281.4K npm downloads last month

Does it fit? What will it cost?

Typed model metadata and cost helpers for LLM applications. Simple, minimal, and accurate token counting for 50+ AI models.

Trusted by builders at

Vercel
Midday
Mastra

50+ AI Models Supported

Accurate token counting for all major language models. Search, filter, and explore.

Model data sourced from public directories (OpenRouter, models.dev). While we strive for accuracy, we cannot guarantee 100% correctness.
Last updated at Nov 5, 2025, 01:00 AM

Models

a
agentica-org(2 models)

Agentica: Deepcoder 14B Preview (free)

Context96k
Free

Agentica: Deepcoder 14B Preview

Context96k
Input$0.01/1M
Output$0.01/1M
Low Cost

a
ai21(2 models)

AI21: Jamba Mini 1.7

Context256k
Input$0.20/1M
Output$0.40/1M
Low Cost

AI21: Jamba Large 1.7

Context256k
Input$2.00/1M
Output$8.00/1M
Mid Tier

a
aion-labs(3 models)

AionLabs: Aion-1.0

Context131k
Input$4.00/1M
Output$8.00/1M
Premium

AionLabs: Aion-1.0-Mini

Context131k
Input$0.70/1M
Output$1.40/1M
Mid Tier

AionLabs: Aion-RP 1.0 (8B)

Context33k
Input$0.20/1M
Output$0.20/1M
Low Cost

a
alfredpros(1 model)

AlfredPros: CodeLLaMa 7B Instruct Solidity

Context4k
Input$0.80/1M
Output$1.20/1M
Mid Tier

a
alibaba(2 models)

Tongyi DeepResearch 30B A3B (free)

Context131k
Free

Tongyi DeepResearch 30B A3B

Context131k
Input$0.09/1M
Output$0.40/1M
Low Cost

a
allenai(1 model)

AllenAI: Olmo 2 32B Instruct

Context4k
Input$0.20/1M
Output$0.35/1M
Low Cost

a
alpindale(1 model)

Goliath 120B

Context6k
Input$4.00/1M
Output$5.50/1M
Premium

a
amazon(4 models)

Amazon: Nova Premier 1.0

Context1000k
Input$2.50/1M
Output$12.50/1M
Mid Tier

Amazon: Nova Lite 1.0

Context300k
Input$0.06/1M
Output$0.24/1M
Low Cost

Amazon: Nova Micro 1.0

Context128k
Input$0.04/1M
Output$0.14/1M
Low Cost

Amazon: Nova Pro 1.0

Context300k
Input$0.80/1M
Output$3.20/1M
Mid Tier

a
anthracite-org(1 model)

Magnum v4 72B

Context16k
Input$3.00/1M
Output$5.00/1M
Premium

a
anthropic(13 models)

Anthropic: Claude Haiku 4.5

Context200k
Input$1.00/1M
Output$5.00/1M
Mid Tier

Anthropic: Claude Sonnet 4.5

Context1000k
Input$3.00/1M
Output$15.00/1M
Premium

Anthropic: Claude Opus 4.1

Context200k
Input$15.00/1M
Output$75.00/1M
Premium

Anthropic: Claude Opus 4

Context200k
Input$15.00/1M
Output$75.00/1M
Premium

Anthropic: Claude Sonnet 4

Context1000k
Input$3.00/1M
Output$15.00/1M
Premium

Anthropic: Claude 3.7 Sonnet (thinking)

Context200k
Input$3.00/1M
Output$15.00/1M
Premium

Anthropic: Claude 3.7 Sonnet

Context200k
Input$3.00/1M
Output$15.00/1M
Premium

Anthropic: Claude 3.5 Haiku

Context200k
Input$0.80/1M
Output$4.00/1M
Mid Tier

Anthropic: Claude 3.5 Haiku (2024-10-22)

Context200k
Input$0.80/1M
Output$4.00/1M
Mid Tier

Anthropic: Claude 3.5 Sonnet

Context200k
Input$3.00/1M
Output$15.00/1M
Premium

Anthropic: Claude 3.5 Sonnet (2024-06-20)

Context200k
Input$3.00/1M
Output$15.00/1M
Premium

Anthropic: Claude 3 Haiku

Context200k
Input$0.25/1M
Output$1.25/1M
Low Cost

Anthropic: Claude 3 Opus

Context200k
Input$15.00/1M
Output$75.00/1M
Premium

a
arcee-ai(5 models)

Arcee AI: AFM 4.5B

Context66k
Input$0.05/1M
Output$0.15/1M
Low Cost

Arcee AI: Spotlight

Context131k
Input$0.18/1M
Output$0.18/1M
Low Cost

Arcee AI: Maestro Reasoning

Context131k
Input$0.90/1M
Output$3.30/1M
Mid Tier

Arcee AI: Virtuoso Large

Context131k
Input$0.75/1M
Output$1.20/1M
Mid Tier

Arcee AI: Coder Large

Context33k
Input$0.50/1M
Output$0.80/1M
Mid Tier

a
arliai(2 models)

ArliAI: QwQ 32B RpR v1 (free)

Context33k
Free

ArliAI: QwQ 32B RpR v1

Context33k
Input$0.03/1M
Output$0.11/1M
Low Cost

b
baidu(5 models)

Baidu: ERNIE 4.5 21B A3B Thinking

Context131k
Input$0.07/1M
Output$0.28/1M
Low Cost

Baidu: ERNIE 4.5 21B A3B

Context120k
Input$0.07/1M
Output$0.28/1M
Low Cost

Baidu: ERNIE 4.5 VL 28B A3B

Context30k
Input$0.14/1M
Output$0.56/1M
Low Cost

Baidu: ERNIE 4.5 VL 424B A47B

Context123k
Input$0.42/1M
Output$1.25/1M
Low Cost

Baidu: ERNIE 4.5 300B A47B

Context123k
Input$0.28/1M
Output$1.10/1M
Low Cost

b
bytedance(1 model)

ByteDance: UI-TARS 7B

Context128k
Input$0.10/1M
Output$0.20/1M
Low Cost

c
cognitivecomputations(1 model)

Venice: Uncensored (free)

Context33k
Free

c
cohere(4 models)

Cohere: Command A

Context256k
Input$2.50/1M
Output$10.00/1M
Mid Tier

Cohere: Command R7B (12-2024)

Context128k
Input$0.04/1M
Output$0.15/1M
Low Cost

Cohere: Command R+ (08-2024)

Context128k
Input$2.50/1M
Output$10.00/1M
Mid Tier

Cohere: Command R (08-2024)

Context128k
Input$0.15/1M
Output$0.60/1M
Low Cost

d
deepcogito(4 models)

Deep Cogito: Cogito V2 Preview Llama 405B

Context33k
Input$3.50/1M
Output$3.50/1M
Premium

Deep Cogito: Cogito V2 Preview Llama 70B

Context33k
Input$0.88/1M
Output$0.88/1M
Mid Tier

Cogito V2 Preview Llama 109B

Context33k
Input$0.18/1M
Output$0.59/1M
Low Cost

Deep Cogito: Cogito V2 Preview Deepseek 671B

Context164k
Input$1.25/1M
Output$1.25/1M
Mid Tier

d
deepseek(19 models)

DeepSeek: DeepSeek V3.2 Exp

Context164k
Input$0.27/1M
Output$0.40/1M
Low Cost

DeepSeek: DeepSeek V3.1 Terminus

Context164k
Input$0.23/1M
Output$0.90/1M
Low Cost

DeepSeek: DeepSeek V3.1 Terminus (exacto)

Context131k
Input$0.27/1M
Output$1.00/1M
Low Cost

DeepSeek: DeepSeek V3.1 (free)

Context164k
Free

DeepSeek: DeepSeek V3.1

Context164k
Input$0.20/1M
Output$0.80/1M
Low Cost

DeepSeek: DeepSeek R1 0528 Qwen3 8B (free)

Context131k
Free

DeepSeek: DeepSeek R1 0528 Qwen3 8B

Context33k
Input$0.03/1M
Output$0.11/1M
Low Cost

DeepSeek: R1 0528 (free)

Context164k
Free

DeepSeek: R1 0528

Context164k
Input$0.40/1M
Output$1.75/1M
Low Cost

DeepSeek: DeepSeek Prover V2

Context164k
Input$0.50/1M
Output$2.18/1M
Mid Tier

DeepSeek: DeepSeek V3 0324 (free)

Context164k
Free

DeepSeek: DeepSeek V3 0324

Context164k
Input$0.24/1M
Output$0.84/1M
Low Cost

DeepSeek: R1 Distill Qwen 32B

Context131k
Input$0.27/1M
Output$0.27/1M
Low Cost

DeepSeek: R1 Distill Qwen 14B

Context33k
Input$0.15/1M
Output$0.15/1M
Low Cost

DeepSeek: R1 Distill Llama 70B (free)

Context8k
Free

DeepSeek: R1 Distill Llama 70B

Context131k
Input$0.03/1M
Output$0.13/1M
Low Cost

DeepSeek: R1 (free)

Context164k
Free

DeepSeek: R1

Context164k
Input$0.30/1M
Output$1.20/1M
Low Cost

DeepSeek: DeepSeek V3

Context164k
Input$0.30/1M
Output$0.85/1M
Low Cost

e
eleutherai(1 model)

EleutherAI: Llemma 7b

Context4k
Input$0.80/1M
Output$1.20/1M
Mid Tier

g
google(24 models)

Google: Gemini 2.5 Flash Image (Nano Banana)

Context33k
Input$0.30/1M
Output$2.50/1M
Low Cost

Google: Gemini 2.5 Flash Preview 09-2025

Context1049k
Input$0.30/1M
Output$2.50/1M
Low Cost

Google: Gemini 2.5 Flash Lite Preview 09-2025

Context1049k
Input$0.10/1M
Output$0.40/1M
Low Cost

Google: Gemini 2.5 Flash Image Preview (Nano Banana)

Context33k
Input$0.30/1M
Output$2.50/1M
Low Cost

Google: Gemini 2.5 Flash Lite

Context1049k
Input$0.10/1M
Output$0.40/1M
Low Cost

Google: Gemma 3n 2B (free)

Context8k
Free

Google: Gemini 2.5 Flash Lite Preview 06-17

Context1049k
Input$0.10/1M
Output$0.40/1M
Low Cost

Google: Gemini 2.5 Flash

Context1049k
Input$0.30/1M
Output$2.50/1M
Low Cost

Google: Gemini 2.5 Pro

Context1049k
Input$1.25/1M
Output$10.00/1M
Mid Tier

Google: Gemini 2.5 Pro Preview 06-05

Context1049k
Input$1.25/1M
Output$10.00/1M
Mid Tier

Google: Gemma 3n 4B (free)

Context8k
Free

Google: Gemma 3n 4B

Context33k
Input$0.02/1M
Output$0.04/1M
Low Cost

Google: Gemini 2.5 Pro Preview 05-06

Context1049k
Input$1.25/1M
Output$10.00/1M
Mid Tier

Google: Gemma 3 4B (free)

Context33k
Free

Google: Gemma 3 4B

Context96k
Input$0.02/1M
Output$0.07/1M
Low Cost

Google: Gemma 3 12B (free)

Context33k
Free

Google: Gemma 3 12B

Context131k
Input$0.03/1M
Output$0.10/1M
Low Cost

Google: Gemma 3 27B (free)

Context131k
Free

Google: Gemma 3 27B

Context131k
Input$0.09/1M
Output$0.16/1M
Low Cost

Google: Gemini 2.0 Flash Lite

Context1049k
Input$0.07/1M
Output$0.30/1M
Low Cost

Google: Gemini 2.0 Flash

Context1049k
Input$0.10/1M
Output$0.40/1M
Low Cost

Google: Gemini 2.0 Flash Experimental (free)

Context1049k
Free

Google: Gemma 2 27B

Context8k
Input$0.65/1M
Output$0.65/1M
Mid Tier

Google: Gemma 2 9B

Context8k
Input$0.03/1M
Output$0.09/1M
Low Cost

g
gryphe(1 model)

MythoMax 13B

Context4k
Input$0.06/1M
Output$0.06/1M
Low Cost

i
ibm-granite(1 model)

IBM: Granite 4.0 Micro

Context131k
Input$0.02/1M
Output$0.11/1M
Low Cost

i
inception(2 models)

Inception: Mercury

Context128k
Input$0.25/1M
Output$1.00/1M
Low Cost

Inception: Mercury Coder

Context128k
Input$0.25/1M
Output$1.00/1M
Low Cost

i
inclusionai(2 models)

inclusionAI: Ring 1T

Context131k
Input$0.57/1M
Output$2.28/1M
Mid Tier

inclusionAI: Ling-1T

Context131k
Input$0.57/1M
Output$2.28/1M
Mid Tier

i
inflection(2 models)

Inflection: Inflection 3 Productivity

Context8k
Input$2.50/1M
Output$10.00/1M
Mid Tier

Inflection: Inflection 3 Pi

Context8k
Input$2.50/1M
Output$10.00/1M
Mid Tier

l
liquid(2 models)

LiquidAI/LFM2-8B-A1B

Context33k
Input$0.05/1M
Output$0.10/1M
Low Cost

LiquidAI/LFM2-2.6B

Context33k
Input$0.05/1M
Output$0.10/1M
Low Cost

m
mancer(1 model)

Mancer: Weaver (alpha)

Context8k
Input$1.13/1M
Output$1.13/1M
Mid Tier

m
meituan(2 models)

Meituan: LongCat Flash Chat (free)

Context131k
Free

Meituan: LongCat Flash Chat

Context131k
Input$0.15/1M
Output$0.75/1M
Low Cost

m
meta-llama(21 models)

Meta: Llama 3.3 8B Instruct (free)

Context128k
Free

Meta: Llama Guard 4 12B

Context164k
Input$0.18/1M
Output$0.18/1M
Low Cost

Meta: Llama 4 Maverick (free)

Context128k
Free

Meta: Llama 4 Maverick

Context1049k
Input$0.15/1M
Output$0.60/1M
Low Cost

Meta: Llama 4 Scout (free)

Context128k
Free

Meta: Llama 4 Scout

Context328k
Input$0.08/1M
Output$0.30/1M
Low Cost

Llama Guard 3 8B

Context131k
Input$0.02/1M
Output$0.06/1M
Low Cost

Meta: Llama 3.3 70B Instruct (free)

Context131k
Free

Meta: Llama 3.3 70B Instruct

Context131k
Input$0.13/1M
Output$0.38/1M
Low Cost

Meta: Llama 3.2 3B Instruct (free)

Context131k
Free

Meta: Llama 3.2 3B Instruct

Context16k
Input$0.02/1M
Output$0.02/1M
Low Cost

Meta: Llama 3.2 1B Instruct

Context131k
Input$0.01/1M
Output$0.01/1M
Low Cost

Meta: Llama 3.2 90B Vision Instruct

Context33k
Input$0.35/1M
Output$0.40/1M
Low Cost

Meta: Llama 3.2 11B Vision Instruct

Context131k
Input$0.05/1M
Output$0.05/1M
Low Cost

Meta: Llama 3.1 405B (base)

Context33k
Input$4.00/1M
Output$4.00/1M
Premium

Meta: Llama 3.1 8B Instruct

Context16k
Input$0.02/1M
Output$0.03/1M
Low Cost

Meta: Llama 3.1 405B Instruct

Context33k
Input$0.80/1M
Output$0.80/1M
Mid Tier

Meta: Llama 3.1 70B Instruct

Context131k
Input$0.40/1M
Output$0.40/1M
Low Cost

Meta: LlamaGuard 2 8B

Context8k
Input$0.20/1M
Output$0.20/1M
Low Cost

Meta: Llama 3 8B Instruct

Context8k
Input$0.03/1M
Output$0.06/1M
Low Cost

Meta: Llama 3 70B Instruct

Context8k
Input$0.30/1M
Output$0.40/1M
Low Cost

m
microsoft(9 models)

Microsoft: Phi 4 Reasoning Plus

Context33k
Input$0.07/1M
Output$0.35/1M
Low Cost

Microsoft: MAI DS R1 (free)

Context164k
Free

Microsoft: MAI DS R1

Context164k
Input$0.30/1M
Output$1.20/1M
Low Cost

Microsoft: Phi 4 Multimodal Instruct

Context131k
Input$0.05/1M
Output$0.10/1M
Low Cost

Microsoft: Phi 4

Context16k
Input$0.06/1M
Output$0.14/1M
Low Cost

Microsoft: Phi-3.5 Mini 128K Instruct

Context128k
Input$0.10/1M
Output$0.10/1M
Low Cost

Microsoft: Phi-3 Mini 128K Instruct

Context128k
Input$0.10/1M
Output$0.10/1M
Low Cost

Microsoft: Phi-3 Medium 128K Instruct

Context128k
Input$1.00/1M
Output$1.00/1M
Mid Tier

WizardLM-2 8x22B

Context66k
Input$0.48/1M
Output$0.48/1M
Low Cost

m
minimax(4 models)

MiniMax: MiniMax M2 (free)

Context131k
Free

MiniMax: MiniMax M2

Context197k
Input$0.15/1M
Output$0.45/1M
Low Cost

MiniMax: MiniMax M1

Context1000k
Input$0.40/1M
Output$2.20/1M
Low Cost

MiniMax: MiniMax-01

Context1000k
Input$0.20/1M
Output$1.10/1M
Low Cost

m
mistralai(36 models)

Mistral: Voxtral Small 24B 2507

Context32k
Input$0.10/1M
Output$0.30/1M
Low Cost

Mistral: Mistral Medium 3.1

Context131k
Input$0.40/1M
Output$2.00/1M
Low Cost

Mistral: Codestral 2508

Context256k
Input$0.30/1M
Output$0.90/1M
Low Cost

Mistral: Devstral Medium

Context131k
Input$0.40/1M
Output$2.00/1M
Low Cost

Mistral: Devstral Small 1.1

Context128k
Input$0.07/1M
Output$0.28/1M
Low Cost

Mistral: Mistral Small 3.2 24B (free)

Context131k
Free

Mistral: Mistral Small 3.2 24B

Context131k
Input$0.06/1M
Output$0.18/1M
Low Cost

Mistral: Magistral Small 2506

Context40k
Input$0.50/1M
Output$1.50/1M
Mid Tier

Mistral: Magistral Medium 2506 (thinking)

Context41k
Input$2.00/1M
Output$5.00/1M
Mid Tier

Mistral: Magistral Medium 2506

Context41k
Input$2.00/1M
Output$5.00/1M
Mid Tier

Mistral: Devstral Small 2505

Context128k
Input$0.06/1M
Output$0.12/1M
Low Cost

Mistral: Mistral Medium 3

Context131k
Input$0.40/1M
Output$2.00/1M
Low Cost

Mistral: Mistral Small 3.1 24B (free)

Context96k
Free

Mistral: Mistral Small 3.1 24B

Context128k
Input$0.05/1M
Output$0.10/1M
Low Cost

Mistral: Saba

Context33k
Input$0.20/1M
Output$0.60/1M
Low Cost

Mistral: Mistral Small 3 (free)

Context33k
Free

Mistral: Mistral Small 3

Context33k
Input$0.05/1M
Output$0.08/1M
Low Cost

Mistral: Codestral 2501

Context262k
Input$0.30/1M
Output$0.90/1M
Low Cost

Mistral Large 2411

Context131k
Input$2.00/1M
Output$6.00/1M
Mid Tier

Mistral Large 2407

Context131k
Input$2.00/1M
Output$6.00/1M
Mid Tier

Mistral: Pixtral Large 2411

Context131k
Input$2.00/1M
Output$6.00/1M
Mid Tier

Mistral: Ministral 8B

Context131k
Input$0.10/1M
Output$0.10/1M
Low Cost

Mistral: Ministral 3B

Context131k
Input$0.04/1M
Output$0.04/1M
Low Cost

Mistral: Pixtral 12B

Context33k
Input$0.10/1M
Output$0.10/1M
Low Cost

Mistral: Mistral Nemo (free)

Context131k
Free

Mistral: Mistral Nemo

Context131k
Input$0.02/1M
Output$0.04/1M
Low Cost

Mistral: Mistral 7B Instruct (free)

Context33k
Free

Mistral: Mistral 7B Instruct

Context33k
Input$0.03/1M
Output$0.05/1M
Low Cost

Mistral: Mistral 7B Instruct v0.3

Context33k
Input$0.03/1M
Output$0.05/1M
Low Cost

Mistral: Mixtral 8x22B Instruct

Context66k
Input$2.00/1M
Output$6.00/1M
Mid Tier

Mistral Large

Context128k
Input$2.00/1M
Output$6.00/1M
Mid Tier

Mistral Small

Context33k
Input$0.20/1M
Output$0.60/1M
Low Cost

Mistral Tiny

Context33k
Input$0.25/1M
Output$0.25/1M
Low Cost

Mistral: Mistral 7B Instruct v0.2

Context33k
Input$0.20/1M
Output$0.20/1M
Low Cost

Mistral: Mixtral 8x7B Instruct

Context33k
Input$0.54/1M
Output$0.54/1M
Mid Tier

Mistral: Mistral 7B Instruct v0.1

Context3k
Input$0.11/1M
Output$0.19/1M
Low Cost

m
moonshotai(5 models)

MoonshotAI: Kimi K2 0905

Context262k
Input$0.39/1M
Output$1.90/1M
Low Cost

MoonshotAI: Kimi K2 0905 (exacto)

Context262k
Input$0.60/1M
Output$2.50/1M
Mid Tier

MoonshotAI: Kimi K2 0711 (free)

Context33k
Free

MoonshotAI: Kimi K2 0711

Context63k
Input$0.14/1M
Output$2.49/1M
Low Cost

MoonshotAI: Kimi Dev 72B

Context131k
Input$0.29/1M
Output$1.15/1M
Low Cost

m
morph(2 models)

Morph: Morph V3 Large

Context262k
Input$0.90/1M
Output$1.90/1M
Mid Tier

Morph: Morph V3 Fast

Context82k
Input$0.80/1M
Output$1.20/1M
Mid Tier

n
neversleep(2 models)

NeverSleep: Lumimaid v0.2 8B

Context33k
Input$0.09/1M
Output$0.60/1M
Low Cost

Noromaid 20B

Context4k
Input$1.00/1M
Output$1.75/1M
Mid Tier

n
nousresearch(7 models)

Nous: Hermes 4 70B

Context131k
Input$0.11/1M
Output$0.38/1M
Low Cost

Nous: Hermes 4 405B

Context131k
Input$0.30/1M
Output$1.20/1M
Low Cost

Nous: DeepHermes 3 Mistral 24B Preview

Context33k
Input$0.15/1M
Output$0.59/1M
Low Cost

Nous: Hermes 3 70B Instruct

Context66k
Input$0.30/1M
Output$0.30/1M
Low Cost

Nous: Hermes 3 405B Instruct (free)

Context131k
Free

Nous: Hermes 3 405B Instruct

Context131k
Input$1.00/1M
Output$1.00/1M
Mid Tier

NousResearch: Hermes 2 Pro - Llama-3 8B

Context33k
Input$0.02/1M
Output$0.08/1M
Low Cost

n
nvidia(7 models)

NVIDIA: Nemotron Nano 12B 2 VL (free)

Context128k
Free

NVIDIA: Nemotron Nano 12B 2 VL

Context131k
Input$0.20/1M
Output$0.60/1M
Low Cost

NVIDIA: Llama 3.3 Nemotron Super 49B V1.5

Context131k
Input$0.10/1M
Output$0.40/1M
Low Cost

NVIDIA: Nemotron Nano 9B V2 (free)

Context128k
Free

NVIDIA: Nemotron Nano 9B V2

Context131k
Input$0.04/1M
Output$0.16/1M
Low Cost

NVIDIA: Llama 3.1 Nemotron Ultra 253B v1

Context131k
Input$0.60/1M
Output$1.80/1M
Mid Tier

NVIDIA: Llama 3.1 Nemotron 70B Instruct

Context131k
Input$0.60/1M
Output$0.60/1M
Mid Tier

o
openai(47 models)

OpenAI: gpt-oss-safeguard-20b

Context131k
Input$0.07/1M
Output$0.30/1M
Low Cost

OpenAI: GPT-5 Image Mini

Context400k
Input$2.50/1M
Output$2.00/1M
Mid Tier

OpenAI: GPT-5 Image

Context400k
Input$10.00/1M
Output$10.00/1M
Premium

OpenAI: o3 Deep Research

Context200k
Input$10.00/1M
Output$40.00/1M
Premium

OpenAI: o4 Mini Deep Research

Context200k
Input$2.00/1M
Output$8.00/1M
Mid Tier

OpenAI: GPT-5 Pro

Context400k
Input$15.00/1M
Output$120.00/1M
Premium

OpenAI: GPT-5 Codex

Context400k
Input$1.25/1M
Output$10.00/1M
Mid Tier

OpenAI: GPT-4o Audio

Context128k
Input$2.50/1M
Output$10.00/1M
Mid Tier

OpenAI: GPT-5 Chat

Context128k
Input$1.25/1M
Output$10.00/1M
Mid Tier

OpenAI: GPT-5

Context400k
Input$1.25/1M
Output$10.00/1M
Mid Tier

OpenAI: GPT-5 Mini

Context400k
Input$0.25/1M
Output$2.00/1M
Low Cost

OpenAI: GPT-5 Nano

Context400k
Input$0.05/1M
Output$0.40/1M
Low Cost

OpenAI: gpt-oss-120b

Context131k
Input$0.04/1M
Output$0.40/1M
Low Cost

OpenAI: gpt-oss-120b (exacto)

Context131k
Input$0.05/1M
Output$0.24/1M
Low Cost

OpenAI: gpt-oss-20b (free)

Context131k
Free

OpenAI: gpt-oss-20b

Context131k
Input$0.03/1M
Output$0.14/1M
Low Cost

OpenAI: o3 Pro

Context200k
Input$20.00/1M
Output$80.00/1M
Premium

OpenAI: Codex Mini

Context200k
Input$1.50/1M
Output$6.00/1M
Mid Tier

OpenAI: o4 Mini High

Context200k
Input$1.10/1M
Output$4.40/1M
Mid Tier

OpenAI: o3

Context200k
Input$2.00/1M
Output$8.00/1M
Mid Tier

OpenAI: o4 Mini

Context200k
Input$1.10/1M
Output$4.40/1M
Mid Tier

OpenAI: GPT-4.1

Context1048k
Input$2.00/1M
Output$8.00/1M
Mid Tier

OpenAI: GPT-4.1 Mini

Context1048k
Input$0.40/1M
Output$1.60/1M
Low Cost

OpenAI: GPT-4.1 Nano

Context1048k
Input$0.10/1M
Output$0.40/1M
Low Cost

OpenAI: o1-pro

Context200k
Input$150.00/1M
Output$600.00/1M
Premium

OpenAI: GPT-4o-mini Search Preview

Context128k
Input$0.15/1M
Output$0.60/1M
Low Cost

OpenAI: GPT-4o Search Preview

Context128k
Input$2.50/1M
Output$10.00/1M
Mid Tier

OpenAI: o3 Mini High

Context200k
Input$1.10/1M
Output$4.40/1M
Mid Tier

OpenAI: o3 Mini

Context200k
Input$1.10/1M
Output$4.40/1M
Mid Tier

OpenAI: o1

Context200k
Input$15.00/1M
Output$60.00/1M
Premium

OpenAI: GPT-4o (2024-11-20)

Context128k
Input$2.50/1M
Output$10.00/1M
Mid Tier

OpenAI: ChatGPT-4o

Context128k
Input$5.00/1M
Output$15.00/1M
Premium

OpenAI: GPT-4o (2024-08-06)

Context128k
Input$2.50/1M
Output$10.00/1M
Mid Tier

OpenAI: GPT-4o-mini

Context128k
Input$0.15/1M
Output$0.60/1M
Low Cost

OpenAI: GPT-4o-mini (2024-07-18)

Context128k
Input$0.15/1M
Output$0.60/1M
Low Cost

OpenAI: GPT-4o

Context128k
Input$2.50/1M
Output$10.00/1M
Mid Tier

OpenAI: GPT-4o (extended)

Context128k
Input$6.00/1M
Output$18.00/1M
Premium

OpenAI: GPT-4o (2024-05-13)

Context128k
Input$5.00/1M
Output$15.00/1M
Premium

OpenAI: GPT-4 Turbo

Context128k
Input$10.00/1M
Output$30.00/1M
Premium

OpenAI: GPT-3.5 Turbo (older v0613)

Context4k
Input$1.00/1M
Output$2.00/1M
Mid Tier

OpenAI: GPT-4 Turbo Preview

Context128k
Input$10.00/1M
Output$30.00/1M
Premium

OpenAI: GPT-4 Turbo (older v1106)

Context128k
Input$10.00/1M
Output$30.00/1M
Premium

OpenAI: GPT-3.5 Turbo Instruct

Context4k
Input$1.50/1M
Output$2.00/1M
Mid Tier

OpenAI: GPT-3.5 Turbo 16k

Context16k
Input$3.00/1M
Output$4.00/1M
Premium

OpenAI: GPT-3.5 Turbo

Context16k
Input$0.50/1M
Output$1.50/1M
Mid Tier

OpenAI: GPT-4

Context8k
Input$30.00/1M
Output$60.00/1M
Premium

OpenAI: GPT-4 (older v0314)

Context8k
Input$30.00/1M
Output$60.00/1M
Premium

o
opengvlab(1 model)

OpenGVLab: InternVL3 78B

Context33k
Input$0.07/1M
Output$0.26/1M
Low Cost

o
openrouter(1 model)

Auto Router

Context2000k
Low Cost

p
perplexity(6 models)

Perplexity: Sonar Pro Search

Context200k
Input$3.00/1M
Output$15.00/1M
Premium

Perplexity: Sonar Reasoning Pro

Context128k
Input$2.00/1M
Output$8.00/1M
Mid Tier

Perplexity: Sonar Pro

Context200k
Input$3.00/1M
Output$15.00/1M
Premium

Perplexity: Sonar Deep Research

Context128k
Input$2.00/1M
Output$8.00/1M
Mid Tier

Perplexity: Sonar Reasoning

Context127k
Input$1.00/1M
Output$5.00/1M
Mid Tier

Perplexity: Sonar

Context127k
Input$1.00/1M
Output$1.00/1M
Mid Tier

q
qwen(47 models)

Qwen: Qwen3 VL 32B Instruct

Context262k
Input$0.35/1M
Output$1.10/1M
Low Cost

Qwen: Qwen3 VL 8B Thinking

Context256k
Input$0.18/1M
Output$2.10/1M
Low Cost

Qwen: Qwen3 VL 8B Instruct

Context131k
Input$0.08/1M
Output$0.50/1M
Low Cost

Qwen: Qwen3 VL 30B A3B Thinking

Context131k
Input$0.20/1M
Output$1.00/1M
Low Cost

Qwen: Qwen3 VL 30B A3B Instruct

Context262k
Input$0.15/1M
Output$0.60/1M
Low Cost

Qwen: Qwen3 VL 235B A22B Thinking

Context262k
Input$0.30/1M
Output$1.20/1M
Low Cost

Qwen: Qwen3 VL 235B A22B Instruct

Context262k
Input$0.22/1M
Output$0.88/1M
Low Cost

Qwen: Qwen3 Max

Context256k
Input$1.20/1M
Output$6.00/1M
Mid Tier

Qwen: Qwen3 Coder Plus

Context128k
Input$1.00/1M
Output$5.00/1M
Mid Tier

Qwen: Qwen3 Coder Flash

Context128k
Input$0.30/1M
Output$1.50/1M
Low Cost

Qwen: Qwen3 Next 80B A3B Thinking

Context262k
Input$0.15/1M
Output$1.20/1M
Low Cost

Qwen: Qwen3 Next 80B A3B Instruct

Context262k
Input$0.10/1M
Output$0.80/1M
Low Cost

Qwen: Qwen Plus 0728

Context1000k
Input$0.40/1M
Output$1.20/1M
Low Cost

Qwen: Qwen Plus 0728 (thinking)

Context1000k
Input$0.40/1M
Output$4.00/1M
Low Cost

Qwen: Qwen3 30B A3B Thinking 2507

Context262k
Input$0.09/1M
Output$0.30/1M
Low Cost

Qwen: Qwen3 Coder 30B A3B Instruct

Context262k
Input$0.06/1M
Output$0.25/1M
Low Cost

Qwen: Qwen3 30B A3B Instruct 2507

Context262k
Input$0.08/1M
Output$0.33/1M
Low Cost

Qwen: Qwen3 235B A22B Thinking 2507

Context262k
Input$0.11/1M
Output$0.60/1M
Low Cost

Qwen: Qwen3 Coder 480B A35B (free)

Context262k
Free

Qwen: Qwen3 Coder 480B A35B

Context262k
Input$0.22/1M
Output$0.95/1M
Low Cost

Qwen: Qwen3 Coder 480B A35B (exacto)

Context262k
Input$0.38/1M
Output$1.53/1M
Low Cost

Qwen: Qwen3 235B A22B Instruct 2507

Context262k
Input$0.08/1M
Output$0.55/1M
Low Cost

Qwen: Qwen3 4B (free)

Context41k
Free

Qwen: Qwen3 30B A3B (free)

Context41k
Free

Qwen: Qwen3 30B A3B

Context41k
Input$0.06/1M
Output$0.22/1M
Low Cost

Qwen: Qwen3 8B

Context128k
Input$0.04/1M
Output$0.14/1M
Low Cost

Qwen: Qwen3 14B (free)

Context41k
Free

Qwen: Qwen3 14B

Context41k
Input$0.05/1M
Output$0.22/1M
Low Cost

Qwen: Qwen3 32B

Context41k
Input$0.05/1M
Output$0.20/1M
Low Cost

Qwen: Qwen3 235B A22B (free)

Context41k
Free

Qwen: Qwen3 235B A22B

Context41k
Input$0.18/1M
Output$0.54/1M
Low Cost

Qwen: Qwen2.5 Coder 7B Instruct

Context33k
Input$0.03/1M
Output$0.09/1M
Low Cost

Qwen: Qwen2.5 VL 32B Instruct (free)

Context16k
Free

Qwen: Qwen2.5 VL 32B Instruct

Context16k
Input$0.05/1M
Output$0.22/1M
Low Cost

Qwen: QwQ 32B

Context33k
Input$0.15/1M
Output$0.40/1M
Low Cost

Qwen: Qwen VL Plus

Context8k
Input$0.21/1M
Output$0.63/1M
Low Cost

Qwen: Qwen VL Max

Context131k
Input$0.80/1M
Output$3.20/1M
Mid Tier

Qwen: Qwen-Turbo

Context1000k
Input$0.05/1M
Output$0.20/1M
Low Cost

Qwen: Qwen2.5 VL 72B Instruct

Context33k
Input$0.08/1M
Output$0.33/1M
Low Cost

Qwen: Qwen-Plus

Context131k
Input$0.40/1M
Output$1.20/1M
Low Cost

Qwen: Qwen-Max

Context33k
Input$1.60/1M
Output$6.40/1M
Mid Tier

Qwen2.5 Coder 32B Instruct (free)

Context33k
Free

Qwen2.5 Coder 32B Instruct

Context33k
Input$0.04/1M
Output$0.16/1M
Low Cost

Qwen: Qwen2.5 7B Instruct

Context33k
Input$0.04/1M
Output$0.10/1M
Low Cost

Qwen2.5 72B Instruct (free)

Context33k
Free

Qwen2.5 72B Instruct

Context33k
Input$0.07/1M
Output$0.26/1M
Low Cost

Qwen: Qwen2.5-VL 7B Instruct

Context33k
Input$0.20/1M
Output$0.20/1M
Low Cost

r
raifle(1 model)

SorcererLM 8x22B

Context16k
Input$4.50/1M
Output$4.50/1M
Premium

r
relace(1 model)

Relace: Relace Apply 3

Context256k
Input$0.85/1M
Output$1.25/1M
Mid Tier

s
sao10k(5 models)

Sao10K: Llama 3.1 70B Hanami x1

Context16k
Input$3.00/1M
Output$3.00/1M
Premium

Sao10K: Llama 3.3 Euryale 70B

Context131k
Input$0.65/1M
Output$0.75/1M
Mid Tier

Sao10K: Llama 3.1 Euryale 70B v2.2

Context33k
Input$0.65/1M
Output$0.75/1M
Mid Tier

Sao10K: Llama 3 8B Lunaris

Context8k
Input$0.04/1M
Output$0.05/1M
Low Cost

Sao10k: Llama 3 Euryale 70B v2.1

Context8k
Input$1.48/1M
Output$1.48/1M
Mid Tier

s
stepfun-ai(1 model)

StepFun: Step3

Context66k
Input$0.57/1M
Output$1.42/1M
Mid Tier

s
switchpoint(1 model)

Switchpoint Router

Context131k
Input$0.85/1M
Output$3.40/1M
Mid Tier

t
tencent(1 model)

Tencent: Hunyuan A13B Instruct

Context131k
Input$0.14/1M
Output$0.57/1M
Low Cost

t
thedrummer(5 models)

TheDrummer: Cydonia 24B V4.1

Context131k
Input$0.30/1M
Output$0.50/1M
Low Cost

TheDrummer: Anubis 70B V1.1

Context131k
Input$0.65/1M
Output$1.00/1M
Mid Tier

TheDrummer: Skyfall 36B V2

Context33k
Input$0.50/1M
Output$0.80/1M
Mid Tier

TheDrummer: UnslopNemo 12B

Context33k
Input$0.40/1M
Output$0.40/1M
Low Cost

TheDrummer: Rocinante 12B

Context33k
Input$0.17/1M
Output$0.43/1M
Low Cost

t
thudm(1 model)

THUDM: GLM 4.1V 9B Thinking

Context66k
Input$0.04/1M
Output$0.14/1M
Low Cost

t
tngtech(4 models)

TNG: DeepSeek R1T2 Chimera (free)

Context164k
Free

TNG: DeepSeek R1T2 Chimera

Context164k
Input$0.30/1M
Output$1.20/1M
Low Cost

TNG: DeepSeek R1T Chimera (free)

Context164k
Free

TNG: DeepSeek R1T Chimera

Context164k
Input$0.30/1M
Output$1.20/1M
Low Cost

u
undi95(1 model)

ReMM SLERP 13B

Context6k
Input$0.45/1M
Output$0.65/1M
Low Cost

x
x-ai(7 models)

xAI: Grok 4 Fast

Context2000k
Input$0.20/1M
Output$0.50/1M
Low Cost

xAI: Grok Code Fast 1

Context256k
Input$0.20/1M
Output$1.50/1M
Low Cost

xAI: Grok 4

Context256k
Input$3.00/1M
Output$15.00/1M
Premium

xAI: Grok 3 Mini

Context131k
Input$0.30/1M
Output$0.50/1M
Low Cost

xAI: Grok 3

Context131k
Input$3.00/1M
Output$15.00/1M
Premium

xAI: Grok 3 Mini Beta

Context131k
Input$0.30/1M
Output$0.50/1M
Low Cost

xAI: Grok 3 Beta

Context131k
Input$3.00/1M
Output$15.00/1M
Premium

z
z-ai(7 models)

Z.AI: GLM 4.6

Context203k
Input$0.40/1M
Output$1.75/1M
Low Cost

Z.AI: GLM 4.6 (exacto)

Context203k
Input$0.45/1M
Output$1.90/1M
Low Cost

Z.AI: GLM 4.5V

Context66k
Input$0.60/1M
Output$1.80/1M
Mid Tier

Z.AI: GLM 4.5

Context131k
Input$0.35/1M
Output$1.55/1M
Low Cost

Z.AI: GLM 4.5 Air (free)

Context131k
Free

Z.AI: GLM 4.5 Air

Context131k
Input$0.13/1M
Output$0.85/1M
Low Cost

Z.AI: GLM 4 32B

Context128k
Input$0.10/1M
Output$0.10/1M
Low Cost

Start counting tokens in seconds

Minimal API. Zero dependencies. Maximum accuracy. Join thousands of developers using tokenlens.