Every provider of MiMo V2.6 Flash from Xiaomi that OpenRouter, Vercel AI Gateway and models.dev list, cheapest first: input, output and cached-input prices per 1M tokens, context, speed and uptime. Checked every hour.
Pareto Inference runs this page and is one of the providers listed. Rows are sorted by price, and Pareto's rows are labeled and placed by price like any other. The methodology says what is included and what is left out. Spot a wrong number? Email us.
Cheapest right now
USD per 1M tokens at 17:32 UTC, peak hours applied.
Providers
Sorted by the agent blend now: the price of 1M tokens that are 5% uncached input, 94% cached input and 1% output, the mix measured on Pareto's coding-agent traffic. Under it, the 3:1 blend: three input tokens to one output token, cache ignored. Speed and time to first token are Vercel AI Gateway's medians for the last hour; uptime is the last day's, from Vercel AI Gateway where it lists the provider, else OpenRouter.
| Provider | Blended | Input | Output | Cached input | Context | Speed | Uptime |
|---|---|---|---|---|---|---|---|
| GMICloudbf16OpenRouter · Vercel AI Gateway | $0.01013:1 $0.14 | $0.112 | $0.224 | $0.0024 | 1.05M945K out | 47 tok/s2.29 s TTFT | 99.37% |
| Pareto InferenceDirect | $0.011193:1 $0.1575 | $0.126 | $0.252 | $0.00252 | 1M131K out | — | — |
| RequestyDirect, per models.dev | $0.012343:1 $0.175 | $0.14 | $0.28 | $0.0027 | 1.05M131K out | — | — |
| BoundlessVercel AI Gateway | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M1.05M out | 132 tok/s0.55 s TTFT | 100% |
| DeepInfrafp8OpenRouter · Vercel AI Gateway | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M944K out | 44 tok/s3.08 s TTFT | 99.93% |
| DevPass (LLM Gateway)Direct, per models.dev | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M131K out | — | — |
| InferenceNetVercel AI Gateway | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M1.05M out | — | — |
| NanoGPTDirect, per models.dev | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M131K out | — | — |
| NovitaVercel AI Gateway | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M131K out | 42 tok/s2.62 s TTFT | 99.95% |
| Ollama CloudDirect, per models.dev | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M131K out | — | — |
| Standard ComputeDirect, per models.dev | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M50K out | — | — |
| Tempr GatewayDirect, per models.dev | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M131K out | — | — |
| Tencent CloudVercel AI Gateway | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1M128K out | 52 tok/s2.12 s TTFT | 99.78% |
| Xiaomifp8OpenRouter · Vercel AI Gateway | $0.012433:1 $0.175 | $0.14 | $0.28 | $0.0028 | 1.05M131K out | 35 tok/s5.43 s TTFT | 99.84% |
| Coherefp8OpenRouter | $0.012623:1 $0.175 | $0.14 | $0.28 | $0.003 | 1.05M131K out | — | 99.24% |
| Makorafp8OpenRouter | $0.012623:1 $0.175 | $0.14 | $0.28 | $0.003 | 1.05M131K out | — | 99.72% |
| AIHubMixDirect, per models.dev | $0.013763:1 $0.1937 | $0.155 | $0.31 | $0.0031 | 1.05M131K out | — | — |
| CrossModelDirect, per models.dev | $0.014963:1 $0.20 | $0.16 | $0.32 | $0.004 | 1.05M131K out | — | — |
| above.devDirect, per models.dev | $0.015043:1 $0.2115 | $0.1692 | $0.3385 | $0.0034 | 1.05M131K out | — | — |
| Venicefp8OpenRouter | $0.015773:1 $0.2187 | $0.175 | $0.35 | $0.00375 | 1M131K out | — | 98.62% |
| Tenstorrentfp8OpenRouter | $0.017763:1 $0.25 | $0.20 | $0.40 | $0.004 | 1.05M131K out | — | 54.46% |
| Darkbloomfp4OpenRouter | $0.05483:1 $0.145 | $0.10 | $0.28 | $0.05 | 1.05M131K out | — | 100% |
| Kilo GatewayDirect, per models.dev | $0.05483:1 $0.145 | $0.10 | $0.28 | $0.05 | 1.05M131K out | — | — |
| EmpirioLabs AIDirect, per models.dev | $0.14143:1 $0.175 | $0.14 | $0.28 | $0.14 | 1.05M131K out | — | — |
- OpenRouter: checked
- Vercel AI Gateway: checked
- models.dev: checked
- Pareto: its own self-serve prices, current
Index