Models & Pricing

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

Training

We provide an 80% discount on cached prefill tokens.

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	Size	Arch	Type	PrefillCached: 80% discount	Sample	Train
InklingLimited-time 50% discount	thinkingmachines/Inkling	64K	Large	MoE	Hybrid + Audio + Vision	$3.74 $1.87$0.374 (cached)	$9.36 $4.68	$11.22 $5.61
Inkling (256K)Limited-time 50% discount	thinkingmachines/Inkling:peft:262144	256K	Large	MoE	Hybrid + Audio + Vision	$7.48 $3.74$0.748 (cached)	$18.72 $9.36	$22.46 $11.23
Inkling-SmallLimited-time 50% discount	thinkingmachines/Inkling-Small	64K	Large	MoE	Hybrid + Audio + Vision	$1.16 $0.58$0.116 (cached)	$2.88 $1.44	$3.46 $1.73
Inkling-Small (256K)Limited-time 50% discount	thinkingmachines/Inkling-Small:peft:262144	256K	Large	MoE	Hybrid + Audio + Vision	$2.32 $1.16$0.232 (cached)	$5.78 $2.89	$6.94 $3.47
Nemotron-3.5-Lightning-30B-A3BLimited-time 50% discount	nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16	64K	Medium	MoE	Hybrid	$0.39 $0.195$0.039 (cached)	$0.99 $0.495	$0.88 $0.44
Nemotron-3.5-Lightning-30B-A3B (256K)Limited-time 50% discount	nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16:peft:262144	256K	Medium	MoE	Hybrid	$0.52 $0.26$0.052 (cached)	$1.32 $0.66	$1.60 $0.80
Nemotron-3-Ultra-550B-A55BLimited-time 50% discount	nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16	64K	Large	MoE	Hybrid	$4.98 $2.49$0.498 (cached)	$12.45 $6.225	$10.956 $5.478
Nemotron-3-Ultra-550B-A55B (256K)Limited-time 50% discount	nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16:peft:262144	256K	Large	MoE	Hybrid	$6.64 $3.32$0.664 (cached)	$16.60 $8.30	$19.92 $9.96
Nemotron-3-Super-120B-A12BLimited-time 50% discount	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16	64K	Large	MoE	Hybrid	$1.14 $0.57$0.114 (cached)	$2.88 $1.44	$2.552 $1.276
Nemotron-3-Super-120B-A12B (256K)Limited-time 50% discount	nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16:peft:262144	256K	Large	MoE	Hybrid	$1.52 $0.76$0.152 (cached)	$3.84 $1.92	$4.64 $2.32
Nemotron-3-Nano-30B-A3BLimited-time 50% discount	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16	64K	Medium	MoE	Hybrid	$0.39 $0.195$0.039 (cached)	$0.99 $0.495	$0.88 $0.44
Kimi-K2.6	moonshotai/Kimi-K2.6	32K	Large	MoE	Hybrid + Vision	$2.205$0.441 (cached)	$5.49	$4.84
Kimi-K2.6 (128K)	moonshotai/Kimi-K2.6:peft:131072	128K	Large	MoE	Hybrid + Vision	$5.15$1.03 (cached)	$12.81	$15.40
Qwen3.6-35B-A3B	Qwen/Qwen3.6-35B-A3B	64K	Medium	MoE	Hybrid + Vision	$0.54$0.108 (cached)	$1.335	$1.177
Qwen3.6-27B	Qwen/Qwen3.6-27B	64K	Medium	Dense	Hybrid + Vision	$1.86$0.372 (cached)	$5.595	$4.103
Qwen3.5-397B-A17B	Qwen/Qwen3.5-397B-A17B	64K	Large	MoE	Hybrid + Vision	$3.00$0.60 (cached)	$7.50	$6.60
Qwen3.5-397B-A17B (256K)	Qwen/Qwen3.5-397B-A17B:peft:262144	256K	Large	MoE	Hybrid + Vision	$4.00$0.80 (cached)	$10.00	$12.00
Qwen3.5-35B-A3B-Base	Qwen/Qwen3.5-35B-A3B-Base	64K	Medium	MoE	Base	$0.54$0.108 (cached)	$1.335	$1.177
Qwen3.5-9B	Qwen/Qwen3.5-9B	64K	Small	Dense	Hybrid + Vision	$0.66$0.132 (cached)	$1.995	$1.463
Qwen3.5-9B-Base	Qwen/Qwen3.5-9B-Base	64K	Small	Dense	Base	$0.66$0.132 (cached)	$1.995	$1.463
Qwen3.5-4B	Qwen/Qwen3.5-4B	64K	Compact	Dense	Hybrid + Vision	$0.33$0.066 (cached)	$1.005	$0.737
Qwen3-8B	Qwen/Qwen3-8B	32K	Small	Dense	Hybrid	$0.195$0.039 (cached)	$0.60	$0.44
GPT-OSS-120B	openai/gpt-oss-120b	32K	Medium	MoE	Reasoning	$0.33$0.066 (cached)	$0.84	$0.737
GPT-OSS-120B (128K)	openai/gpt-oss-120b:peft:131072	128K	Medium	MoE	Reasoning	$0.78$0.156 (cached)	$1.94	$2.33
GPT-OSS-20B	openai/gpt-oss-20b	32K	Small	MoE	Reasoning	$0.18$0.036 (cached)	$0.45	$0.396
DeepSeek-V3.1	deepseek-ai/DeepSeek-V3.1	32K	Large	MoE	Hybrid	$1.695$0.339 (cached)	$4.215	$3.718

Serverless Inference (Beta)

Serverless inference is currently in beta and available for Inkling and Inkling-Small only. We do not recommend it for intensive production use until it is out of beta. If you're interested in production use, email us at [email protected] to join the waitlist. Please include which models you need, your expected volume and latency requirements, and your use case.

Model	Tinker ID	Context	Prefill (Input)	Sample (Output)
Inkling-Small	thinkingmachines/Inkling-Small:peft:262144:sampling-nvfp4	256K	$0.30$0.06 (cached)	$1.20
Inkling	thinkingmachines/Inkling:peft:262144:sampling-nvfp4	256K	$1.00$0.17 (cached)	$4.05

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

Machine-Readable Pricing

If you want to use this data programmatically (cost estimation, model pickers, dashboards), don't scrape the tables above. The data behind them is published as JSON alongside this page, and those files are the stable interface for scripts (the tables' HTML is presentational and may change):

• models.json: the Training table. One object per model with name, tinker_id, context, size, arch, type, url, and per-million-token prices prefill, cached_prefill, sample, train (strings like "$0.374"). Temporarily discounted models also carry original_* price fields and a note.
• serverless.json: the Serverless Inference table, with name, tinker_id, context, url, input, cached_input, output.

For example:

import json, urllib.request

url = "https://tinker-docs.thinkingmachines.ai/tinker/models.json"
models = json.load(urllib.request.urlopen(url))
for m in models:
    print(m["tinker_id"], m["train"])

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