Olmocr 7B 0725
olmOCR-7B-0725-FP8Pricing
List prices at DeepInfra, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.27 | $1.50 |
What it costs a month
At DeepInfra list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$193
- RAG over documents2,000 requests a day, 8K in / 0.6K out$184
- Coding agent1,000 requests a day, 40K in / 2K out$414
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,008
Where to run it
1 host serve Olmocr 7B 0725. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
DeepInfraInference olmOCR-7B-0725-FP8 | $0.27 / $1.50 | olmOCR-7B-0725-FP8 |
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
- Open weights
- License: Apache-2.0Runtimes: TGI, 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 DeepInfra.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 20% less
- 65% less
- 65% less
- 55% less
Open-weight picks
- 9% less
- 9% less
- 16% less
- 22% less
Call it
Using DeepInfra's API.
from litellm import completion
response = completion(
model="deepinfra/olmOCR-7B-0725-FP8",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Olmocr 7B 0725 cost?
On DeepInfra, Olmocr 7B 0725 costs $0.27 per million input tokens and $1.50 per million output tokens.
Which APIs offer Olmocr 7B 0725?
Olmocr 7B 0725 runs on 1 API: DeepInfra.
What is Olmocr 7B 0725's context window?
16K tokens, with up to 16K tokens in one reply.
Is Olmocr 7B 0725 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Olmocr 7B 0725?
Models that cost less and keep most of what it can do: GPT-5.4 Nano on OpenAI (20% less), Claude Haiku 5.5 on Anthropic (65% less) and DeepSeek Flash on DeepSeek (9% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Olmocr 7B 0725's API model id?
Use olmOCR-7B-0725-FP8 with DeepInfra.
Sources
Raw catalog entry for olmOCR-7B-0725-FP8 on DeepInfra
{
"max_input_tokens": 16384,
"max_output_tokens": 16384,
"input_cost_per_token": 2.7e-7,
"output_cost_per_token": 0.0000015,
"litellm_provider": "deepinfra",
"mode": "chat",
"supports_tool_choice": false
}