Cheaper Inference

Service status

unknown

568 indexed models

568 matching models

qwen3-coder-30b-a3b

cheaperInference/qwen3-coder-30b-a3b

Context window
262,144
Maximum output
8,192
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

qwen3-coder-30b-a3b-instruct

cheaperInference/qwen3-coder-30b-a3b-instruct

Context window
256,000
Maximum output
8,192
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

qwen3-coder-next

cheaperInference/qwen3-coder-next

Context window
256,000
Maximum output
256,000
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

qwen3-embedding-0.6b

cheaperInference/qwen3-embedding-0.6b

Context window
32,768
Maximum output
32,768
Output modalities
embeddings
Capabilities
embeddings

qwen3-embedding-4b

cheaperInference/qwen3-embedding-4b

Context window
32,768
Maximum output
32,768
Output modalities
embeddings
Capabilities
embeddings

qwen3-embedding-8b

cheaperInference/qwen3-embedding-8b

Context window
32,768
Maximum output
32,768
Output modalities
embeddings
Capabilities
embeddings

qwen3-max-thinking

cheaperInference/qwen3-max-thinking

Context window
256,000
Maximum output
65,536
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

qwen3-next-80b-a3b-instruct

cheaperInference/qwen3-next-80b-a3b-instruct

Context window
256,000
Maximum output
262,114
Input modalities
text
Output modalities
text
Capabilities
structuredOutputs, toolCalling

Inference prices

qwen3-next-80b-a3b-thinking

cheaperInference/qwen3-next-80b-a3b-thinking

Context window
262,144
Maximum output
262,144
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Inference prices

qwen3-omni-30b-a3b-thinking

cheaperInference/qwen3-omni-30b-a3b-thinking

Context window
65,536
Maximum output
16,384
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, videoInput, visionInput

Inference prices

qwen3-vl-235b-a22b-instruct

cheaperInference/qwen3-vl-235b-a22b-instruct

Context window
256,000
Maximum output
262,144
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, toolCalling, visionInput

Inference prices

qwen3-vl-30b-a3b-instruct

cheaperInference/qwen3-vl-30b-a3b-instruct

Context window
16,384
Maximum output
8,192
Input modalities
text, image, video
Output modalities
text
Capabilities
multimodal, structuredOutputs, toolCalling, videoInput, visionInput

Inference prices

qwen3-vl-instruct

cheaperInference/qwen3-vl-instruct

Context window
262,144
Maximum output
262,144
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, promptCaching, structuredOutputs, toolCalling, visionInput

Inference prices

qwen-mt-plus

cheaperInference/qwen-mt-plus

Context window
16,384
Maximum output
8,192
Input modalities
text
Output modalities
text

Inference prices

Qwen: Qwen3 30B A3B

qwen/qwen3-30b-a3b-04-28

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique ability to switch seamlessly between a thinking mode for complex

Context window
40,960
Input modalities
text
Output modalities
text
Capabilities
reasoning, structuredOutputs, toolCalling

Benchmarks

  • Artificial Analysis: 7.6
  • LLM Stats · GitHub archive: 0.804
  • OpenRouter Benchmarks: 47%

Inference prices

recraft-v2

cheaperInference/recraft-v2

Output modalities
image
Capabilities
imageOutput

recraft-v3

cheaperInference/recraft-v3

Output modalities
image
Capabilities
imageOutput

recraft-v4

cheaperInference/recraft-v4

Output modalities
image
Capabilities
imageOutput

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace