Models | Machine Learning Inference

featured

text-generation

olmOCR is a specialized AI tool that converts PDF documents into clean, structured text while preserving important formatting and layout information. What makes olmOCR particularly valuable for developers is its ability to handle challenging PDFs that traditional OCR tools struggle with—including complex layouts, poor-quality scans, handwritten text, and documents with mixed content types. Built on a fine-tuned 7B vision-language model, olmOCR provides enterprise-grade PDF processing at a fraction of the cost of proprietary solutions.

fp8

16k

$0.14 in, $0.80 out / 1M

featured

text-generation

meta-llama/

Llama-4-Maverick-17B-128E-Instruct-FP8

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Maverick, a 17 billion parameter model with 128 experts

fp8

1024k

$0.15 in, $0.60 out / 1M

featured

text-generation

meta-llama/

Llama-4-Scout-17B-16E-Instruct

The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Scout, a 17 billion parameter model with 16 experts

fp8

320k

$0.08 in, $0.30 out / 1M

featured

text-generation

mistralai/

Mistral-Small-3.2-24B-Instruct-2506

Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the infinite-generation errors, and a more robust function-calling interface—while otherwise matching or slightly improving on all previous text and vision benchmarks.

fp8

125k

$0.075 in, $0.20 out / 1M

featured

text-generation

anthropic/

claude-4-opus

Anthropic’s most powerful model yet and the state-of-the-art coding model. It delivers sustained performance on long-running tasks that require focused effort and thousands of steps, significantly expanding what AI agents can solve. Claude Opus 4 is ideal for powering frontier agent products and features.

195k

$16.50 in, $82.50 out / 1M

featured

text-generation

anthropic/

claude-4-sonnet

Anthropic's mid-size model with superior intelligence for high-volume uses in coding, in-depth research, agents, & more.

195k

$3.30 in, $16.50 out / 1M

featured

text-generation

google/

gemini-2.5-flash

Gemini 2.5 Flash is Google's latest thinking model, designed to tackle increasingly complex problems. It's capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy. Gemini 2.5 Flash: best for balancing reasoning and speed.

976k

$0.30 in, $2.50 out / 1M

featured

text-generation

google/

gemini-2.5-pro

Gemini 2.5 Pro is Google's the most advanced thinking model, designed to tackle increasingly complex problems. Gemini 2.5 Pro leads common benchmarks by meaningful margins and showcases strong reasoning and code capabilities. Gemini 2.5 models are thinking models, capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accuracy. The Gemini 2.5 Pro model is now available on DeepInfra.

976k

$1.25 in, $10.00 out / 1M

featured

text-generation

google/

gemma-3-27b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2

fp8

128k

$0.09 in, $0.16 out / 1M

featured

text-generation

google/

gemma-3-12b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3-12B is Google's latest open source model, successor to Gemma 2

bfloat16

128k

$0.04 in, $0.13 out / 1M

featured

text-generation

google/

gemma-3-4b-it

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3-12B is Google's latest open source model, successor to Gemma 2

bfloat16

128k

$0.04 in, $0.08 out / 1M

text-generation

Qwen/

Qwen2.5-VL-32B-Instruct

bfloat16

125k

$0.20 in, $0.60 out / 1M

text-generation

Qwen/

Qwen3-VL-235B-A22B-Instruct

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

fp8

256k

$0.30 in, $1.49 out / 1M

text-generation

Qwen/

Qwen3-VL-235B-A22B-Thinking

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

fp8

256k

$0.45 in, $3.49 out / 1M

text-generation

Qwen/

Qwen3-VL-30B-A3B-Instruct

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

fp8

256k

$0.29 in, $0.99 out / 1M

text-generation

Qwen/

Qwen3-VL-30B-A3B-Thinking

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

fp8

256k

$0.29 in, $0.99 out / 1M

text-generation

Qwen/

Qwen3-VL-4B-Instruct

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

fp8

256k

$0.10 in, $0.60 out / 1M

text-generation

Qwen/

Qwen3-VL-4B-Thinking

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

fp8

256k

$0.10 in, $1.00 out / 1M

text-generation

Qwen/

Qwen3-VL-8B-Instruct

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

fp8

256k

$0.18 in, $0.69 out / 1M

text-generation

Qwen/

Qwen3-VL-8B-Thinking

Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.

fp8

256k

$0.18 in, $2.09 out / 1M

text-generation

anthropic/

claude-3-7-sonnet-latest

195k

$0.33 cached, $3.30 in, $16.50 out / 1M

text-generation

google/

gemini-1.5-flash

Gemini 1.5 Flash is Google's foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video. It's adept at processing visual and text inputs such as photographs, documents, infographics, and screenshots. Gemini 1.5 Flash is designed for high-volume, high-frequency tasks where cost and latency matter.

976k

Deprecated

text-generation

google/

gemini-1.5-flash-8b

976k

Deprecated

text-generation

google/

gemini-2.0-flash-001

976k

$0.10 in, $0.40 out / 1M

Browse deepinfra models: