As of August 30, 2026, MiniCPM-SALA is 67% cheaper per million tokens than GPT OSS 120B High. GPT OSS 120B High is $0.10 / $0.50 per million input/output tokens versus MiniCPM-SALA at $0.10 / $0.10. Sources: https://developers.openai.com/api/docs/pricing and https://www.openbmb.cn/
Sources: OpenAI API pricing (https://developers.openai.com/api/docs/pricing); OpenBMB pricing (https://www.openbmb.cn/)
GPT OSS 120B High
OpenAI
Input
$0.10
Output
$0.50
MiniCPM-SALA
OpenBMB
Input
$0.10
Output
$0.10
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 120B HighMiniCPM-SALAVerdict
MiniCPM-SALA offers significantly lower pricing, while GPT OSS 120B High leads on benchmark performance. Your choice depends on whether cost efficiency or raw capability matters more for your use case.
As of August 30, 2026, MiniCPM-SALA is 67% cheaper on blended LLM API pricing. MiniCPM-SALA costs $0.10 per million input tokens and $0.10 per million output tokens ($0.20 blended 1M-in + 1M-out). GPT OSS 120B High costs $0.10 / $0.50 per million tokens ($0.60 blended). Sources: https://developers.openai.com/api/docs/pricing and https://www.openbmb.cn/. The cheapest LLM for your app still depends on how many output tokens you generate.
GPT OSS 120B High OpenAI API pricing is $0.10 input and $0.50 output per million tokens via OpenAI. MiniCPM-SALA OpenBMB API pricing is $0.10 input and $0.10 output per million tokens via OpenBMB. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
MiniCPM-SALA has a published HumanEval score of 95.1%. GPT OSS 120B High does not have that eval on this page yet.
GPT OSS 120B High supports a 131K token context window, while MiniCPM-SALA supports 33K tokens. GPT OSS 120B High 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.
GPT OSS 120B High leads on 3 of 3 shared benchmarks versus MiniCPM-SALA'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 GPT OSS 120B High and MiniCPM-SALA are production API models. For cost-sensitive production traffic, MiniCPM-SALA 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 120B High through OpenAI and MiniCPM-SALA through OpenBMB 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 OpenBMB API pricing, quoted per million tokens. Official rate sheets: https://developers.openai.com/api/docs/pricing and https://www.openbmb.cn/. 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 120B High supports up to 131K output tokens per request, while MiniCPM-SALA 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.
GPT OSS 120B High has a measured throughput of approximately 100 tokens/second. Throughput data for MiniCPM-SALA 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 GPT OSS 120B High or MiniCPM-SALA 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 120B High costs $0.10/M input and $0.50/M output. MiniCPM-SALA costs $0.10/M input and $0.10/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
343 models across 36 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.
