Model ID
moonshotai/kimi-k2.6
Kimi K2.6
Model ID
moonshotai/kimi-k2.6
Kimi K2.6
Model ID
z-ai/glm-4.7
GLM-4.7
Model ID
deepseek/deepseek-r1-0528
DeepSeek R1
Model ID
deepseek/deepseek-v3.1
DeepSeek V3.1
Model ID
deepseek/deepseek-v3.2
DeepSeek V3.2
Model ID
qwen/qwen3-235b-a22b-2507
Qwen3 235B
Model ID
qwen/qwen3-coder
Qwen3 Coder
Model ID
meta-llama/llama-4-scout
Llama 4 Scout
Model ID
meta-llama/llama-3.3-70b
Llama 3.3 70B
Model ID
mistralai/mistral-small-3.2
Mistral Small 3.2
Model ID
openai/gpt-oss-120b
gpt-oss-120b
Model ID
microsoft/phi-4
Phi-4
Model ID
meta-llama/llama-3.1-8b
Llama 3.1 8B
Flagship · Moonshot AI
Strong open model for agents and code
≈ 0.26 pts per answer · 55 tok/s · context 256K
Prices in Harvanera Points (100 Points = USD 1). Click a model ID to copy it.
How charges are rounded: each request is charged for the tokens it actually processes at the model's listed price, converted at 100 Points = USD 1 and rounded up to the nearest 0.0001 Point. Prices on this page are rounded for display.
Strong open model for agents and code
Reasoning and coding with tool use
Step-by-step reasoning for hard problems
Flagship quality at a budget price
Newer DeepSeek with cheaper output
Large all-rounder at a small-model price
Open model for agents in your IDE
Long context and image input
Reliable workhorse for chat and RAG
Compact, fast, understands images
Open-weight reasoning model for pennies
Small model for simple tasks and classification
The cheapest option for bulk processing