT OSS 20B supports up to 33K output tokens per request, while Mercury 2 supports up to 8K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
GPT OSS 20B runs at approximately 1000 tokens/second while Mercury 2 runs at 1009 tokens/second. Mercury 2 is faster in raw throughput. 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 GPT OSS 20B or Mercury 2 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. GPT OSS 20B costs $0.05/M input and $0.20/M output. Mercury 2 costs $0.25/M input and $0.75/M output.
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.
