Cobuddy
cobuddyPricing
List prices at Novita AI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.28 | $1.13 | |
| Cached input 75% off input | $0.07 | 75% off input |
What it costs a month
At Novita AI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$150
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$125
- Coding agent1,000 requests a day, 40K in / 2K out, cached$227
- Overnight batch20,000 requests a day, 4K in / 0.4K out$943
Where to run it
1 host serve Cobuddy. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Novita AIInference cobuddy | $0.28 / $1.13 | cobuddy |
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
- 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 Novita AI.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 6% less
- 59% less
- 59% less
- 47% less
Open-weight picks
- 2% less
- 4% less
- 12% less
- 20% less
Call it
Using Novita AI's API.
from litellm import completion
response = completion(
model="novita/cobuddy",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Cobuddy cost?
On Novita AI, Cobuddy costs $0.28 per million input tokens and $1.13 per million output tokens. Cached input costs $0.07 per million tokens.
Which APIs offer Cobuddy?
Cobuddy runs on 1 API: Novita AI.
What is Cobuddy's context window?
131K tokens, with up to 66K tokens in one reply.
Is Cobuddy being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Cobuddy?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (6% less), Claude Haiku 5.5 on Anthropic (59% less) and Qwen3.7 Plus on Replicate (2% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Cobuddy's API model id?
Use cobuddy with Novita AI.
Sources
Raw catalog entry for cobuddy on Novita AI
{
"cache_read_input_token_cost": 7e-8,
"input_cost_per_token": 2.8e-7,
"litellm_provider": "novita",
"max_input_tokens": 131072,
"max_output_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 0.00000113,
"source": "https://novita.ai/pricing",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": false
}