Provider Models
Thinking Machines LLM Models
Compare Thinking Machines models with normalized token pricing, context window limits, modalities, and capability metadata. This page is optimized for provider-level model research.
38 active models listed. Open all Thinking Machines models filters
| Model | Context | Input Price | Output Price |
|---|---|---|---|
|
DeepSeek-V3.1
thinkingmachines/deepseek-ai/DeepSeek-V3.1
|
32,768 | $1.695/1M | $4.215/1M |
|
DeepSeek V4.1 Flash
thinkingmachines/deepseek-ai/DeepSeek-V4.1-Flash:peft:262144
|
262,144 | $0.6/1M | $3.6/1M |
|
DeepSeek V4.1 Flash 1017
thinkingmachines/deepseek-ai/DeepSeek-V4.1-Flash-1017:peft:262144
|
262,144 | $0.6/1M | $3.6/1M |
|
GLM-5.3
thinkingmachines/zai-org/GLM-5.3:peft:262144
|
262,144 | $3.78/1M | $12.15/1M |
|
GLM-5.3-Flash
thinkingmachines/zai-org/GLM-5.3-Flash:peft:262144
|
262,144 | $0.84/1M | $2.11/1M |
|
GPT OSS 120B
thinkingmachines/openai/gpt-oss-120b:peft:131072
|
131,072 | $0.33/1M | $0.84/1M |
|
GPT OSS 120B
thinkingmachines/openai/gpt-oss-120b
|
32,768 | $0.33/1M | $0.84/1M |
|
GPT OSS 20B
thinkingmachines/openai/gpt-oss-20b
|
32,768 | $0.18/1M | $0.45/1M |
|
Inkling
thinkingmachines/thinkingmachines/Inkling:peft:262144:sampling-nvfp4
|
262,144 | $1/1M | $4.05/1M |
|
Inkling
thinkingmachines/thinkingmachines/Inkling
|
65,536 | $1.87/1M | $4.68/1M |
|
Inkling (256K)
thinkingmachines/thinkingmachines/Inkling:peft:262144
|
262,144 | $1.87/1M | $4.68/1M |
|
Inkling Small
thinkingmachines/thinkingmachines/Inkling-Small
|
65,536 | $0.58/1M | $1.44/1M |
|
Inkling Small
thinkingmachines/thinkingmachines/Inkling-Small:peft:262144
|
262,144 | $0.58/1M | $1.44/1M |
|
Inkling Small
thinkingmachines/thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4
|
262,144 | $0.3/1M | $1.2/1M |
|
Kimi K2.6
thinkingmachines/moonshotai/Kimi-K2.6
|
32,768 | $2.205/1M | $5.49/1M |
|
Kimi K2.6
thinkingmachines/moonshotai/Kimi-K2.6:peft:131072
|
131,072 | $2.205/1M | $5.49/1M |
|
Nemotron 3.5 Lightning 30B A3B
thinkingmachines/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144
|
262,144 | $0.184/1M | $0.495/1M |
|
Nemotron 3.5 Lightning 30B A3B
thinkingmachines/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
|
65,536 | $0.184/1M | $0.495/1M |
|
Nemotron 3.5 Super VL 120B A12B
thinkingmachines/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16
|
65,536 | $0.57/1M | $1.44/1M |
|
Nemotron 3.5 Super VL 120B A12B
thinkingmachines/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:262144
|
262,144 | $0.57/1M | $1.44/1M |
|
Nemotron 3 Nano 30B A3B
thinkingmachines/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
|
65,536 | $0.195/1M | $0.495/1M |
|
Nemotron 3 Super 120B A12B
thinkingmachines/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144
|
262,144 | $0.57/1M | $1.44/1M |
|
Nemotron 3 Super 120B A12B
thinkingmachines/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
|
65,536 | $0.57/1M | $1.44/1M |
|
Nemotron 3 Ultra 550B A55B
thinkingmachines/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
|
65,536 | $1.8/1M | $6.225/1M |
|
Nemotron 3 Ultra 550B A55B
thinkingmachines/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144
|
262,144 | $1.8/1M | $6.225/1M |
|
Qwen3.5 35B-A3B Base
thinkingmachines/Qwen/Qwen3.5-35B-A3B-Base
|
65,536 | $0.54/1M | $1.335/1M |
|
Qwen3.5 397B-A17B
thinkingmachines/Qwen/Qwen3.5-397B-A17B:peft:262144
|
262,144 | $1.65/1M | $7.5/1M |
|
Qwen3.5 397B-A17B
thinkingmachines/Qwen/Qwen3.5-397B-A17B
|
65,536 | $1.65/1M | $7.5/1M |
|
Qwen3.5 4B
thinkingmachines/Qwen/Qwen3.5-4B
|
65,536 | $0.33/1M | $1.005/1M |
|
Qwen3.5 4B
thinkingmachines/Qwen/Qwen3.5-4B:peft:262144
|
262,144 | $0.33/1M | $1.005/1M |