Thinking Machines is a first-party provider, serving models it develops itself. Its published rate is the reference other channels are measured against, and first-party hosting usually comes with the most predictable availability.
It lists 38 models on this page. Coverage spans text and chat (38). The lowest-priced model hosted here is GPT OSS 20B.
Thinking Machines is the lowest paid channel for 3 models that have at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| GPT OSS 20Bopenai/gpt-oss-20b13.8× pricier | $0.18 | $0.45 | $0.036 | 32,768 | 13.8× pricier |
| Nemotron 3.5 Lightning 30B A3Bnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:2621445.4× pricier | $0.18 | $0.50 | $0.037 | 262,144 | 5.4× pricier |
| Nemotron 3.5 Lightning 30B A3Bnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF165.4× pricier | $0.18 | $0.50 | $0.037 | 65,536 | 5.4× pricier |
| Nemotron 3 Nano 30B A3Bnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF163.1× pricier | $0.20 | $0.50 | $0.039 | 65,536 | 3.1× pricier |
| Qwen3 8BQwen/Qwen3-8B4.9× pricier | $0.20 | $0.60 | $0.039 | 32,768 | 4.9× pricier |
| Qwen3.5 9BQwen/Qwen3.5-9B4.3× pricier | $0.30 | $0.81 | $0.06 | 65,536 | 4.3× pricier |
| Qwen3.5 9B BaseQwen/Qwen3.5-9B-BaseOnly channel | $0.30 | $0.81 | $0.06 | 65,536 | Only channel |
| GPT OSS 120Bopenai/gpt-oss-120b:peft:1310727.9× pricier | $0.33 | $0.84 | $0.066 | 131,072 | 7.9× pricier |
| GPT OSS 120Bopenai/gpt-oss-120b7.9× pricier | $0.33 | $0.84 | $0.066 | 32,768 | 7.9× pricier |
| Qwen3.5 4BQwen/Qwen3.5-4B:peft:26214410.5× pricier | $0.33 | $1.01 | $0.066 | 262,144 | 10.5× pricier |
| Qwen3.5 4BQwen/Qwen3.5-4B10.5× pricier | $0.33 | $1.01 | $0.066 | 65,536 | 10.5× pricier |
| Inkling Smallthinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4Lowest anywhere | $0.30 | $1.20 | $0.06 | 262,144 | Lowest anywhere |
| Qwen3.6 35B-A3BQwen/Qwen3.6-35B-A3B6.2× pricier | $0.45 | $1.34 | $0.09 | 65,536 | 6.2× pricier |
| Qwen3.6 35B-A3BQwen/Qwen3.6-35B-A3B:peft:2621446.2× pricier | $0.45 | $1.34 | $0.09 | 262,144 | 6.2× pricier |
| Qwen3.5 35B-A3B BaseQwen/Qwen3.5-35B-A3B-BaseOnly channel | $0.54 | $1.34 | $0.11 | 65,536 | Only channel |
| Nemotron 3.5 Super VL 120B A12Bnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16:peft:2621445.9× pricier | $0.57 | $1.44 | $0.11 | 262,144 | 5.9× pricier |
| Nemotron 3.5 Super VL 120B A12Bnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF165.9× pricier | $0.57 | $1.44 | $0.11 | 65,536 | 5.9× pricier |
| Nemotron 3 Super 120B A12Bnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF167.9× pricier | $0.57 | $1.44 | $0.11 | 65,536 | 7.9× pricier |
| Nemotron 3 Super 120B A12Bnvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:2621447.9× pricier | $0.57 | $1.44 | $0.11 | 262,144 | 7.9× pricier |
| Inkling Smallthinkingmachines/Inkling-SmallLowest anywhere | $0.58 | $1.44 | $0.12 | 65,536 | Lowest anywhere |
| Inkling Smallthinkingmachines/Inkling-Small:peft:262144Lowest anywhere | $0.58 | $1.44 | $0.12 | 262,144 | Lowest anywhere |
| GLM-5.3-Flashzai-org/GLM-5.3-Flash:peft:26214423.4× pricier | $0.84 | $2.11 | $0.17 | 262,144 | 23.4× pricier |
| DeepSeek V4.1 Flash 1017deepseek-ai/DeepSeek-V4.1-Flash-1017:peft:26214425.7× pricier | $0.60 | $3.60 | $0.12 | 262,144 | 25.7× pricier |
| DeepSeek V4.1 Flashdeepseek-ai/DeepSeek-V4.1-Flash:peft:26214425.7× pricier | $0.60 | $3.60 | $0.12 | 262,144 | 25.7× pricier |
| Inklingthinkingmachines/Inkling:peft:262144:sampling-nvfp41.0× pricier | $1.00 | $4.05 | $0.17 | 262,144 | 1.0× pricier |
| Qwen3.8 27BQwen/Qwen3.8-27B:peft:26214416.9× pricier | $0.70 | $5.60 | $0.14 | 262,144 | 16.9× pricier |
| Qwen3.8 27BQwen/Qwen3.8-27B16.9× pricier | $0.70 | $5.60 | $0.14 | 65,536 | 16.9× pricier |
| DeepSeek-V3.1deepseek-ai/DeepSeek-V3.17.3× pricier | $1.70 | $4.22 | $0.34 | 32,768 | 7.3× pricier |
| Inklingthinkingmachines/Inkling1.5× pricier | $1.87 | $4.68 | $0.37 | 65,536 | 1.5× pricier |
| Inklingthinkingmachines/Inkling:peft:2621441.5× pricier | $1.87 | $4.68 | $0.37 | 262,144 | 1.5× pricier |
| Qwen3.6 27BQwen/Qwen3.6-27B7.8× pricier | $1.86 | $5.60 | $0.37 | 65,536 | 7.8× pricier |
| Nemotron 3 Ultra 550B A55Bnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF1629.1× pricier | $1.80 | $6.23 | $0.36 | 65,536 | 29.1× pricier |
| Nemotron 3 Ultra 550B A55Bnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:26214429.1× pricier | $1.80 | $6.23 | $0.36 | 262,144 | 29.1× pricier |
| Kimi K2.6moonshotai/Kimi-K2.69.7× pricier | $2.21 | $5.49 | $0.44 | 32,768 | 9.7× pricier |
| Kimi K2.6moonshotai/Kimi-K2.6:peft:1310729.7× pricier | $2.21 | $5.49 | $0.44 | 131,072 | 9.7× pricier |
| Qwen3.5 397B-A17BQwen/Qwen3.5-397B-A17B:peft:2621448.4× pricier | $1.65 | $7.50 | $0.33 | 262,144 | 8.4× pricier |
| Qwen3.5 397B-A17BQwen/Qwen3.5-397B-A17B8.4× pricier | $1.65 | $7.50 | $0.33 | 65,536 | 8.4× pricier |
| GLM-5.3zai-org/GLM-5.3:peft:26214417.1× pricier | $3.78 | $12.15 | $0.76 | 262,144 | 17.1× pricier |