impulse

Agnes 2.5 Pro

API id agnes-2.5-pro
Input / 1M
$0.45
at AIHubMix
Output / 1M
$0.90
at AIHubMix
Context window
1M
tokens
Max output
66K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at AIHubMix, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.45$0.90
Cached input
99% off input
$0.00378

What it costs a month

At AIHubMix list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$162
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$141
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$219
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,296
Use your own numbers

Where to run it

1 host serve Agnes 2.5 Pro. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
AIHubMixGateway
agnes-2.5-pro
$0.45 / $0.90

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
Features
Prompt caching

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 AIHubMix.

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
    18% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    64% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    64% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    53% less

Open-weight picks

  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    7% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    14% less
  • MiMo V2.6 Pro
    Xiaomi · on GMI Cloud
    $0.348 / $0.696
    Has every key capability
    23% less
  • MiniMax M3
    MiniMax · on EmpirioLabs AI
    $0.225 / $0.90
    Has every key capability
    30% less

Call it

Using AIHubMix's API.

Python
from litellm import completion

response = completion(
    model="aihubmix/agnes-2.5-pro",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Agnes 2.5 Pro cost?

On AIHubMix, Agnes 2.5 Pro costs $0.45 per million input tokens and $0.90 per million output tokens. Cached input costs $0.00378 per million tokens.

Which APIs offer Agnes 2.5 Pro?

Agnes 2.5 Pro runs on 1 API: AIHubMix.

What is Agnes 2.5 Pro's context window?

1M tokens, with up to 66K tokens in one reply.

Is Agnes 2.5 Pro being retired?

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

What are cheaper alternatives to Agnes 2.5 Pro?

Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (18% less), Claude Haiku 5.5 on Anthropic (64% less) and DeepSeek Flash on DeepSeek (7% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Agnes 2.5 Pro's API model id?

Use agnes-2.5-pro with AIHubMix.

Sources

Raw catalog entry for agnes-2.5-pro on AIHubMix
{
  "cache_read_input_token_cost": 3.78e-9,
  "input_cost_per_token": 4.5e-7,
  "litellm_provider": "aihubmix",
  "max_input_tokens": 1000000,
  "max_output_tokens": 65536,
  "mode": "chat",
  "output_cost_per_token": 9e-7,
  "source": "https://aihubmix.com/api/v1/models",
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_vision": true
}