Morph Kimik3
morph-kimik3Pricing
List prices at Morph, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.50 | $14.00 | |
| Cached input 88% off input | $0.29 | 88% off input |
What it costs a month
At Morph list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,601
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$1,174
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,984
- Overnight batch20,000 requests a day, 4K in / 0.4K out$9,360
Where to run it
1 host serve Morph Kimik3. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
MorphCloud morph-kimik3 | $2.50 / $14.00 | morph-kimik3 |
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
- Parallel tool callsPrompt caching
- Open weights
- License: Modified MIT LicenseRuntimes: SGLang, vLLM
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 Morph.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 10% less
- 26% less
- 26% less
- 44% less
Open-weight picks
- 26% less
- 58% less
- 68% less
- 90% less
Call it
Using Morph's API.
from litellm import completion
response = completion(
model="morph/morph-kimik3",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Morph Kimik3 cost?
On Morph, Morph Kimik3 costs $2.50 per million input tokens and $14.00 per million output tokens. Cached input costs $0.29 per million tokens.
Which APIs offer Morph Kimik3?
Morph Kimik3 runs on 1 API: Morph.
What is Morph Kimik3's context window?
1M tokens, with up to 1M tokens in one reply.
Is Morph Kimik3 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Morph Kimik3?
Models that cost less and keep most of what it can do: GPT-5.3 Codex on OpenAI (10% less), Gemini 4 Carbon on Google AI Studio (26% less) and Kimi K3.1 Pro on Databricks (26% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Morph Kimik3's API model id?
Use morph-kimik3 with Morph.
Sources
Raw catalog entry for morph-kimik3 on Morph
{
"max_input_tokens": 1048576,
"max_output_tokens": 1048576,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.000014,
"cache_read_input_token_cost": 2.9e-7,
"litellm_provider": "morph",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_reasoning": true,
"supports_prompt_caching": true,
"source": "https://www.morphllm.com/pricing",
"supports_vision": true
}