Models & Pricing

All prices are per million tokens. Checkpoint storage is charged at $0.10 per GB per month.

We provide an 80% discount on cached prefill tokens.

Some models have a limited-time 50% discount: the struck-through price is the original, and the price next to it is what you pay.

All Types

All Types

Base

Reasoning

Hybrid

Vision

All Architectures

All Architectures

Dense

MoE

All Sizes

All Sizes

Compact

Small

Medium

Large

Model	Tinker ID	Context	PrefillCached: 80% discount	Sample	Train	Size	Arch	Type
InklingLimited-time 50% off	thinkingmachines/Inkling	64K	$3.74 $1.87$0.374 (cached)	$9.36 $4.68	$11.22 $5.61	Large	MoE	Hybrid + Audio + Vision
Inkling (256K)Limited-time 50% off	thinkingmachines/Inkling:peft:262144	256K	$7.48 $3.74$0.748 (cached)	$18.72 $9.36	$22.46 $11.23	Large	MoE	Hybrid + Audio + Vision
Nemotron-3-Ultra-550B-A55BLimited-time 50% off	nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16	64K	$4.98 $2.49$0.498 (cached)	$12.45 $6.225	$10.956 $5.478	Large	MoE	Hybrid
Nemotron-3-Ultra-550B-A55B (256K)Limited-time 50% off	nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144	256K	$6.64 $3.32$0.664 (cached)	$16.60 $8.30	$19.92 $9.96	Large	MoE	Hybrid
Nemotron-3-Super-120B-A12BLimited-time 50% off	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16	64K	$1.14 $0.57$0.114 (cached)	$2.88 $1.44	$2.552 $1.276	Large	MoE	Hybrid
Nemotron-3-Super-120B-A12B (256K)Limited-time 50% off	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144	256K	$1.52 $0.76$0.152 (cached)	$3.84 $1.92	$4.64 $2.32	Large	MoE	Hybrid
Nemotron-3-Nano-30B-A3BLimited-time 50% off	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	64K	$0.39 $0.195$0.039 (cached)	$0.99 $0.495	$0.88 $0.44	Medium	MoE	Hybrid
Kimi-K2.6	moonshotai/Kimi-K2.6	32K	$2.205$0.441 (cached)	$5.49	$4.84	Large	MoE	Hybrid + Vision
Kimi-K2.6 (128K)	moonshotai/Kimi-K2.6:peft:131072	128K	$5.15$1.03 (cached)	$12.81	$15.40	Large	MoE	Hybrid + Vision
Qwen3.6-35B-A3B	Qwen/Qwen3.6-35B-A3B	64K	$0.54$0.108 (cached)	$1.335	$1.177	Medium	MoE	Hybrid + Vision
Qwen3.6-27B	Qwen/Qwen3.6-27B	64K	$1.86$0.372 (cached)	$5.595	$4.103	Medium	Dense	Hybrid + Vision
Qwen3.5-397B-A17B	Qwen/Qwen3.5-397B-A17B	64K	$3.00$0.60 (cached)	$7.50	$6.60	Large	MoE	Hybrid + Vision
Qwen3.5-397B-A17B (256K)	Qwen/Qwen3.5-397B-A17B:peft:262144	256K	$4.00$0.80 (cached)	$10.00	$12.00	Large	MoE	Hybrid + Vision
Qwen3.5-35B-A3B-Base	Qwen/Qwen3.5-35B-A3B-Base	64K	$0.54$0.108 (cached)	$1.335	$1.177	Medium	MoE	Base
Qwen3.5-9B	Qwen/Qwen3.5-9B	64K	$0.66$0.132 (cached)	$1.995	$1.463	Small	Dense	Hybrid + Vision
Qwen3.5-9B-Base	Qwen/Qwen3.5-9B-Base	64K	$0.66$0.132 (cached)	$1.995	$1.463	Small	Dense	Base
Qwen3.5-4B	Qwen/Qwen3.5-4B	64K	$0.33$0.066 (cached)	$1.005	$0.737	Compact	Dense	Hybrid + Vision
Qwen3-8B	Qwen/Qwen3-8B	32K	$0.195$0.039 (cached)	$0.60	$0.44	Small	Dense	Hybrid
GPT-OSS-120B	openai/gpt-oss-120b	32K	$0.33$0.066 (cached)	$0.84	$0.737	Medium	MoE	Reasoning
GPT-OSS-120B (128K)	openai/gpt-oss-120b:peft:131072	128K	$0.78$0.156 (cached)	$1.94	$2.33	Medium	MoE	Reasoning
GPT-OSS-20B	openai/gpt-oss-20b	32K	$0.18$0.036 (cached)	$0.45	$0.396	Small	MoE	Reasoning
DeepSeek-V3.1	deepseek-ai/DeepSeek-V3.1	32K	$1.695$0.339 (cached)	$4.215	$3.718	Large	MoE	Hybrid

Pricing Terms

• Prefill: Processing input/prompt tokens (forward pass only)
• Cached prefill: The smaller price under each prefill price; applies to input tokens that hit the prompt cache (80% off)
• 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.

Model Types

• Base: Raw pretrained models with no chat or instruction tuning. Best for post-training research or running the full post-training pipeline yourself.
• Reasoning: Always produce chain-of-thought before their answer. Highest intelligence, higher latency and token cost.
• Hybrid: Run in both thinking and non-thinking modes. They reason by default, but chain-of-thought can be disabled via a renderer or argument for faster, cheaper direct answers.
• Vision: Vision-language models that accept images alongside text. Shown as a + Vision suffix on the underlying type (for example, Hybrid + Vision).
• Audio: Models that accept audio alongside text. Shown as a + Audio suffix on the underlying type.

Architecture is either Dense (all parameters active per token) or MoE (mixture-of-experts, only a subset of parameters active per token). MoE models are highlighted in amber.

Choosing a Model

• Cost-effective: Use MoE models (highlighted in amber)
• Research/post-training: Use Base models
• Task-specific fine-tuning: Start with a Hybrid model
• Low latency: Use a Hybrid model with chain-of-thought disabled
• High intelligence: Use Reasoning or Hybrid models (chain-of-thought)
• Vision tasks: Use models with Vision in the type

Retired Models

These models have been retired and can no longer be used for training or inference, grouped by retirement date. See Model deprecations for the recommended replacement for each.

July 12, 2026

• Kimi: Kimi-K2.5

June 12, 2026

• Qwen: Qwen3-235B-A22B-Instruct-2507, Qwen3-VL-235B-A22B-Instruct, Qwen3.5-35B-A3B, Qwen3.5-27B, Qwen3-32B, Qwen3-30B-A3B, Qwen3-30B-A3B-Instruct-2507, Qwen3-VL-30B-A3B-Instruct, Qwen3-30B-A3B-Base, Qwen3-8B-Base, Qwen3-4B-Instruct-2507
• Llama: Llama-3.3-70B-Instruct, Llama-3.1-70B, Llama-3.1-8B, Llama-3.1-8B-Instruct, Llama-3.2-3B, Llama-3.2-1B
• DeepSeek: DeepSeek-V3.1-Base
• Kimi: Kimi-K2-Thinking