PRICE~z-ai/glm-latest cached_input_per_mtok increased from 0.08 to 0.1514m PRICE~z-ai/glm-latest output_per_mtok decreased from 4.00 to 2.7914m PRICE~z-ai/glm-latest input_per_mtok decreased from 0.12 to 0.06614m PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.4514m PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.98 to 0.9714m PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.8114m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.008614m PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok decreased from 0.10 to 0.004214m PRICE~deepseek/deepseek-pro-latest output_per_mtok decreased from 4.20 to 0.4014m PRICE~deepseek/deepseek-pro-latest input_per_mtok increased from 0.13 to 0.1314m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01214m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01214m PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8045m PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0045m PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9845m PRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.131h PRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.201h PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.101h PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.751h PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.361h PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.291h PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.992h PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.002h PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.802h 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

PRICE~z-ai/glm-latest cached_input_per_mtok increased from 0.08 to 0.1514m PRICE~z-ai/glm-latest output_per_mtok decreased from 4.00 to 2.7914m PRICE~z-ai/glm-latest input_per_mtok decreased from 0.12 to 0.06614m PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.4514m PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.98 to 0.9714m PRICE~deepseek/deepseek-v4-flash-latest output_per_mtok decreased from 1.04 to 0.8114m PRICE~deepseek/deepseek-v4-flash-latest input_per_mtok increased from 0.0038 to 0.008614m PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok decreased from 0.10 to 0.004214m PRICE~deepseek/deepseek-pro-latest output_per_mtok decreased from 4.20 to 0.4014m PRICE~deepseek/deepseek-pro-latest input_per_mtok increased from 0.13 to 0.1314m PRICEdeepseek/deepseek-v4-flash-0731 cached_input_per_mtok increased from 0.0051 to 0.01214m PRICEdeepseek/deepseek-v4-flash-0731 input_per_mtok increased from 0.0051 to 0.01214m PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.8045m PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.0045m PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.9845m PRICE~deepseek/deepseek-pro-latest input_per_mtok decreased from 0.13 to 0.131h PRICE~deepseek/deepseek-pro-latest output_per_mtok increased from 0.40 to 4.201h PRICE~deepseek/deepseek-pro-latest cached_input_per_mtok increased from 0.0042 to 0.101h PRICE~moonshotai/kimi-latest input_per_mtok decreased from 0.99 to 0.751h PRICE~moonshotai/kimi-latest output_per_mtok decreased from 13.00 to 11.361h PRICE~moonshotai/kimi-latest cached_input_per_mtok decreased from 0.80 to 0.291h PRICE~moonshotai/kimi-latest input_per_mtok increased from 0.75 to 0.992h PRICE~moonshotai/kimi-latest output_per_mtok increased from 11.36 to 13.002h PRICE~moonshotai/kimi-latest cached_input_per_mtok increased from 0.29 to 0.802h 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

Mistral Large 3

3 providers · 675B MoE · 256k context · 2 regions · all models →

Mistral Large 3 provider ranking

#1 OverallOpenRouter100.0 FastestOpenRouter5.33 s Best valueOpenRouter Europe #1Cortecs98.3 Best toolsCortecs100.0%Best structuredOpenRouter99.0%

#ProviderΔ30d

01OpenRouterBEST OVERALL● MEASUREDUS · Routed · Mistral Large 3100.0%——406—5.3s81P100↑ 5.6

02CortecsBEST TOOLSEU RESIDENT● MEASUREDAT · Routed · Mistral Large 3100.0%100.0%86.1%4137205.4s79P33↑ 0.8

03MistralEU RESIDENTEU OWNED● MEASUREDFR · Serverless · Mistral Large 3100.0%100.0%83.3%38915855.9s73P67—

3 of 3 providers ranked · Methodology →

Sort

01OpenRouter100.0

Best overallUS · Routed · Mistral Large 3

TTFT406 ms

Rel.100.0%

Tok/s81

$ Out$1.50

Tools—

Δ30d+5.6

Best toolsAT · Routed · Mistral Large 3

TTFT413 ms

Rel.100.0%

Tok/s79

$ Out$1.89

Tools100.0%

Δ30d+0.8

FR · Serverless · Mistral Large 3

TTFT389 ms

Rel.100.0%

Tok/s73

$ Out$1.50

Tools100.0%

Δ30d—

3 of 3 providers ranked · Methodology →

Mistral Large 3 inference benchmark: fastest & cheapest providers · InferenceBench