Models & Pricing

All prices are per million tokens.

All Types

Base

Instruction

Reasoning

Hybrid

Vision

All Architectures

Dense

MoE

All Sizes

Compact

Small

Medium

Large

Model	Tinker ID	Type	Arch	Size	Context	Prefill	Sample	Train
Nemotron-3-Nano-30B-A3B	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	Hybrid	MoE	Medium	64K	$0.13	$0.33	$0.40
Nemotron-3-Super-120B-A12B	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16	Hybrid	MoE	Large	64K	$0.38	$0.96	$1.16
Nemotron-3-Super-120B-A12B (256K)	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144	Hybrid	MoE	Large	256K	$0.76	$1.92	$2.32
Qwen3.5-397B-A17B	Qwen/Qwen3.5-397B-A17B	Hybrid + Vision	MoE	Large	64K	$2.00	$5.00	$6.00
Qwen3.5-397B-A17B (256K)	Qwen/Qwen3.5-397B-A17B:peft:262144	Hybrid + Vision	MoE	Large	256K	$4.00	$10.00	$12.00
Qwen3.5-35B-A3B	Qwen/Qwen3.5-35B-A3B	Hybrid + Vision	MoE	Medium	64K	$0.36	$0.89	$1.07
Qwen3.5-27B	Qwen/Qwen3.5-27B	Hybrid + Vision	Dense	Medium	64K	$1.24	$3.73	$3.73
Qwen3.5-4B	Qwen/Qwen3.5-4B	Hybrid + Vision	Dense	Compact	64K	$0.22	$0.67	$0.67
Qwen3-VL-235B-A22B-Instruct	Qwen/Qwen3-VL-235B-A22B-Instruct	Vision	MoE	Large	32K	$0.43	$1.07	$1.29
Qwen3-VL-30B-A3B-Instruct	Qwen/Qwen3-VL-30B-A3B-Instruct	Vision	MoE	Medium	32K	$0.12	$0.30	$0.36
Qwen3-235B-A22B-Instruct-2507	Qwen/Qwen3-235B-A22B-Instruct-2507	Instruction	MoE	Large	32K	$0.43	$1.07	$1.29
Qwen3-30B-A3B-Instruct-2507	Qwen/Qwen3-30B-A3B-Instruct-2507	Instruction	MoE	Medium	32K	$0.12	$0.30	$0.36
Qwen3-30B-A3B	Qwen/Qwen3-30B-A3B	Hybrid	MoE	Medium	32K	$0.12	$0.30	$0.36
Qwen3-30B-A3B-Base	Qwen/Qwen3-30B-A3B-Base	Base	MoE	Medium	32K	$0.12	$0.30	$0.36
Qwen3-32B	Qwen/Qwen3-32B	Hybrid	Dense	Medium	32K	$0.44	$1.33	$1.33
Qwen3-8B	Qwen/Qwen3-8B	Hybrid	Dense	Small	32K	$0.13	$0.40	$0.40
Qwen3-8B-Base	Qwen/Qwen3-8B-Base	Base	Dense	Small	32K	$0.13	$0.40	$0.40
Qwen3-4B-Instruct-2507	Qwen/Qwen3-4B-Instruct-2507	Instruction	Dense	Compact	32K	$0.07	$0.22	$0.22
GPT-OSS-120B	openai/gpt-oss-120b	Reasoning	MoE	Medium	32K	$1.59	$4.76	$5.72
GPT-OSS-120B (128K)	openai/gpt-oss-120b:peft:131072	Reasoning	MoE	Medium	128K	$3.18	$9.52	$11.44
GPT-OSS-20B	openai/gpt-oss-20b	Reasoning	MoE	Small	32K	$0.27	$0.80	$0.96
DeepSeek-V3.1	deepseek-ai/DeepSeek-V3.1	Hybrid	MoE	Large	64K	$0.68	$1.71	$2.06
DeepSeek-V3.1-Base	deepseek-ai/DeepSeek-V3.1-Base	Base	MoE	Large	64K	$0.68	$1.71	$2.06
Llama-3.1-70B	meta-llama/Llama-3.1-70B	Base	Dense	Large	32K	$1.51	$4.53	$4.53
Llama-3.3-70B-Instruct	meta-llama/Llama-3.3-70B-Instruct	Instruction	Dense	Large	32K	$1.51	$4.53	$4.53
Llama-3.1-8B	meta-llama/Llama-3.1-8B	Base	Dense	Small	32K	$0.13	$0.40	$0.40
Llama-3.1-8B-Instruct	meta-llama/Llama-3.1-8B-Instruct	Instruction	Dense	Small	32K	$0.13	$0.40	$0.40
Llama-3.2-3B	meta-llama/Llama-3.2-3B	Base	Dense	Compact	32K	$0.07	$0.20	$0.20
Llama-3.2-1B	meta-llama/Llama-3.2-1B	Base	Dense	Compact	32K	$0.04	$0.13	$0.13
Kimi-K2-Thinking	moonshotai/Kimi-K2-Thinking	Reasoning	MoE	Large	64K	$0.68	$1.71	$2.06
Kimi-K2.5	moonshotai/Kimi-K2.5	Reasoning + Vision	MoE	Large	32K	$0.68	$1.71	$2.06
Kimi-K2.5 (128K)	moonshotai/Kimi-K2.5:peft:131072	Reasoning + Vision	MoE	Large	128K	$1.36	$3.42	$4.12

Pricing Terms

Prefill: Processing input/prompt tokens (forward pass only)
Sample: Generating output tokens (forward pass + sampling)
Train: Forward and backward pass for gradient computation
Context: Maximum sequence length. Models with :peft: suffix support extended context at higher prices.
Tinker ID: The exact string to pass to create_lora_training_client(base_model=...) or create_sampling_client(base_model=...)

MoE models are priced by active parameters, making them significantly more cost-effective than dense models of similar quality.

Choosing a Model

Cost-effective: Use MoE models (highlighted in amber)
Research/post-training: Use Base models
Task-specific fine-tuning: Start with an Instruction or Hybrid model
Low latency: Use Instruction models (no chain-of-thought)
High intelligence: Use Reasoning or Hybrid models (chain-of-thought)
Vision tasks: Use models with Vision in the type

For the latest pricing, see the Tinker Console.