Model provider

NanoGPT

Explore models served by NanoGPT.

193models

Pricing & endpoints

280 offers · USD per million tokens
ModelProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredRoute
Gemma 4 31B ITNanoGPT
google/gemma-4-31b-it
262,144131,072$0.10 / $0.45YesYesYes
View route
Step 3.5 FlashNanoGPT
stepfun-ai/step-3.5-flash
262,14465,536$0.10 / $0.30YesNoNo
View route
Qwen3.6 35B-A3BNanoGPT
qwen/qwen3.6-35b-a3b
262,14416,384$0.112 / $0.80NoYesNo
View route
Qwen3.6 35B-A3BNanoGPT
qwen/qwen3.6-35b-a3b:thinking
262,14416,384$0.112 / $0.80YesYesNo
View route
Gemma 4 26B A4B ITNanoGPT
google/gemma-4-26b-a4b-it
262,144131,072$0.12 / $0.38YesYesYes
View route
GLM-4.5-AirNanoGPT
z-ai/GLM-4.5-Air
128,00098,304$0.12 / $0.80NoYesYes
View route
GLM-4.5-AirNanoGPT
z-ai/GLM-4.5-Air:thinking
128,00098,304$0.12 / $0.80YesYesYes
View route
DeepSeek V4.1 FlashNanoGPT
deepseek/deepseek-v4.1-flash
1,000,000384,000$0.13 / $0.52YesYesYes
View route
DeepSeek V4.1 FlashNanoGPT
deepseek/deepseek-v4.1-flash:thinking
1,000,000384,000$0.13 / $0.52YesYesYes
View route
Gemma 4 26B A4B ITNanoGPT
google/gemma-4-26b-a4b-it:thinking
262,144131,072$0.13 / $0.40YesYesYes
View route
Qwen3 235B-A22B Instruct 2507NanoGPT
qwen/qwen3-235b-a22b-instruct-2507
262,14416,384$0.13 / $0.50NoYesYes
View route
DeepSeek V4 FlashNanoGPT
deepseek/deepseek-v4-flash
1,048,576384,000$0.14 / $0.28YesYesYes
View route
MiMo-V2.5NanoGPT
xiaomi/mimo-v2.5
1,048,576131,072$0.14 / $0.28YesYesYes
View route
MiMo-V2.6-FlashNanoGPT
xiaomi/mimo-v2.6-flash
1,048,576131,072$0.14 / $0.28YesYesYes
View route
Qwen3.8 FlashNanoGPT
qwen/qwen3.8-flash
991,808131,072$0.14 / $0.42YesYesYes
View route
DeepSeek V4 FlashNanoGPT
deepseek/deepseek-v4-flash:thinking
1,048,576384,000$0.14 / $0.28YesYesYes
View route
MiMo-V2.5NanoGPT
xiaomi/mimo-v2.5:thinking
1,048,576131,072$0.14 / $0.28YesYesYes
View route
Qwen3-Next 80B-A3B InstructNanoGPT
qwen/qwen3-next-80b-a3b-instruct
262,14432,768$0.15 / $0.65NoYesYes
View route
Qwen3.8 Omni FlashNanoGPT
qwen/qwen3.8-omni-flash
991,808131,072$0.15 / $0.47YesYesYes
View route
Qwen3.8 27BNanoGPT
qwen/qwen3.8-27b
262,14432,768$0.15 / $0.70YesYesYes
View route
GPT-4o miniNanoGPT
openai/gpt-4o-mini
128,00016,384$0.15 / $0.60NoNoNo
View route
GLM-5.3-FlashNanoGPT
TEE/glm-5.3-flash
1,048,576131,072$0.15 / $0.50YesYesYes
View route
Llama 3.3 Nemotron Super 49B v1NanoGPT
nvidia/Llama-3.3-Nemotron-Super-49B-v1
128,00016,384$0.15 / $0.15NoNoNo
View route
Gemma 4 31B ITNanoGPT
TEE/gemma-4-31b-it
262,144262,144$0.15 / $0.46YesYesNo
View route
Qwen3.8 27BNanoGPT
qwen/qwen3.8-27b:thinking
262,14432,768$0.15 / $0.70YesYesYes
View route
Qwen3-Next 80B-A3B (Thinking)NanoGPT
qwen/qwen3-next-80b-a3b-thinking
256,00032,768$0.15 / $0.65NoNoNo
View route
Nemotron 3 Nano 30B A3BNanoGPT
nvidia/nemotron-3-nano-30b-a3b
262,144235,929$0.17 / $0.68NoNoNo
View route
MiniMax-M2NanoGPT
minimax/minimax-m2
200,000131,072$0.17 / $1.53YesNoNo
View route
Qwen3.6 FlashNanoGPT
qwen/qwen3.6-flash
991,80865,536$0.19 / $1.16NoNoNo
View route
DeepSeek V3 0324NanoGPT
deepseek-v3-0324
128,0008,192$0.20 / $0.77NoYesYes
View route
Step 3.7 FlashNanoGPT
stepfun/step-3.7-flash:thinking
262,144256,000$0.20 / $1.15YesYesYes
View route
GPT OSS 20BNanoGPT
openai/gpt-oss-20b
128,00016,384$0.20 / $0.30YesYesNo
View route
GPT-5.6 LunaNanoGPT
openai/gpt-5.6-luna
1,050,000128,000$0.20 / $1.20YesYesYes
View route
Qwen3 Coder NextNanoGPT
qwen/qwen3-coder-next
262,14465,536$0.20 / $1.50NoYesYes
View route
GPT-5.4 nanoNanoGPT
openai/gpt-5.4-nano
400,000128,000$0.20 / $1.25YesYesYes
View route
Qwen3.6 35B-A3BNanoGPT
TEE/qwen3.6-35b-a3b
262,144262,144$0.20 / $1.27NoNoNo
View route
GPT-5.6 LunaNanoGPT
openai/gpt-5.6-luna-pro
1,050,000128,000$0.20 / $1.20YesYesYes
View route
Qwen2.5-Coder-32B-InstructNanoGPT
qwen/qwen2.5-coder-32b-instruct
32,0008,192$0.2006 / $0.2006NoNoNo
View route
Qwen3.6 27BNanoGPT
qwen/qwen3.6-27b
260,09665,536$0.203 / $2.24NoYesNo
View route
Qwen3.6 27BNanoGPT
qwen/qwen3.6-27b:thinking
260,09665,536$0.203 / $2.24YesYesNo
View route
41–80 of 280

Prices, limits and configurations apply to each serving offer. Open a model for its complete specifications and provider comparison.