MiMo V2.5 Pro API pricing
DeepInfra · chat model · 1.0M context · ranked #1008 of 1557 by input price
Reviewed by Mohammad Ghonchegi · dataset generated 2026-10-28 12:57 UTC · every figure below is recomputed from it on each refresh · how the numbers are produced
What MiMo V2.5 Pro costs in practice
MiMo V2.5 Pro from DeepInfra is billed at $1 per million input tokens and $3 per million output tokens. Cached input costs $0.2 per million — 80% below fresh input, which is what a long system prompt resent on every call actually pays. It ranks #1008 of 1557 priced chat listings by input price, which makes it 1.7× the median priced model in this index ($0.6).
Three concrete workloads on this model's rates: a 20,000 requests/day support bot sending 2,500 tokens in and 400 out costs about $2220 a month; summarising 5,000 documents a day at 12,000 tokens in and a 600-token summary costs about $2070; and 1,000 agent sessions a day at 30,000 input and 5,000 output tokens costs about $1350. With 80% of that input served from cache it drops to $774 — the cache rate matters more than the headline rate for this shape of workload.
How DeepInfra bills: DeepInfra hosts open-weight models per million tokens, with cache-read discounts on some endpoints and no minimum spend. The rate above is the one this index normalises to (USD per million tokens); the authoritative figure is always the provider's own pricing page, linked below.
The figure above excludes batch and committed-use discounts, regional rates, free tiers and enterprise agreements — providers publish those separately, and they can move the real bill by tens of percent. Context is listed as 1.0M tokens with at most 1.0M tokens of output per call; some providers bill requests above a long-context threshold at a higher tier, which this page does not model. Token counting also differs between providers' tokenizers, so two providers quoting the same rate can bill a different total for the same text.
Use MiMo V2.5 Pro when you need tool calling, reasoning modes, prompt caching and the monthly figure above fits the budget. If it does not, Gemini Exp 1114 (Google Gemini) is the nearest cheaper option at free per million input tokens — keep the capability flags in mind before swapping, since a cheaper model that lacks one of the features above will cost more once you work around it.
The same model on every platform we track
MiMo V2.5 Pro appears on 2 platforms here, and the spread is real: Novita AI lists input at $0.522 per million tokens against $1 at DeepInfra — 1.9× the same model for identical work. The platform table below is the whole point of this page.
| Platform | Input $/1M | Output $/1M | Cached $/1M | Context | Listing |
|---|---|---|---|---|---|
| Novita AI | $0.522 | $1.04 | $0.0043 | 1.0M | details |
| DeepInfrathis page | $1 | $3 | $0.2 | 1.0M | — |
Cheapest listing today: Novita AI at $0.522 per million input tokens — see that listing
Monthly cost examples
Assuming 1,200 prompt + 400 completion tokens per request unless noted, billed 30 days a month and without cache hits.
| Workload | Cost / month | Cost / day |
|---|---|---|
| 1,000 requests/day | $72 | $2.4 |
| 10,000 requests/day | $720 | $24 |
| 100,000 requests/day | $7200 | $240 |
| 1M summaries/month | $8899.91 | $296.66 |
Model a different profile in the cost calculator.
Capabilities
Cheaper alternatives
Ranked by blended cost (3× input + 1× output) — cheaper, but check context and capabilities before switching.
| # | Model | Provider | Input $/1M | Output $/1M | Cached $/1M | Context |
|---|---|---|---|---|---|---|
| 1 | Gemini Exp 1114 | Google Gemini | free | free | — | 1.0M |
| 2 | Gemini Exp 1206 | Google Gemini | free | free | — | 2.1M |
| 3 | Gemma 3 27b It | Google Gemini | free | free | — | 131K |
| 4 | Gemma 4 26b A4b It | Google Gemini | free | free | — | 262K |
| 5 | Gemma 4 31b It | Google Gemini | free | free | — | 262K |
| 6 | Learnlm 1.5 Pro Experimental | Google Gemini | free | free | — | 33K |
Data provenance
This page is assembled from the sources below. Where two sources disagree, both are shown.
Only one source publishes this model; no independent cross-check available yet.
Compilation is automated and re-run on every refresh (2026-10-28 12:57 UTC); the page structure and its explanatory copy are written and reviewed by the editor — see how this is made. For turning this rate into a budget rather than a rate, see the cost-planning guide.
More from DeepInfra
Frequently asked
› How much does MiMo V2.5 Pro cost per 1,000 tokens?
About $0.001 for input and $0.003 for output tokens, based on the per-million rates on this page.
› Is MiMo V2.5 Pro cheaper than other models?
By input price it ranks #1008 of 1557 priced chat models in this index, putting it in the more expensive half of the market.
› Is MiMo V2.5 Pro cheaper on another platform?
We track 2 platforms serving this model. The cheapest input rate today is $0.522 per million tokens at Novita AI; the most expensive is $1 at DeepInfra.
› How often is MiMo V2.5 Pro's price checked?
The dataset was last refreshed 2026-10-28 12:57 UTC. Providers can change pricing at any time — verify with DeepInfra before committing to a budget.
This is one of several platform listings of MiMo V2.5 Pro. The canonical, most complete version of this page is Novita AI's listing.