Llama 3.3 70B Instruct vs Mistral Medium 3.5
API pricing, context, and independently measured performance, side by side. Llama 3.3 70B Instruct starts 93% cheaper on input than Mistral Medium 3.5 at list prices.
Llama 3.3 70B Instruct
Meta · released Dec 6, 2024
Best input$0.10 / MTok
Best output$0.32 / MTok
Context131K
Providers13
Fastest measured0.59s° TTFT · 86 tok/s
Open weightsToolsStructured outputPrompt caching
Mistral Medium 3.5
Mistral · released Apr 30, 2026
Best input$1.50 / MTok
Best output$7.50 / MTok
Context262K
Providers1
Fastest measured4.3s° TTFT · 151 tok/s
VisionToolsReasoningStructured output
Cheapest providers, measuredUSD / MTOK
| MODEL | PROVIDER | INPUT | OUTPUT | TTFT | TPS | SMOKE |
|---|---|---|---|---|---|---|
| Llama 3.3 70B Instruct |  DeepInfra | $0.10 | $0.32 | 1.9s° | 12° tok/s | 5/5 |
| Llama 3.3 70B Instruct |  Nebius | $0.13 | $0.40 | 15s° | 3° tok/s | 5/5 |
| Llama 3.3 70B Instruct |  Novita | $0.135 | $0.40 | 1.8s° | 25° tok/s | 5/5 |
| Mistral Medium 3.5 |  Mistral | $1.50 | $7.50 | 4.3s° | 151° tok/s | — |
TTFT/TPS: ModelIndex-measured medians (P50, trailing 72h) · chat10k profile (~10K in / 200 out) · ° = measured via OpenRouter routing (adds a hop) · SMOKE: of 5 programmatic capability probes passed · methodology v1.1 — full details on each model page