Skip to content

Language models: what a million tokens costs

Every model sold through OpenRouter, read from its public list each day: the price of a million input and output tokens, how much text it holds, what it accepts and returns, and when the price last moved.

read 2026-11-06 · 343 models · 57 vendors · prices kept since 2026-10-28

Prices are OpenRouter's, in US dollars. For most models that is the vendor's own list price; a vendor selling direct can differ.

AI chatbots and assistants, ranked by real use

Cheapest with tool calling and structured output
ModelInput, 1MOutput, 1MInput + outputContext
Mistral Nemo$0.0290$0.0300$0.0590131K
Ling 3.0 Tiny$0.0150$0.0450$0.0600262K
gpt-oss-120b$0.0140$0.0510$0.0650131K
Llama 3.1 8B Instruct$0.0500$0.0800$0.130131K
gpt-oss-20b$0.0300$0.130$0.160131K
Mercury 2.5$0.0400$0.150$0.190260K
Gemma 3 12B$0.0500$0.150$0.200131K
Ministral 3 3B 2512$0.100$0.100$0.200131K
Reka Edge$0.100$0.100$0.20016K
Ternary Bonsai 2 9B$0.0800$0.130$0.210262K

Ranked by the price of one million input tokens plus one million output tokens. Price says nothing about quality.

Do models know what tools cost?2026-10-27

Cheap models were asked, from what they know and without the web, for the cheapest paid plan of 300 tools whose price the Atlas read on the vendor's own page within 60 days. Each answer was scored against that page. Run 2026-10-27.

ModelRightNearWrongSaid it didn't know
GPT-6 Luna26.7%14%22.3%37%
DeepSeek V4.1 Flash20.6%14.5%28%36.8%
Claude Haiku 5.519.7%10.3%17.7%52.3%
Gemini 3.5 Flash Lite17.3%16%25.7%41%
GLM 5.3 Flash13.3%9%14.7%63%
Llama 4 Maverick13.3%12.3%43%31.3%
Qwen3.8 Flash12.8%9.1%19.5%58.7%
Nova 2 Lite11.3%21.3%53.7%13.7%
Kimi K2.58.3%6.7%9.3%75.7%
Mistral Small 45.9%11.1%24.1%58.9%
Grok 4.31.7%2%0.7%95.7%

Right: within 10% of the page's monthly price. Near: within 35%. Wrong: a price further off, the answer that misleads a buyer. Saying "I don't know" is not counted as wrong.

Price changed in the last 30 days
  • DeepSeek V3input $0.257 → $0.320, output $1.03 → $0.890, since 2026-11-06
  • DeepSeek V4.1 Flashinput $0.0450 → $0.0510, output $0.500 → $0.567, since 2026-11-06
  • DeepSeek V4.1 Flash 1017input $0.150 → $0.300, output $0.600 → $1.20, since 2026-11-06
  • DeepSeek V4 Flash 0731input $0.0434 → $0.0590, output $0.300 → $0.300, since 2026-11-06
  • DeepSeek V4 Flash Vision Expinput $0.216 → $0.440, output $0.647 → $1.32, since 2026-11-06
  • DeepSeek V4 Pro 0423input $0.955 → $1.60, output $1.91 → $3.20, since 2026-11-06
  • DeepSeek V4 Pro 0813input $0.103 → $0.117, output $4.11 → $4.66, since 2026-11-06
  • Gemma 4 26B A4Binput $0.0765 → $0.0900, output $0.255 → $0.300, since 2026-11-06
  • MiniMax M3.1 Flashinput $0.0750 → $0.150, output $0.300 → $0.600, since 2026-11-06
  • gpt-oss-120binput $0.0290 → $0.0140, output $0.109 → $0.0510, since 2026-11-06
  • Hy3input $0.0825 → $0.132, output $0.330 → $0.528, since 2026-11-06
  • Hy4 previewinput $0.751 → $0.834, output $2.25 → $2.50, since 2026-11-06
  • Llama 3.3 70B Instructinput $0.200 → $0.590, output $0.520 → $0.790, since 2026-11-05
  • Llama 4 Maverickinput $0.188 → $0.350, output $0.652 → $1.00, since 2026-11-05
  • MiniMax M2.7input $0.300 → $0.210, output $1.20 → $0.840, since 2026-11-05
  • Kimi K2.7 Codeinput $0.600 → $0.600, output $3.50 → $3.50, since 2026-11-05
  • Kimi K3input $0.200 → $0.192, output $16.00 → $16.00, since 2026-11-05
  • gpt-oss-20binput $0.0180 → $0.0300, output $0.0900 → $0.130, since 2026-11-05
  • Qwen3 235B A22B Instruct 2507input $0.0900 → $0.140, output $0.550 → $0.800, since 2026-11-05
  • Qwen3 Next 80B A3B Instructinput $0.100 → $0.0900, output $1.10 → $1.10, since 2026-11-05
  • Beam 1.0 501B A23Binput $0.250 → $0.300, output $1.00 → $1.00, since 2026-11-05
  • Granite 4.2 8Binput $0.0600 → $0.0600, output $0.150 → $0.250, since 2026-11-04
  • GLM 5.3input $0.0800 → $0.0699, output $3.60 → $1.40, since 2026-11-04
  • GLM 5.3 Flashinput $0.0269 → $0.150, output $0.0996 → $0.500, since 2026-11-04
  • Llama 3.1 70B Instructinput $0.400 → $0.720, output $0.400 → $0.720, since 2026-11-03
  • Llama 3.2 3B Instructinput $0.0500 → $0.0509, output $0.330 → $0.335, since 2026-11-03
  • Qwen3 Coder 30B A3B Instructinput $0.0700 → $0.150, output $0.280 → $0.600, since 2026-11-03
  • GLM 5.3 FlashXinput $0.370 → $0.370, output $1.25 → $1.25, since 2026-11-02
  • GLM 5.3 FlashX Legalinput $0.370 → $0.370, output $1.25 → $1.25, since 2026-11-02
  • Qwen3.8 27Binput $0.0400 → $0.150, output $2.30 → $1.88, since 2026-11-01
  • MiniMax M2.5input $0.300 → $0.270, output $1.20 → $0.950, since 2026-10-31
  • Qwen3.6 27Binput $0.320 → $0.450, output $3.20 → $2.70, since 2026-10-31
  • GLM 4.7input $0.540 → $0.600, output $1.98 → $2.20, since 2026-10-31
  • GLM 5.2input $0.00600 → $0.00600, output $7.00 → $6.80, since 2026-10-31
  • DeepSeek V3.2input $0.280 → $0.260, output $0.420 → $0.380, since 2026-10-30
  • Particle-1input $0.250 → $0.0500, output $1.00 → $0.500, since 2026-10-30
  • GLM 4.6Vinput $0.300 → $0.300, output $0.900 → $0.900, since 2026-10-30
  • Mistral Large 4input $1.36 → $0.700, output $4.18 → $2.10, since 2026-10-29
  • GLM 4.6input $0.550 → $0.500, output $2.20 → $2.00, since 2026-10-29
  • Llama 3.1 8B Instructinput $0.0200 → $0.0500, output $0.0400 → $0.0800, since 2026-10-28
New in the last 30 days
ModelInput, 1MOutput, 1MContext
Gemini Omni 1.2 Flash$1.50$9.00131K
Gemini Omni 1.1 Flash$1.50$9.00131K
ricursiveAI/Ripple-65B-Preview$0.200$0.6001.05M
Hy4$0.417$1.251.05M
Crouton Alphafreefree1.05M
GLM 5.3 FlashX Legal$0.370$1.251.05M
Particle-1$0.0500$0.5001.05M
GPT-6.1 Terra$1.00$5.001.05M
GPT-6.1 Terra Pro$1.00$5.001.05M
Kimi K3.1 Pro$2.00$10.001.05M
MiniMax M3.1 Flash$0.150$0.6001.05M
DeepSeek V4.1 Flash 1017$0.300$1.201.05M
Glimpse$0.600$3.00262K
Mercury 3$0.100$0.3501M
Ternary Bonsai 2 9B$0.0800$0.130262K
Beam 1.0 501B A23B$0.300$1.001.05M
Muse Spark Open$1.25$4.251.05M
Moondream 3.1$0.300$2.5032K
Moondream 3 Preview$0.300$2.5032K
Nemotron 3.5 Super VL$0.150$0.5001.05M
OpenAI58 models
ModelInput, 1MOutput, 1MContext
GPT-6.1 Terra$1.00$5.001.05M
GPT-6.1 Terra Pro$1.00$5.001.05M
GPT-6.1 Sol$2.00$10.001.05M
GPT-6.1 Sol Pro$2.00$10.001.05M
GPT-6 Luna$0.100$0.5001.05M
GPT-6 Luna Pro$0.100$0.5001.05M
GPT-6 Sol$2.00$10.001.05M
GPT-6 Sol Pro$2.00$10.001.05M

Older: GPT-6 Astra, GPT-6 Astra Pro, GPT-5.6 Luna, GPT-5.6 Luna Pro, GPT-5.6 Sol, GPT-5.6 Sol Pro, GPT-5.6 Terra, GPT-5.6 Terra Pro, GPT Chat Latest, GPT-5.5, GPT-5.5 Pro, GPT-5.4 Image 2, GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.4, GPT-5.4 Pro, GPT-5.3-Codex, GPT Audio, GPT Audio Mini, GPT-5.2-Codex, GPT-5.2, GPT-5.2 Chat, GPT-5.2 Pro, GPT-5.1-Codex-Max, GPT-5.1, GPT-5.1-Codex, GPT-5.1-Codex-Mini, gpt-oss-safeguard-20b, GPT-5 Image Mini, GPT-5 Image, GPT-5 Pro, GPT-5, GPT-5 Mini, GPT-5 Nano, gpt-oss-120b, gpt-oss-20b, o3 Pro, o3, GPT-4.1, GPT-4.1 Mini, GPT-4.1 Nano, GPT-4o (2024-11-20), GPT-4o (2024-08-06), GPT-4o-mini, GPT-4o-mini (2024-07-18), GPT-4o, GPT-4o (2024-05-13), GPT-3.5 Turbo (older v0613), GPT-3.5 Turbo 16k, GPT-4

Qwen41 models
ModelInput, 1MOutput, 1MContext
Qwen3.8 Max Prime$4.00$12.001M
Qwen3.8 Omni Flash$0.150$0.4701M
Qwen3.8 Max (0902)$2.00$6.001M
Qwen3.8 Flash$0.150$0.4701M
Qwen3.8 27B$0.150$1.881.02M
Qwen3.8 2.4T A95B$2.00$6.001.05M
Qwen3.7 Flash$0.0300$0.1301M
Qwen3.7 Plus$0.320$1.281M

Older: Qwen3.7 Max, Qwen3.5 Plus 2026-04-20, Qwen3.6 27B, Qwen3.6 35B A3B, Qwen3.6 Flash, Qwen3.6 Plus, Qwen3.5-9B, Qwen3.5-122B-A10B, Qwen3.5-27B, Qwen3.5-35B-A3B, Qwen3.5-Flash, Qwen3.5 397B A17B, Qwen3.5 Plus 2026-02-15, Qwen3 Coder Next, Qwen3 VL 8B Instruct, Qwen3 VL 30B A3B Instruct, Qwen3 VL 30B A3B Thinking, Qwen3 VL 235B A22B Instruct, Qwen3 Coder Flash, Qwen3 Next 80B A3B Instruct, Qwen3 Coder 30B A3B Instruct, Qwen3 30B A3B Instruct 2507, Qwen3 235B A22B Thinking 2507, Qwen3 Coder 480B A35B, Qwen3 235B A22B Instruct 2507, Qwen3 14B, Qwen3 30B A3B, Qwen3 32B, Qwen2.5 VL 72B Instruct, Qwen-Plus, Qwen2.5 Coder 32B Instruct, Qwen2.5 7B Instruct, Qwen2.5 72B Instruct

Google32 models
ModelInput, 1MOutput, 1MContext
Gemini Omni 1.2 Flash$1.50$9.00131K
Gemini Omni 1.1 Flash$1.50$9.00131K
Gemini 4 Argon$2.00$10.001.05M
Nano Banana 2.1$1.50$7.5066K
Gemini 3.8 Flash$0.825$4.131.05M
Gemini 3.7 Flash$0.750$3.751.05M
Gemini 3.5 Flash Lite$0.300$2.501.05M
Gemini 3.6 Flash$0.750$3.751.05M

Older: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image), Nano Banana 2 (Gemini 3.1 Flash Image), Nano Banana Pro (Gemini 3 Pro Image), Gemini 3.5 Flash, Gemini 3.1 Flash Lite, Gemma 4 26B A4B, Gemma 4 31B, Lyria 3 Clip Preview, Lyria 3 Pro Preview, Gemini 3.1 Flash Lite Preview, Nano Banana 2 (Gemini 3.1 Flash Image Preview), Gemini 3.1 Pro Preview Custom Tools, Gemini 3.1 Pro Preview, Gemini 3 Flash Preview, Nano Banana Pro (Gemini 3 Pro Image Preview), Nano Banana (Gemini 2.5 Flash Image), Gemini 2.5 Flash Lite, Gemini 2.5 Flash, Gemini 2.5 Pro, Gemini 2.5 Pro Preview 06-05, Gemma 3 12B, Gemma 3 4B, Gemma 3 27B, Gemma 2 27B

Mistral AI20 models
ModelInput, 1MOutput, 1MContext
Mistral Large 4$0.700$2.101.05M
Mistral Medium 3.5$1.50$7.50262K
Mistral Small 4$0.150$0.600262K
Devstral 2 2512$0.400$2.00262K
Ministral 3 14B 2512$0.200$0.200262K
Ministral 3 3B 2512$0.100$0.100131K
Ministral 3 8B 2512$0.150$0.150262K
Mistral Large 3 2512$0.500$1.50262K

Older: Voxtral Small 24B 2507, Mistral Medium 3.1, Codestral 2508, Mistral Small 3.2 24B, Mistral Medium 3, Mistral Small 3.1 24B, Saba, Mistral Small 3, Mistral Large 2407, Mistral Nemo, Mixtral 8x22B Instruct, Mistral Large

Z.ai17 models
ModelInput, 1MOutput, 1MContext
GLM 5.3 FlashX Legal$0.370$1.251.05M
GLM 5.3 Prime$2.80$8.801M
GLM 5.3 FlashX$0.370$1.251.05M
GLM 5.3 Flash$0.150$0.5001.05M
GLM 5.3$0.0699$1.401.05M
GLM 5.2$0.00600$6.801.05M
GLM 5.1$1.40$4.40205K
GLM 5V Turbo$1.20$4.00203K

Older: GLM 5 Turbo, GLM 5, GLM 4.7 Flash, GLM 4.7, GLM 4.6V, GLM 4.6, GLM 4.5V, GLM 4.5, GLM 4.5 Air

Anthropic15 models
ModelInput, 1MOutput, 1MContext
Claude Haiku 5.5$0.100$0.5001M
Claude Sonnet 5.5$2.00$10.001M
Claude Opus 5.5$4.00$20.001M
Claude Fable 5.1$10.00$50.001M
Claude Opus 5$5.00$25.001M
Claude Sonnet 5$2.00$10.001M
Claude Fable 5$10.00$50.001M
Claude Opus 4.8$5.00$25.001M

Older: Claude Opus 4.7, Claude Sonnet 4.6, Claude Opus 4.6, Claude Opus 4.5, Claude Haiku 4.5, Claude Sonnet 4.5, Claude Opus 4.1

DeepSeek14 models
ModelInput, 1MOutput, 1MContext
DeepSeek V4.1 Flash 1017$0.300$1.201.05M
DeepSeek V4.1 Flash$0.0510$0.5671.05M
DeepSeek V4 Flash Vision Exp$0.440$1.321.05M
DeepSeek V4 Pro 0813$0.117$4.661.05M
DeepSeek V4 Flash 0731$0.0590$0.3001.05M
DeepSeek V4 Flash 0423$0.0910$0.1821.05M
DeepSeek V4 Pro 0423$1.60$3.201.05M
DeepSeek V3.2$0.260$0.380164K

Older: DeepSeek V3.2 Exp, DeepSeek V3.1 Terminus, DeepSeek V3.1, R1 0528, DeepSeek V3 0324, DeepSeek V3

Meta8 models
ModelInput, 1MOutput, 1MContext
Muse Spark Open$1.25$4.251.05M
Muse Wonder$4.00$20.001.05M
Muse Spark 1.3$1.25$4.251.05M
Muse Spark 1.3 Contributor$0.100$0.2001.05M
Muse Spark 1.2 Contributor$0.100$0.2001.05M
Muse Glimmer 30B$0.300$1.20131K
Muse Spark 1.2$1.25$4.251.05M
Muse Spark 1.1$1.25$4.251.05M
Meta Llama8 models
ModelInput, 1MOutput, 1MContext
Llama Guard 4 12B$0.180$0.180164K
Llama 4 Maverick$0.350$1.00524K
Llama 4 Scout$0.100$0.3001.31M
Llama 3.3 70B Instruct$0.590$0.790131K
Llama 3.2 1B Instruct$0.0270$0.20160K
Llama 3.2 3B Instruct$0.0509$0.335131K
Llama 3.1 70B Instruct$0.720$0.720131K
Llama 3.1 8B Instruct$0.0500$0.0800131K
Moonshot AI8 models
ModelInput, 1MOutput, 1MContext
Kimi K3.1 Pro$2.00$10.001.05M
Kimi K3$0.192$16.001.05M
Kimi K2.7 Code$0.600$3.50262K
Kimi K2.6$0.650$3.41262K
Kimi K2.5$0.500$2.50262K
Kimi K2 Thinking$0.600$2.50262K
Kimi K2 0905$0.600$2.50262K
Kimi K2 0711$0.570$2.30131K
Tencent8 models
ModelInput, 1MOutput, 1MContext
Hy4$0.417$1.251.05M
Hy4 preview$0.834$2.501.05M
Hy-MT2-1.8B$0.0440$0.1778K
Hy-MT2-30B-A3B$0.0740$0.2958K
Hy-MT2-7B$0.0740$0.2958K
Hy3$0.132$0.528262K
Hy3 preview$0.180$0.600262K
Hunyuan A13B Instruct$0.140$0.570131K
NVIDIA7 models
ModelInput, 1MOutput, 1MContext
Nemotron 3.5 Super VL$0.150$0.5001.05M
Switchyard--1M
Nemotron 3.5 Lightning$0.0700$0.200262K
Nemotron 3.5 Content Safety$0.200$0.200131K
Nemotron 3 Ultra$0.600$2.40262K
Nemotron 3 Super$0.300$2.401.05M
Nemotron 3 Nano 30B A3B$0.0600$0.240262K
xAI7 models
ModelInput, 1MOutput, 1MContext
Grok 4.7$2.00$6.00500K
Grok 4.6$2.00$6.00500K
Grok 4.5$2.00$6.00500K
Grok Build 0.1$1.00$2.00256K
Grok 4.3$1.25$2.501M
Grok 4.20$1.25$2.502M
Grok 4.20 Multi-Agent$1.25$2.502M
aion-labs6 models
ModelInput, 1MOutput, 1MContext
Aion 3.5$3.00$6.00262K
Aion 3.5 Mini$0.700$1.40262K
Aion-3.0$3.00$6.00131K
Aion-3.0-Mini$0.700$1.40131K
Aion-2.0$0.800$1.60131K
Aion-RP 1.0 (8B)$0.800$1.6033K
ByteDance Seed6 models
ModelInput, 1MOutput, 1MContext
Seed-2.0-Code$0.500$3.00262K
Seed 2.1 Turbo$0.500$2.50262K
Seed-2.0-Lite$0.250$2.00262K
Seed-2.0-Mini$0.100$0.400262K
Seed 1.6$0.250$2.00262K
Seed 1.6 Flash$0.0750$0.300262K
Amazon5 models
ModelInput, 1MOutput, 1MContext
Nova 2 Lite$0.300$2.501M
Nova Premier 1.0$2.50$12.501M
Nova Lite 1.0$0.0600$0.240300K
Nova Micro 1.0$0.0350$0.140128K
Nova Pro 1.0$0.800$3.20300K
Cohere5 models
ModelInput, 1MOutput, 1MContext
Command A+$0.300$1.50192K
Command A$2.50$10.00256K
Command R7B (12-2024)$0.0375$0.150128K
Command R (08-2024)$0.150$0.600128K
Command R+ (08-2024)$2.50$10.00128K
MiniMax5 models
ModelInput, 1MOutput, 1MContext
MiniMax M3.1 Flash$0.150$0.6001.05M
MiniMax M3$0.300$1.201.05M
MiniMax M2.7$0.210$0.840205K
MiniMax M2.5$0.270$0.950205K
MiniMax M1$0.550$2.201M
Perplexity5 models
ModelInput, 1MOutput, 1MContext
Sonar Pro Search$3.00$15.00200K
Sonar Deep Research$2.00$8.00128K
Sonar Pro$3.00$15.00200K
Sonar Reasoning Pro$2.00$8.00128K
Sonar$1.00$1.00127K
Xiaomi5 models
ModelInput, 1MOutput, 1MContext
MiMo-V2.6-Flash$0.140$0.2801.05M
MiMo-V2.6-Pro$0.435$0.8701.05M
MiMo-V2.6-Pro-UltraSpeed$4.35$8.701.05M
MiMo-V2.5$0.400$2.001M
MiMo-V2.5-Pro$0.480$1.801.05M
inclusionai4 models
ModelInput, 1MOutput, 1MContext
Ling 3.1 Flash$0.0750$0.2251M
Ling 3.0 Flash VL$0.0600$0.180131K
Ling 3.0 Tiny$0.0150$0.0450262K
Ling 3.0 Flash$0.0210$0.0630262K
sakana4 models
ModelInput, 1MOutput, 1MContext
Fugu Max$2.00$6.001M
Fugu Ultra v2$5.00$30.001M
Sakana Namazu$0.950$4.00262K
Fugu Ultra$5.00$30.001M
inception3 models
ModelInput, 1MOutput, 1MContext
Mercury 3$0.100$0.3501M
Mercury 2.5$0.0400$0.150260K
Mercury 2$0.250$0.750128K
stepfun3 models
ModelInput, 1MOutput, 1MContext
Step 5 Preview$1.00$2.701.05M
Step 3.7 Flash$0.200$1.15262K
Step 3.5 Flash$0.100$0.300262K
thedrummer3 models
ModelInput, 1MOutput, 1MContext
Cydonia 24B V4.1$0.300$0.500131K
Skyfall 36B V2$0.550$0.80033K
UnslopNemo 12B$0.400$0.4001.02M
inference-net2 models
ModelInput, 1MOutput, 1MContext
Schematron V2 Small$0.0500$0.230128K
Schematron V2 Turbo$0.0300$0.150128K
liquid2 models
ModelInput, 1MOutput, 1MContext
LFM2.5-24B-A2B$0.0500$0.700128K
LFM2.5-2.6B$0.350$0.500128K
moondream2 models
ModelInput, 1MOutput, 1MContext
Moondream 3.1$0.300$2.5032K
Moondream 3 Preview$0.300$2.5032K
morph2 models
ModelInput, 1MOutput, 1MContext
Morph V3 Fast$0.800$1.20262K
Morph V3 Large$0.900$1.90262K
nex-agi2 models
ModelInput, 1MOutput, 1MContext
Nex-N2.5-Mini$0.0250$0.100262K
Nex-N2.5-Pro$0.0750$0.250262K
perceptron2 models
ModelInput, 1MOutput, 1MContext
Perceptron Mk1.5$0.150$1.5037K
Perceptron Mk1$0.150$1.5033K
prism-ml2 models
ModelInput, 1MOutput, 1MContext
Ternary Bonsai 2 9B$0.0800$0.130262K
Ternary Bonsai 2 27B$0.0750$0.500262K
rekaai2 models
ModelInput, 1MOutput, 1MContext
Reka Edge$0.100$0.10016K
Reka Flash 3$0.100$0.20066K
relace2 models
ModelInput, 1MOutput, 1MContext
Relace Search$1.00$3.00256K
Relace Apply 3$0.850$1.25256K
sao10k2 models
ModelInput, 1MOutput, 1MContext
Llama 3.1 Euryale 70B v2.2$0.850$0.850131K
Llama 3 8B Lunaris$0.0400$0.05008K
scaledown2 models
ModelInput, 1MOutput, 1MContext
Extract$0.0400free1M
Summarize$0.0400free1M
thinkingmachines2 models
ModelInput, 1MOutput, 1MContext
Inkling Small$0.450$1.20524K
Inkling$1.00$4.05524K
unbiased2 models
ModelInput, 1MOutput, 1MContext
Pareto 26.10$0.800$3.201.05M
Pareto 26.9$2.50$7.50262K
upstage2 models
ModelInput, 1MOutput, 1MContext
Solar Mini 4$0.0500$0.200524K
Solar Pro 4$0.150$0.600524K
anthracite-org1 models
ModelInput, 1MOutput, 1MContext
Magnum v4 72B$2.50$5.0033K
bytedance1 models
ModelInput, 1MOutput, 1MContext
UI-TARS 7B$0.100$0.200128K
cognitivecomputations1 models
ModelInput, 1MOutput, 1MContext
Uncensored$0.200$0.900128K
elorian1 models
ModelInput, 1MOutput, 1MContext
Glimpse$0.600$3.00262K
fireworks1 models
ModelInput, 1MOutput, 1MContext
Ember-1$3.00$15.001.05M
gryphe1 models
ModelInput, 1MOutput, 1MContext
MythoMax 13B$0.0800$0.1108K
ibm-granite1 models
ModelInput, 1MOutput, 1MContext
Granite 4.2 8B$0.0600$0.250131K
mancer1 models
ModelInput, 1MOutput, 1MContext
Weaver (alpha)$0.400$0.7508K
meituan1 models
ModelInput, 1MOutput, 1MContext
LongCat 2.0$0.300$1.201.05M
Microsoft1 models
ModelInput, 1MOutput, 1MContext
Phi 4$0.0700$0.14016K
nousresearch1 models
ModelInput, 1MOutput, 1MContext
Hermes 4 405B$1.00$3.00131K
particle-ai1 models
ModelInput, 1MOutput, 1MContext
Particle-1$0.0500$0.5001.05M
reflection1 models
ModelInput, 1MOutput, 1MContext
Beam 1.0 501B A23B$0.300$1.001.05M
ricursiveai1 models
ModelInput, 1MOutput, 1MContext
ricursiveAI/Ripple-65B-Preview$0.200$0.6001.05M
stealth1 models
ModelInput, 1MOutput, 1MContext
Crouton Alphafreefree1.05M
typesafe1 models
ModelInput, 1MOutput, 1MContext
Jev Router--1M
undi951 models
ModelInput, 1MOutput, 1MContext
ReMM SLERP 13B$0.350$0.6506K
writer1 models
ModelInput, 1MOutput, 1MContext
Palmyra X5$0.600$6.001.04M

How this is read

  1. A program reads OpenRouter's public model list (openrouter.ai/api/v1/models) every six hours. No key, no language model.
  2. Prices are stored per million tokens. An unchanged price extends the current run; a new price opens a run with its first day, so every change has a date.
  3. A model the list stops naming is marked gone and stays on its page for 120 days. Aliases, routers and the rate-limited ":free" copies are left out.
  4. Nothing here is a benchmark. Quality, speed and how often a model is right are other questions, measured elsewhere.

The same data as JSON · CC BY 4.0: cite INITE Atlas with a link.