impulse

Minicpm V 4.5

API id MiniCPM-V-4_5
Input / 1M
$0.658
at Nebius AI Studio
Output / 1M
$1.11
at Nebius AI Studio
Context window
32K
tokens
Max output
32K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Nebius AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.658$1.11
Cached input
80% off input
$0.13

What it costs a month

At Nebius AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$233
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$229
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$413
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,846
Use your own numbers

Where to run it

1 host serve Minicpm V 4.5. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
MiniCPM-V-4_5
$0.658 / $1.11

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Nebius AI Studio.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    40% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    74% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    74% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    66% less

Open-weight picks

  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    11% less
  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    17% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    32% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    37% less

Call it

Using Nebius AI Studio's API.

Python
from litellm import completion

response = completion(
    model="nebius/MiniCPM-V-4_5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Minicpm V 4.5 cost?

On Nebius AI Studio, Minicpm V 4.5 costs $0.658 per million input tokens and $1.11 per million output tokens. Cached input costs $0.13 per million tokens.

Which APIs offer Minicpm V 4.5?

Minicpm V 4.5 runs on 1 API: Nebius AI Studio.

What is Minicpm V 4.5's context window?

32K tokens, with up to 32K tokens in one reply.

Is Minicpm V 4.5 being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Minicpm V 4.5?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (40% less), Claude Haiku 5.5 on Anthropic (74% less) and Kimi K2.7 Code on CLF AI Gateway (11% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Minicpm V 4.5's API model id?

Use MiniCPM-V-4_5 with Nebius AI Studio.

Sources

Raw catalog entry for MiniCPM-V-4_5 on Nebius AI Studio
{
  "max_input_tokens": 32000,
  "max_output_tokens": 32000,
  "input_cost_per_token": 6.58e-7,
  "output_cost_per_token": 0.00000111,
  "litellm_provider": "nebius",
  "mode": "chat",
  "supports_vision": true,
  "source": "https://tokenfactory.nebius.com/api/public/models_info",
  "cache_read_input_token_cost": 1.3e-7
}