impulse

Baichuan M2 32B

API id baichuan-m2-32b
Input / 1M
$0.07
at Novita AI
Output / 1M
$0.07
at Novita AI
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.07$0.07

What it costs a month

At Novita AI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$26.25
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$36.12
  • Coding agent1,000 requests a day, 40K in / 2K out$88.20
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$185
Use your own numbers

Where to run it

1 host serve Baichuan M2 32B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Novita AIInference
baichuan-m2-32b
$0.07 / $0.07

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
Text
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 Novita AI.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • DeepSeek R1 Qwen3 8B
    DeepSeek · on Novita AI
    $0.06 / $0.09
    Has every key capability
    4% less
  • Command R7B
    Cohere · on Cohere Chat
    $0.0375 / $0.15
    Has every key capability
    6% less
  • gpt-oss-120b
    OpenAI · on W&B Inference
    $0.03 / $0.17
    Has every key capability
    7% less
  • Gemma 4 26B
    Google · on Darkbloom
    $0.03 / $0.165
    Has every key capability
    9% less

Call it

Using Novita AI's API.

Python
from litellm import completion

response = completion(
    model="novita/baichuan-m2-32b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Baichuan M2 32B cost?

On Novita AI, Baichuan M2 32B costs $0.07 per million input tokens and $0.07 per million output tokens.

Which APIs offer Baichuan M2 32B?

Baichuan M2 32B runs on 1 API: Novita AI.

What is Baichuan M2 32B's context window?

131K tokens, with up to 131K tokens in one reply.

Is Baichuan M2 32B being retired?

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

What are cheaper alternatives to Baichuan M2 32B?

Models that cost less and keep most of what it can do: DeepSeek R1 Qwen3 8B on Novita AI (4% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Baichuan M2 32B's API model id?

Use baichuan-m2-32b with Novita AI.

Sources

Raw catalog entry for baichuan-m2-32b on Novita AI
{
  "litellm_provider": "novita",
  "mode": "chat",
  "input_cost_per_token": 7e-8,
  "output_cost_per_token": 7e-8,
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "supports_system_messages": true
}