PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.292mPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.362mPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.752mPRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.102mPRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.202mPRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.132mPRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8033mPRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0033mPRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9933mPERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%1hPERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%1hPERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%1hPERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%1hPERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%1hPERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%1hPERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%1hPERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%1hPERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%1hPERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%1hPERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%1hPERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%1hPERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%1hPERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%1hPERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%1hPERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%1hPERFORMANCEGLM-4.7 via OpenRouter: TTFT ↓ 78%1hPERFORMANCEGPT-OSS 20B → Groq: TTFT ↑ 24%1hPERFORMANCEKimi K3 → Together AI: TTFT ↓ 34%1hPERFORMANCEDeepSeek V4 Flash via OpenRouter: throughput ↓ 17%1hPERFORMANCELlama 3.3 70B via Cortecs: TTFT ↓ 51%1hPERFORMANCEQwen3 235B via OpenRouter: throughput ↑ 37%1hPERFORMANCEQwen3 235B via OpenRouter: TTFT ↓ 29%1hPERFORMANCEDeepSeek V4 Flash → Together AI: throughput ↑ 19%1hPERFORMANCEGLM-5.3 via OpenRouter: throughput ↓ 17%1hPERFORMANCEGPT-OSS 20B via Cortecs: throughput ↑ 28%1hPERFORMANCELlama 3.3 70B → Together AI: TTFT ↓ 33%1hPRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.291hPRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.361hPRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.751hPRICE~deepseek/deepseek-v4-flash-latest cached_input_per_mtok decreased from 0.0077 to 0.00111h
MARKET INTELLIGENCE

The Price–Performance Frontier

Which measured providers are worth their price — and which are dominated on both axes at once.

Key findings
  • Measured output prices span $0.45–$15.60 per million tokens — a 35× range.
  • 2 of 8 measured providers are on the frontier; the rest are dominated — some other provider is both better and cheaper.
  • OpenAI carries the highest measured output price in the current window.

The frontier

A provider belongs on the frontier when nothing measured beats it on score and price simultaneously. Today that set is Cerebras, Groq — every other measured provider is paying for something the data does not show.

879196100$4.37$8.74$13.10$17.47Output price $/M →Score ↑Cerebras — $0.75/M out · score 99.0CerebrasGroq — $0.45/M out · score 98.2Mistral — $4.50/M out · score 93.2Scaleway — $1.81/M out · score 92.4Cortecs — $1.23/M out · score 92.1OpenAI — $15.60/M out · score 90.4Together — $1.12/M out · score 85.5OpenRouter — $1.20/M out · score 84.3
Measured score vs $/M output · frontier providers highlighted · ● MEASURED
What this means for engineers
  • Price is measurable and volatile; re-evaluate the frontier after every pricing event, not annually.
  • A dominated provider is not necessarily a wrong choice — residency, contracts or capabilities may justify it — but the premium should be a decision, not an accident.
Dataset

Figures recompute from the live rolling window on every visit; the snapshot and versions above are the provenance of the regime that produced them. View the current benchmark →

Cite this researchInferenceBench (2026). The Price–Performance Frontier. InferenceBench Research.
← All research
Related research
The Price–Performance Frontier · InferenceBench