LLM prices per 1M tokens

Models264Price changes161

264 models · 161 price changes

The brief · Mon Nov 9

DeepSeek V4 Flash 0731 (DeepSeek) on the wafer/us route saw its input price per 1M tokens drop from $0.0522 to $0.0434 and cached input price drop from $0.0512 to $0.035. Qwen3.6 35B A3B (Qwen (Alibaba)) on the primeintellect/fp8 route increased its input price from $0.01 to $0.016, output price from $0.092 to $0.144, and cached input price from $0.009 to $0.014 per 1M tokens. GLM 5.3 Flash (Z.ai) on the inferencenet/us route raised its cached input price from $0.032 to $0.033 per 1M tokens. GLM 5.3 had its tenstorrent/fp8 and nebius/fp4 routes removed.

Read more

Price moves

by day, newest first
Thursday, Nov 51 model
Price cut-33%Embed 5 FastCohere cut its API price: input $0.12 to $0.08 per 1M tokens.
Tuesday, Nov 31 model
Price cut-17%GLM 5.3 FlashXZ.ai cut its API price: cached input $0.09 to $0.075 per 1M tokens.
Thursday, Oct 291 model
Price rise+20%GPT-4.1 NanoOpenAI raised its API price: cached input $0.025 to $0.03 per 1M tokens.
Saturday, Oct 241 model
Price cut-50%Claude Sonnet 5.5Anthropic cut its API price: cached input $0.2 to $0.1 per 1M tokens.
Friday, Oct 232 models
Price rise+100%GPT-5.6 SolOpenAI raised its API price: input $2 to $4 and output $10 to $20 per 1M tokens.Price rise+100%GPT-5.6 Sol ProOpenAI raised its API price: input $2 to $4 and output $10 to $20 per 1M tokens.
Wednesday, Oct 211 model
Price rise+100%Mistral Large 4Mistral AI raised its API price: input $0.68 to $1.36 and output $2.09 to $4.18 per 1M tokens.
Friday, Oct 21 model
Price rise+25%Grok 4.7xAI raised its API price: input $1.6 to $2 and output $4.8 to $6 per 1M tokens.
Saturday, Aug 291 model
Price rise+100%Gemini 3.7 FlashGoogle raised its API price: input $0.375 to $0.75 and output $1.88 to $3.75 per 1M tokens.
Monday, Aug 242 models
Price cut-20%GPT-5.6 SolOpenAI cut its API price: input $2.5 to $2 and output $15 to $10 per 1M tokens.Price cut-20%GPT-5.6 Sol ProOpenAI cut its API price: input $2.5 to $2 and output $15 to $10 per 1M tokens.
Friday, Aug 216 models
Price cut-50%GPT-5.6 SolOpenAI cut its API price: input $5 to $2.5 and output $30 to $15 per 1M tokens.Price cut-50%GPT-5.6 Sol ProOpenAI cut its API price: input $5 to $2.5 and output $30 to $15 per 1M tokens.Price rise+100%GPT-5.6 TerraOpenAI raised its API price: input $1 to $2 and output $6 to $12 per 1M tokens.Price rise+100%GPT-5.6 Terra ProOpenAI raised its API price: input $1 to $2 and output $6 to $12 per 1M tokens.Price rise+100%GPT-5.6 LunaOpenAI raised its API price: input $0.1 to $0.2 and output $0.6 to $1.2 per 1M tokens.Price rise+100%GPT-5.6 Luna ProOpenAI raised its API price: input $0.1 to $0.2 and output $0.6 to $1.2 per 1M tokens.
Friday, Aug 141 model
Price cut-50%Gemini 3.6 FlashGoogle cut its API price: input $1.5 to $0.75 and output $7.5 to $3.75 per 1M tokens.
Friday, Jul 315 models
Price cut-1%Qwen3.6 Max PreviewQwen (Alibaba) cut its API price: input $1.04 to $1.03 and output $6.24 to $6.16 per 1M tokens.Price cut-20%GPT-5.6 TerraOpenAI cut its API price: input $1.25 to $1 and output $7.5 to $6 per 1M tokens.Price cut-20%GPT-5.6 Terra ProOpenAI cut its API price: input $1.25 to $1 and output $7.5 to $6 per 1M tokens.Price cut-80%GPT-5.6 LunaOpenAI cut its API price: input $0.5 to $0.1 and output $3 to $0.6 per 1M tokens.Price cut-80%GPT-5.6 Luna ProOpenAI cut its API price: input $0.5 to $0.1 and output $3 to $0.6 per 1M tokens.
Every price change →

Leaders, priced

leadersboard rank, blended price
1GPT-6 AstraOpenAI's model, ranked #1 on leadersboard.fru.dev; $10 in and $50 out per 1M tokens, $10 blended on OpenAI (flex).$202Claude Fable 5.1Anthropic's model, ranked #2 on leadersboard.fru.dev; $10 in and $50 out per 1M tokens.$203GPT-6.1 SolOpenAI's model, ranked #3 on leadersboard.fru.dev; $2 in and $10 out per 1M tokens, $2 blended on OpenAI (flex).$44Claude Opus 5.5Anthropic's model, ranked #4 on leadersboard.fru.dev; $4 in and $20 out per 1M tokens.$85Gemini 4 ArgonGoogle's model, ranked #5 on leadersboard.fru.dev; $2 in and $10 out per 1M tokens, $2 blended on Google Gemini API (flex).$46Claude Fable 5Anthropic's model, ranked #6 on leadersboard.fru.dev; $10 in and $50 out per 1M tokens.$207Claude Opus 5Anthropic's model, ranked #7 on leadersboard.fru.dev; $5 in and $25 out per 1M tokens.$108Claude Sonnet 5.5Anthropic's model, ranked #8 on leadersboard.fru.dev; $2 in and $10 out per 1M tokens.$49GPT-5.6 SolOpenAI's model, ranked #10 on leadersboard.fru.dev; $4 in and $20 out per 1M tokens, $4 blended on OpenAI (flex).$810Claude Opus 4.6Anthropic's model, ranked #11 on leadersboard.fru.dev; $5 in and $25 out per 1M tokens.$1011GPT-6.1 TerraOpenAI's model, ranked #12 on leadersboard.fru.dev; $1 in and $5 out per 1M tokens, $1 blended on OpenAI (flex).$212Claude Opus 4.7Anthropic's model, ranked #13 on leadersboard.fru.dev; $5 in and $25 out per 1M tokens.$1013Gemini 3.8 FlashGoogle's model, ranked #14 on leadersboard.fru.dev; $0.75 in and $3.75 out per 1M tokens, $0.75 blended on Google Gemini API (flex).$1.514Muse Spark 1.1Meta's model, ranked #15 on leadersboard.fru.dev; $1.25 in and $4.25 out per 1M tokens.$215Qwen3.8 Max (0902)Qwen (Alibaba)'s model, ranked #17 on leadersboard.fru.dev; $2 in and $6 out per 1M tokens.$316Gemini 3.1 Pro PreviewGoogle's model, ranked #18 on leadersboard.fru.dev; $2 in and $12 out per 1M tokens, $2.25 blended on Google Vertex AI (global-flex).$4.517GPT-6 SolOpenAI's model, ranked #19 on leadersboard.fru.dev; $2 in and $10 out per 1M tokens, $2 blended on OpenAI (flex).$418GPT-5.4 ProOpenAI's model, ranked #21 on leadersboard.fru.dev; $30 in and $180 out per 1M tokens, $33.8 blended on OpenAI (flex).$67.519Gemini 3.7 FlashGoogle's model, ranked #22 on leadersboard.fru.dev; $0.75 in and $3.75 out per 1M tokens, $0.75 blended on Google Vertex AI (global-flex).$1.520Muse WonderMeta's model, ranked #24 on leadersboard.fru.dev; $4 in and $20 out per 1M tokens.$821GPT-5.5OpenAI's model, ranked #26 on leadersboard.fru.dev; $5 in and $30 out per 1M tokens, $5.63 blended on OpenAI (flex).$11.322Muse Spark 1.3Meta's model, ranked #28 on leadersboard.fru.dev; $1.25 in and $4.25 out per 1M tokens.$223Kimi K3Moonshot AI's model, ranked #29 on leadersboard.fru.dev; $3 in and $15 out per 1M tokens, $2.88 blended on InferenceNet (us).$624Claude Sonnet 5Anthropic's model, ranked #30 on leadersboard.fru.dev; $2 in and $10 out per 1M tokens.$425Muse Spark OpenMeta's model, ranked #31 on leadersboard.fru.dev; $1.25 in and $4.25 out per 1M tokens.$226Qwen3.8 2.4T A95BQwen (Alibaba)'s model, ranked #32 on leadersboard.fru.dev; $2 in and $6 out per 1M tokens.$327Claude Opus 4.8Anthropic's model, ranked #33 on leadersboard.fru.dev; $5 in and $25 out per 1M tokens.$1028Kimi K3.1 ProMoonshot AI's model, ranked #34 on leadersboard.fru.dev; $0.377 in and $7.95 out per 1M tokens.$2.2729DeepSeek V4.1 Flash 1017DeepSeek's model, ranked #35 on leadersboard.fru.dev; $0.15 in and $0.6 out per 1M tokens, $0.081 blended on Particle AI (us-flex).$0.26230DeepSeek V4.1 FlashDeepSeek's model, ranked #35 on leadersboard.fru.dev; $0.045 in and $0.3 out per 1M tokens.$0.10931GPT-5.6 TerraOpenAI's model, ranked #35 on leadersboard.fru.dev; $2 in and $12 out per 1M tokens, $2.25 blended on OpenAI (flex).$4.532GLM 5.3Z.ai's model, ranked #37 on leadersboard.fru.dev; $0.179 in and $1.4 out per 1M tokens.$0.48433GPT-5.4OpenAI's model, ranked #39 on leadersboard.fru.dev; $2.5 in and $15 out per 1M tokens, $2.81 blended on OpenAI (flex).$5.6334Gemini 3.5 FlashGoogle's model, ranked #40 on leadersboard.fru.dev; $1.5 in and $9 out per 1M tokens, $1.69 blended on Google Vertex AI (global-flex).$3.3835Claude Haiku 5.5Anthropic's model, ranked #42 on leadersboard.fru.dev; $0.1 in and $0.5 out per 1M tokens.$0.236Muse Spark 1.2Meta's model, ranked #43 on leadersboard.fru.dev; $1.25 in and $4.25 out per 1M tokens.$237Claude Sonnet 4.6Anthropic's model, ranked #44 on leadersboard.fru.dev; $3 in and $15 out per 1M tokens.$6
Compare models →

Cheapest

per 1M tokens, blended 3:1
1gpt-oss-20bAn open-weight model by OpenAI; $0.004 in and $0.017 out per 1M tokens.$0.00732gpt-oss-120bAn open-weight model by OpenAI; $0.01 in and $0.037 out per 1M tokens.$0.0173Mistral NemoAn open-weight model by Mistral AI; $0.018 in and $0.03 out per 1M tokens.$0.0214Llama 3.1 8B InstructAn open-weight model by Meta; $0.02 in and $0.04 out per 1M tokens.$0.0255Gemma 3 4BAn open-weight model by Google; $0.04 in and $0.05 out per 1M tokens.$0.0426Qwen3.6 35B A3BAn open-weight model by Qwen (Alibaba); $0.016 in and $0.144 out per 1M tokens.$0.0487GLM 5.3 FlashAn open-weight model by Z.ai; $0.012 in and $0.158 out per 1M tokens.$0.0498Nemotron 3.5 LightningAn open-weight model by NVIDIA; $0.025 in and $0.12 out per 1M tokens.$0.0499Qwen3.7 FlashA model by Qwen (Alibaba); $0.03 in and $0.13 out per 1M tokens.$0.05510Mistral Small 3An open-weight model by Mistral AI; $0.05 in and $0.08 out per 1M tokens.$0.05811Gemma 3 12BAn open-weight model by Google; $0.04 in and $0.12 out per 1M tokens.$0.0612Nova Micro 1.0A model by Amazon Nova; $0.035 in and $0.14 out per 1M tokens.$0.06113Command R7B (12-2024)A model by Cohere; $0.037 in and $0.15 out per 1M tokens.$0.06614Llama 3.2 1B InstructAn open-weight model by Meta; $0.027 in and $0.201 out per 1M tokens.$0.07115Gemma 4 26B A4BAn open-weight model by Google; $0.08 in and $0.1 out per 1M tokens.$0.08516DeepSeek V4 Flash 0731An open-weight model by DeepSeek; $0.019 in and $0.3 out per 1M tokens.$0.08917Qwen3.5-9BAn open-weight model by Qwen (Alibaba); $0.08 in and $0.13 out per 1M tokens.$0.09218Gemma 3 27BAn open-weight model by Google; $0.08 in and $0.16 out per 1M tokens.$0.119Ministral 3 3B 2512An open-weight model by Mistral AI; $0.1 in and $0.1 out per 1M tokens.$0.120Nemotron 3 Nano 30B A3BAn open-weight model by NVIDIA; $0.06 in and $0.24 out per 1M tokens.$0.10521Nova Lite 1.0A model by Amazon Nova; $0.06 in and $0.24 out per 1M tokens.$0.10522Mistral Small 3.2 24BAn open-weight model by Mistral AI; $0.075 in and $0.2 out per 1M tokens.$0.10623DeepSeek V4.1 FlashAn open-weight model by DeepSeek; $0.045 in and $0.3 out per 1M tokens.$0.10924DeepSeek V4 Flash 0423An open-weight model by DeepSeek; $0.09 in and $0.18 out per 1M tokens.$0.11325Qwen3.5-FlashA model by Qwen (Alibaba); $0.065 in and $0.26 out per 1M tokens.$0.11426Llama 4 ScoutAn open-weight model by Meta; $0.08 in and $0.24 out per 1M tokens.$0.1227Llama 3.2 3B InstructAn open-weight model by Meta; $0.05 in and $0.33 out per 1M tokens.$0.1228Qwen3 Coder 30B A3B InstructAn open-weight model by Qwen (Alibaba); $0.07 in and $0.28 out per 1M tokens.$0.12329Muse Spark 1.2 ContributorA model by Meta; $0.1 in and $0.2 out per 1M tokens.$0.12530Muse Spark 1.3 ContributorA model by Meta; $0.1 in and $0.2 out per 1M tokens.$0.12531Qwen2.5 7B InstructAn open-weight model by Qwen (Alibaba); $0.1 in and $0.2 out per 1M tokens.$0.12532Qwen3 14BAn open-weight model by Qwen (Alibaba); $0.1 in and $0.22 out per 1M tokens.$0.1333Qwen3 32BAn open-weight model by Qwen (Alibaba); $0.08 in and $0.28 out per 1M tokens.$0.1334gpt-oss-safeguard-20bAn open-weight model by OpenAI; $0.075 in and $0.3 out per 1M tokens.$0.13135Nemotron 3.5 Super VLAn open-weight model by NVIDIA; $0.06 in and $0.35 out per 1M tokens.$0.13336GPT-5 NanoA model by OpenAI; $0.05 in and $0.4 out per 1M tokens.$0.13837Qwen3 30B A3B Instruct 2507An open-weight model by Qwen (Alibaba); $0.09 in and $0.3 out per 1M tokens.$0.14338Llama Guard 4 12BAn open-weight model by Meta; $0.144 in and $0.144 out per 1M tokens.$0.14439GLM 4.7 FlashAn open-weight model by Z.ai; $0.06 in and $0.4 out per 1M tokens.$0.14540Ministral 3 8B 2512An open-weight model by Mistral AI; $0.15 in and $0.15 out per 1M tokens.$0.1541Voxtral Small 24B 2507An open-weight model by Mistral AI; $0.1 in and $0.3 out per 1M tokens.$0.1542Llama 3.3 70B InstructAn open-weight model by Meta; $0.1 in and $0.32 out per 1M tokens.$0.15543Nemotron 3 SuperAn open-weight model by NVIDIA; $0.075 in and $0.4 out per 1M tokens.$0.15644Gemma 4 31BAn open-weight model by Google; $0.1 in and $0.34 out per 1M tokens.$0.1645Gemini 2.5 Flash LiteA model by Google; $0.1 in and $0.4 out per 1M tokens.$0.17546GPT-4.1 NanoA model by OpenAI; $0.1 in and $0.4 out per 1M tokens.$0.17547Claude Haiku 5.5A model by Anthropic; $0.1 in and $0.5 out per 1M tokens.$0.248GPT-6 LunaA model by OpenAI; $0.1 in and $0.5 out per 1M tokens.$0.249GPT-6 Luna ProA model by OpenAI; $0.1 in and $0.5 out per 1M tokens.$0.250Ministral 3 14B 2512An open-weight model by Mistral AI; $0.2 in and $0.2 out per 1M tokens.$0.251Nemotron 3.5 Content SafetyAn open-weight model by NVIDIA; $0.2 in and $0.2 out per 1M tokens.$0.252Qwen3 235B A22B Instruct 2507An open-weight model by Qwen (Alibaba); $0.09 in and $0.55 out per 1M tokens.$0.20553Qwen3 30B A3BAn open-weight model by Qwen (Alibaba); $0.12 in and $0.5 out per 1M tokens.$0.21554Qwen3.8 FlashAn open-weight model by Qwen (Alibaba); $0.15 in and $0.47 out per 1M tokens.$0.2355Qwen3.8 Omni FlashA model by Qwen (Alibaba); $0.15 in and $0.47 out per 1M tokens.$0.2356Command R (08-2024)A model by Cohere; $0.15 in and $0.6 out per 1M tokens.$0.26257DeepSeek V4.1 Flash 1017An open-weight model by DeepSeek; $0.15 in and $0.6 out per 1M tokens.$0.26258GPT-4o-miniA model by OpenAI; $0.15 in and $0.6 out per 1M tokens.$0.26259GPT-4o-mini (2024-07-18)A model by OpenAI; $0.15 in and $0.6 out per 1M tokens.$0.26260Mistral Small 4An open-weight model by Mistral AI; $0.15 in and $0.6 out per 1M tokens.$0.262
Every model, every price →