LLM API pricing

Compare per-token prices across LLM API providers.

3,516
Chat models
18
Providers
Free
Lowest input / 1M tokens
10.5M
Largest context

LLM market heatmap

3,582 models grouped by vendor — click a vendor, then a family to filter the catalog

DEAL% · listings-weighted · signed (− red / + green) · n=24/29

Models

293 models
ModelProvidersInput from / 1MOutput from / 1MContextCapabilities
DeepSeek: DeepSeek V3 03241$0.24/1M tokens$0.90/1M tokens
Anthropic: Claude 3 Haiku1$0.25/1M tokens$1.25/1M tokens
Arcee AI: Trinity Large Thinking1$0.25/1M tokens$0.80/1M tokens
ByteDance Seed: Seed 1.61$0.25/1M tokens$2.00/1M tokens
ByteDance Seed: Seed-2.0-Lite1$0.25/1M tokens$2.00/1M tokens
DeepSeek: DeepSeek V3.11$0.25/1M tokens$0.95/1M tokens
Google: Gemini 3.1 Flash Lite1$0.25/1M tokens$1.50/1M tokens
Google: Gemini 3.1 Flash Lite Preview1$0.25/1M tokens$1.50/1M tokens
Inception: Mercury 21$0.25/1M tokens$0.75/1M tokens
OpenAI: GPT-5 Mini1$0.25/1M tokens$2.00/1M tokens
OpenAI: GPT-5.1-Codex-Mini1$0.25/1M tokens$2.00/1M tokens
Z.ai: GLM 5.3 Flash1$0.25/1M tokens$0.83/1M tokens
DeepSeek: DeepSeek V31$0.26/1M tokens$1.03/1M tokens
MiniMax: MiniMax M21$0.26/1M tokens$1.02/1M tokens
Qwen: Qwen-Plus1$0.26/1M tokens$0.78/1M tokens
Qwen: Qwen Plus 07281$0.26/1M tokens$0.78/1M tokens
Qwen: Qwen3.5-122B-A10B1$0.26/1M tokens$2.08/1M tokens
Qwen: Qwen3.5 Plus 2026-02-151$0.26/1M tokens$1.56/1M tokens
DeepSeek: DeepSeek V3.1 Terminus1$0.27/1M tokens$1.00/1M tokens
DeepSeek: DeepSeek V3.2 Exp1$0.27/1M tokens$0.41/1M tokens
MiniMax: MiniMax M2.51$0.27/1M tokens$0.95/1M tokens
Amazon: Nova 2 Lite1$0.30/1M tokens$2.50/1M tokens
Google: Gemini 2.5 Flash1$0.30/1M tokens$2.50/1M tokens
Google: Gemini 3.5 Flash Lite1$0.30/1M tokens$2.50/1M tokens
Kwaipilot: KAT-Coder-Pro V21$0.30/1M tokens$1.20/1M tokens
Meituan: LongCat 2.01$0.30/1M tokens$1.20/1M tokens
Meta: Muse Glimmer 30B1$0.30/1M tokens$1.10/1M tokens
MiniMax: MiniMax M2.11$0.30/1M tokens$1.20/1M tokens
Mistral: Codestral 25081$0.30/1M tokens$0.90/1M tokens
Qwen: Qwen3.5 Plus 2026-04-201$0.30/1M tokens$1.80/1M tokens
Qwen: Qwen3.6 27B1$0.30/1M tokens$2.00/1M tokens
Xiaomi: MiMo-V2.5-Pro1$0.30/1M tokens$0.61/1M tokens
Z.ai: GLM 4.6V1$0.30/1M tokens$0.90/1M tokens
Qwen: Qwen3.7 Plus1$0.32/1M tokens$1.28/1M tokens
Qwen: Qwen3.6 Plus1$0.33/1M tokens$1.95/1M tokens
DeepSeek: DeepSeek V4 Flash1$0.36/1M tokens$1.09/1M tokens
Qwen2.5 72B Instruct1$0.36/1M tokens$0.40/1M tokens
Qwen: Qwen3.5 397B A17B1$0.39/1M tokens$2.34/1M tokens
Meta: Llama 3.1 70B Instruct1$0.40/1M tokens$0.40/1M tokens
MiniMax: MiniMax M11$0.40/1M tokens$2.20/1M tokens
Mistral: Devstral 2 25121$0.40/1M tokens$2.00/1M tokens
Mistral: Mistral Medium 31$0.40/1M tokens$2.00/1M tokens
Mistral: Mistral Medium 3.11$0.40/1M tokens$2.00/1M tokens
OpenAI: GPT-4.1 Mini1$0.40/1M tokens$1.60/1M tokens
Qwen: Qwen3 VL 235B A22B Thinking1$0.40/1M tokens$4.00/1M tokens
TheDrummer: UnslopNemo 12B1$0.40/1M tokens$0.40/1M tokens
Z.ai: GLM 4.71$0.40/1M tokens$1.75/1M tokens
Z.ai: GLM 4.61$0.43/1M tokens$1.75/1M tokens
MoonshotAI: Kimi K2.51$0.45/1M tokens$2.25/1M tokens
Qwen: Qwen3 235B A22B1$0.45/1M tokens$1.82/1M tokens
Thinking Machines: Inkling Small1$0.45/1M tokens$1.20/1M tokens
ByteDance Seed: Seed 2.1 Turbo1$0.50/1M tokens$2.50/1M tokens
ByteDance Seed: Seed-2.0-Code1$0.50/1M tokens$3.00/1M tokens
DeepSeek: R1 05281$0.50/1M tokens$2.15/1M tokens
Google: Gemini 3 Flash Preview1$0.50/1M tokens$3.00/1M tokens
Mistral: Mistral Large 3 25121$0.50/1M tokens$1.50/1M tokens
NVIDIA: Nemotron 3 Ultra1$0.50/1M tokens$2.20/1M tokens
OpenAI: GPT-3.5 Turbo1$0.50/1M tokens$1.50/1M tokens
MoonshotAI: Kimi K2 07111$0.57/1M tokens$2.30/1M tokens
DeepSeek: DeepSeek V4 Pro 08131$0.58/1M tokens$1.73/1M tokens
MoonshotAI: Kimi K2.61$0.58/1M tokens$2.44/1M tokens
MoonshotAI: Kimi K2 09051$0.60/1M tokens$2.50/1M tokens
MoonshotAI: Kimi K2 Thinking1$0.60/1M tokens$2.50/1M tokens
OpenAI: GPT Audio Mini1$0.60/1M tokens$2.40/1M tokens
Z.ai: GLM 4.51$0.60/1M tokens$2.20/1M tokens
Z.ai: GLM 4.5V1$0.60/1M tokens$1.80/1M tokens
Z.ai: GLM 51$0.60/1M tokens$1.92/1M tokens
DeepSeek: DeepSeek V4 Pro 04231$0.65/1M tokens$1.29/1M tokens
Qwen: Qwen3 Coder Plus1$0.65/1M tokens$3.25/1M tokens
MoonshotAI: Kimi K2.7 Code1$0.68/1M tokens$3.40/1M tokens
AionLabs: Aion-3.0-Mini1$0.70/1M tokens$1.40/1M tokens
DeepSeek: R11$0.70/1M tokens$2.50/1M tokens
Kwaipilot: KAT-Coder-Pro V2.51$0.74/1M tokens$2.96/1M tokens
Google: Gemini 3.6 Flash1$0.75/1M tokens$3.75/1M tokens
Google: Gemini 3.7 Flash1$0.75/1M tokens$3.75/1M tokens
Google: Gemini 3.8 Flash1$0.75/1M tokens$3.75/1M tokens
OpenAI: GPT-5.4 Mini1$0.75/1M tokens$4.50/1M tokens
Google: Gemini Flash Latest1$0.75/1M tokens$3.75/1M tokens
OpenAI: GPT Mini Latest1$0.75/1M tokens$4.50/1M tokens
Qwen: Qwen3 Max1$0.78/1M tokens$3.90/1M tokens
Qwen: Qwen3 Max Thinking1$0.78/1M tokens$3.90/1M tokens
AionLabs: Aion-2.01$0.80/1M tokens$1.60/1M tokens
Amazon: Nova Pro 1.01$0.80/1M tokens$3.20/1M tokens
Tencent: Hy4 preview1$0.83/1M tokens$2.50/1M tokens
Sao10K: Llama 3.1 Euryale 70B v2.21$0.85/1M tokens$0.85/1M tokens
Z.ai: GLM 5.31$0.87/1M tokens$3.36/1M tokens
Z.ai: GLM Latest1$0.87/1M tokens$3.36/1M tokens
Z.ai: GLM 5.21$0.90/1M tokens$2.83/1M tokens
Thinking Machines: Inkling1$0.95/1M tokens$4.05/1M tokens
Z.ai: GLM 5.11$0.96/1M tokens$3.03/1M tokens
Claude Haiku 4.51$1.00/1M tokens$5.00/1M tokens
OpenAI: GPT-3.5 Turbo (older v0613)1$1.00/1M tokens$2.00/1M tokens
Relace: Relace Search1$1.00/1M tokens$3.00/1M tokens
SpaceXAI: Grok Build 0.11$1.00/1M tokens$2.00/1M tokens
Anthropic: Claude Haiku Latest1$1.00/1M tokens$5.00/1M tokens
Qwen: Qwen3.6 Max Preview1$1.03/1M tokens$6.16/1M tokens
OpenAI: o3 Mini1$1.10/1M tokens$4.40/1M tokens
OpenAI: o3 Mini High1$1.10/1M tokens$4.40/1M tokens
OpenAI: o4 Mini1$1.10/1M tokens$4.40/1M tokens
OpenAI: o4 Mini High1$1.10/1M tokens$4.40/1M tokens
LLM API pricing — page 2 — Aggregation Marketplace