PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.808m PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.008m PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.988m PRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.1339m PRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.2039m PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.1039m PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.7539m PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.3639m PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.2939m PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.991h PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.001h PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.801h PERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%2h PERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%2h PERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%2h PERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%2h PERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%2h PERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%2h PERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%2h PERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%2h PERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%2h PERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%2h PERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%2h PERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%2h PERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%2h PERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%2h PERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%2h PERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%2h PERFORMANCEGLM-4.7 via OpenRouter: TTFT ↓ 78%2h PERFORMANCEGPT-OSS 20B → Groq: TTFT ↑ 24%2h PERFORMANCEKimi K3 → Together AI: TTFT ↓ 34%2h PERFORMANCEDeepSeek V4 Flash via OpenRouter: throughput ↓ 17%2h PERFORMANCELlama 3.3 70B via Cortecs: TTFT ↓ 51%2h PERFORMANCEQwen3 235B via OpenRouter: throughput ↑ 37%2h PERFORMANCEQwen3 235B via OpenRouter: TTFT ↓ 29%2h PERFORMANCEDeepSeek V4 Flash → Together AI: throughput ↑ 19%2h PERFORMANCEGLM-5.3 via OpenRouter: throughput ↓ 17%2h PERFORMANCEGPT-OSS 20B via Cortecs: throughput ↑ 28%2h PERFORMANCELlama 3.3 70B → Together AI: TTFT ↓ 33%2h PRICEtencent/hy4-preview output_per_mtok increased from 2.25 to 2.502h

PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.808m PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.008m PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.988m PRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.1339m PRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.2039m PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.1039m PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.7539m PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.3639m PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.2939m PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.991h PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.001h PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.801h PERFORMANCEGLM-5.2 → Scaleway: TTFT ↑ 20%2h PERFORMANCEDeepSeek V4 Flash → Scaleway: TTFT ↑ 35%2h PERFORMANCEMistral Medium 3.5 → Scaleway: TTFT ↓ 21%2h PERFORMANCEDeepSeek V4 Flash → Scaleway: throughput ↓ 20%2h PERFORMANCEGPT-OSS 120B → Scaleway: throughput ↑ 31%2h PERFORMANCEGPT-OSS 120B → Scaleway: TTFT ↓ 24%2h PERFORMANCEGPT-OSS 120B → Together AI: throughput ↑ 20%2h PERFORMANCEKimi K3 via OpenRouter: TTFT ↓ 49%2h PERFORMANCEGLM-5.2 via OpenRouter: reliability recovered 96.8% → 100.0%2h PERFORMANCEKimi K3 via Cortecs: throughput ↑ 184%2h PERFORMANCEKimi K3 via Cortecs: TTFT ↓ 42%2h PERFORMANCEGLM-5.2 via OpenRouter: throughput ↓ 49%2h PERFORMANCEGLM-5.2 via OpenRouter: TTFT ↑ 121%2h PERFORMANCEMiniMax M3 via OpenRouter: reliability recovered 96.8% → 100.0%2h PERFORMANCEDeepSeek V4 Pro via Cortecs: throughput ↑ 27%2h PERFORMANCEGPT-OSS 120B via OpenRouter: throughput ↓ 22%2h PERFORMANCEGLM-4.7 via OpenRouter: TTFT ↓ 78%2h PERFORMANCEGPT-OSS 20B → Groq: TTFT ↑ 24%2h PERFORMANCEKimi K3 → Together AI: TTFT ↓ 34%2h PERFORMANCEDeepSeek V4 Flash via OpenRouter: throughput ↓ 17%2h PERFORMANCELlama 3.3 70B via Cortecs: TTFT ↓ 51%2h PERFORMANCEQwen3 235B via OpenRouter: throughput ↑ 37%2h PERFORMANCEQwen3 235B via OpenRouter: TTFT ↓ 29%2h PERFORMANCEDeepSeek V4 Flash → Together AI: throughput ↑ 19%2h PERFORMANCEGLM-5.3 via OpenRouter: throughput ↓ 17%2h PERFORMANCEGPT-OSS 20B via Cortecs: throughput ↑ 28%2h PERFORMANCELlama 3.3 70B → Together AI: TTFT ↓ 33%2h PRICEtencent/hy4-preview output_per_mtok increased from 2.25 to 2.502h

Mistral Medium 3.5

4 providers · 128B dense · 256k context · 2 regions · all models →

Mistral Medium 3.5 across 4 providers

Same model. Different infrastructure.

TTFT spread1.6×Throughput spread2.2×Output price1.1×Tool reliability0.0 pts

TTFT164 ms262 msbest: Scaleway

Throughput69 tok/s152 tok/sbest: OpenRouter

Output price$7.50/M$8.60/Mbest: OpenRouter

Reliability99.5%100.0%best: Mistral

Tool success100.0%100.0%best: Mistral

Mistral Medium 3.5 — tool-calling benchmark

4 providers · 100.0% → 100.0% · 0.0 pt spread

#	Provider	Tools	Δ best	Rel.	JSON	TTFT	P95	Tok/s	$ Out
01	OpenRouter	100.0%	—	100.0%	100.0%	262 ms	449 ms	152	$7.50
02	Cortecs	100.0%	−0.0	99.5%	100.0%	262 ms	447 ms	151	$8.07
03	Scaleway	100.0%	−0.0	100.0%	100.0%	164 ms	597 ms	69	$8.60
04	Mistral	100.0%	−0.0	100.0%	100.0%	224 ms	433 ms	145	$7.50

Mistral Medium 3.5 inference benchmark: fastest & cheapest providers · InferenceBench