LLM PricesModelsChangelog
Prices in USD per 1M tokens, text only. Each price shows where it came from and when it was last verified. Prices marked unverified come from models.dev (community-maintained) until we read them from the provider directly.

Model prices across providers

Cheapest standard-tier price per model. Open a model to see every provider serving it, their exact model ids, quantization, cache and tier pricing.

All modelsFrontier
ModelReleasedWeightsContextProvidersInputOutputBlended 3:1Cheapest atVerified
Claude Haiku 5.5
anthropic/claude-haiku-5-5
Oct '26Closed1M3$0.10$0.50$0.20Anthropic5h ago•
Mistral Large 4Frontier
mistral/mistral-large-4
Oct '26Closed1M1$0.68$2.09$1.03Mistral5h ago•
GPT-6.1 SolFrontier
openai/gpt-6.1-sol
Page 1Next →

• means at least one provider's price for that model is unverified community data.

Sep '26
Closed
1.1M
3
$2.0
$10.0
$4.0
AWS Bedrock
2h ago•
Claude Sonnet 5.5
anthropic/claude-sonnet-5-5
Sep '26Closed1M4$2.0$10.0$4.0DeepInfra3h ago•
Claude Opus 5.5Frontier
anthropic/claude-opus-5-5
Sep '26Closed1M4$4.0$20.0$8.0Google Vertex AI3h ago•
GPT-6 Luna
openai/gpt-6-luna
Sep '26Closed1.1M3$0.10$0.50$0.20AWS Bedrock2h ago•
GPT-6 SolFrontier
openai/gpt-6-sol
Sep '26Closed1.1M3$2.0$10.0$4.0Azure AI Foundry2h ago•
MiMo-V2.6-Flash
xiaomi/mimo-v2.6-flash
Sep '26Open1M1$0.14$0.28$0.175DeepInfra3h ago
MiMo-V2.6-ProFrontier
xiaomi/mimo-v2.6-pro
Sep '26Open1M1$0.43$0.87$0.54DeepInfra3h ago
Grok 4.7Frontier
xai/grok-4.7
Sep '26Closed500k3$2.0$6.0$3.0AWS Bedrock2h ago•
DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4.1-flash
Sep '26Open1M5$0.15$0.60$0.263DeepSeek2h ago•
Ling 3.0 Flash VL
inclusionai/ling-3.0-flash-vl
Sep '26Open262k1$0.06$0.18$0.09DeepInfra3h ago
GPT-6 AstraFrontier
openai/gpt-6-astra
Sep '26Closed1.1M3$10.0$50.0$20.0OpenAI2h ago•
Gemini 3.8 Flash
google/gemini-3.8-flash
Sep '26Closed1M2$0.75$3.75$1.5Google Vertex AI5h ago•
Claude Fable 5.1Frontier
anthropic/claude-fable-5-1
Sep '26Closed1M3$10.0$50.0$20.0AWS Bedrock5h ago•
Hy4 preview
tencent/hy4-preview
Aug '26Open1M1$0.834$2.5$1.25DeepInfra3h ago
Ling 3.0 Flash Fin
inclusionai/ling-3.0-flash-fin
Aug '26Open262k1$0.06$0.18$0.09DeepInfra3h ago
GLM-5.3-Flash
zhipuai/glm-5.3-flash
Aug '26Open1M4$0.15$0.50$0.237Together AI2h ago•
Qwen3.8 Flash
alibaba/qwen3.8-flash
Aug '26Closed1M1$0.113$0.382$0.18DeepInfra3h ago
DeepSeek V4 Flash Vision Exp
deepseek/deepseek-v4-flash-vision-exp
Aug '26Open1M1$0.44$1.32$0.66DeepInfra3h ago
GLM-5.3 HighspeedFrontier
zhipuai/glm-5.3
Aug '26Open1M6$0.90$4.0$1.68DeepInfra2h ago•
Qwen3.8 27B
alibaba/qwen3.8-27b
Aug '26Open262k3$0.20$2.5$0.775DeepInfra3h ago•
Gemini 3.7 Flash
google/gemini-3.7-flash
Aug '26Closed1M3$0.75$3.75$1.5DeepInfra3h ago•
Gemini Flash Latest
google/gemini-flash-latest
Aug '26Closed1M1$0.75$3.75$1.5Google Gemini API5h ago•
DeepSeek V4 ProFrontier
deepseek/deepseek-v4-pro-0813
Aug '26Open1M3$0.66$1.98$0.99DeepSeek3h ago•
Grok 4.6Frontier
xai/grok-4.6
Aug '26Closed500k3$2.0$6.0$3.0AWS Bedrock2h ago•
Qwen3.8-MaxFrontier
alibaba/qwen3.8-2.4t-a95b
Aug '26Open1M2$2.0$6.0$3.0Fireworks AI3h ago•
MAI-Code-1.1-Flash
microsoft/mai-code-1.1-flash
Aug '26Closed256k1$0.20$1.2$0.45Azure AI Foundry2h ago
Nemotron 3.5 Lightning 30B A3B
nvidia/nemotron-3.5-lightning
Aug '26Open262k1$0.05$0.20$0.087Fireworks AI5h ago•
Muse Glimmer 30B
meta/muse-glimmer-30b
Aug '26Open131k1$0.30$1.2$0.525DeepInfra3h ago
Daybreak Red
openai/gpt-5.6-cyber
Aug '26Closed400k1$12.5$75.0$28.13OpenAI5h ago•
Qwen3.8 MaxFrontier
alibaba/qwen3.8-max
Aug '26Closed1M2$1.65$4.95$2.48DeepInfra3h ago•
DeepSeek V4 Flash
deepseek/deepseek-v4-flash-0731
Jul '26Open1M3$0.06$0.18$0.09DeepInfra2h ago•
Inkling Small
thinkingmachines/inkling-small
Jul '26Open524k1$0.45$1.2$0.637DeepInfra3h ago
Claude Opus 5Frontier
anthropic/claude-opus-5
Jul '26Closed1M4$5.0$25.0$10.0AWS Bedrock3h ago•
Ling 3.0 Flash
inclusionai/ling-3.0-flash
Jul '26Open262k1$0.06$0.18$0.09DeepInfra3h ago
Gemini 3.5 Flash Lite
google/gemini-3.5-flash-lite
Jul '26Closed1M2$0.30$2.5$0.85Google Gemini API5h ago•
Gemini 3.6 Flash
google/gemini-3.6-flash
Jul '26Closed1M2$0.75$3.75$1.5Google Gemini API5h ago•
Gemini Flash Lite Latest
google/gemini-flash-lite-latest
Jul '26Closed1M1$0.30$2.5$0.85Google Gemini API5h ago•
Kimi K3Frontier
moonshotai/kimi-k3
Jul '26Open1M5$2.85$14.25$5.7DeepInfra2h ago•
Inkling (256K)
thinkingmachines/inkling
Jul '26Open262k4$0.95$4.05$1.73DeepInfra2h ago•
GPT-5.6 Luna
openai/gpt-5.6-luna
Jul '26Closed1.1M3$0.20$1.2$0.45OpenAI2h ago•
GPT-5.6Frontier
openai/gpt-5.6-sol
Jul '26Closed1.1M3$4.0$20.0$8.0AWS Bedrock2h ago•
GPT-5.6 Terra
openai/gpt-5.6-terra
Jul '26Closed1.1M3$2.0$12.0$4.5OpenAI2h ago•
Hy3
tencent/hy3
Jul '26Open256k1$0.13$0.53$0.23DeepInfra3h ago
Claude Sonnet 5
anthropic/claude-sonnet-5
Jun '26Closed1M4$2.0$10.0$4.0Google Vertex AI3h ago•
Ornith-1.0-35B-FP8
deepreinforce/ornith-1.0-35b
Jun '26Open262k1$0.10$0.75$0.263DeepInfra3h ago
GLM-5.2Frontier
zhipuai/glm-5.2
Jun '26Open1M5$0.75$2.4$1.16DeepInfra2h ago•
Kimi K2.7 Code
moonshotai/kimi-k2.7-code
Jun '26Open262k2$0.68$3.4$1.36DeepInfra2h ago
Claude Fable 5Frontier
anthropic/claude-fable-5
Jun '26Closed1M4$10.0$50.0$20.0Anthropic3h ago•
Nemotron 3 Ultra 550B A55BFrontier
nvidia/nemotron-3-ultra-550b-a55b
Jun '26Open1M2$0.60$2.4$1.05Fireworks AI5h ago•
MiniMax-M3Frontier
minimax/minimax-m3
Jun '26Open524k3$0.28$1.1$0.485DeepInfra3h ago•
Step 3.7 Flash
stepfun/step-3.7-flash
May '26Open256k1$0.20$1.15$0.438DeepInfra3h ago
Claude-Opus-4.8Frontier
anthropic/claude-opus-4-8
May '26Closed1M4$5.0$25.0$10.0AWS Bedrock3h ago•
Qwen3.7 MaxFrontier
alibaba/qwen3.7-max
May '26Closed1M2$1.25$3.75$1.88Together AI3h ago•
Gemini 3.5 Flash
google/gemini-3.5-flash
May '26Closed1M3$1.5$9.0$3.38Google Gemini API3h ago•
Gemini 3.1 Flash Lite
google/gemini-3.1-flash-lite
May '26Closed1M3$0.25$1.5$0.563DeepInfra3h ago•
Mistral Medium 3.5
mistral/mistral-medium-2604
Apr '26Open262k1$1.5$7.5$3.0Mistral5h ago•
Mistral Medium (latest)
mistral/mistral-medium-latest
Apr '26Open262k1$1.5$7.5$3.0Mistral5h ago•
Nemotron 3 Nano Omni
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
Apr '26Open256k1$0.20$0.80$0.35DeepInfra3h ago
DeepSeek V4 Flash
deepseek/deepseek-v4-flash
Apr '26Open1M1$0.09$0.18$0.113DeepInfra3h ago
DeepSeek V4 ProFrontier
deepseek/deepseek-v4-pro
Apr '26Open1M1$1.3$2.6$1.63DeepInfra3h ago
GPT 5.5Frontier
openai/gpt-5.5
Apr '26Closed1.1M3$5.0$30.0$11.25OpenAI2h ago•
GPT-5.5 ProFrontier
openai/gpt-5.5-pro
Apr '26Closed1.1M1$30.0$180.0$67.5OpenAI5h ago•
Qwen3.6 27B
alibaba/qwen3.6-27b
Apr '26Open262k2$0.32$3.2$1.04DeepInfra3h ago•
Gemini Embedding 2
google/gemini-embedding-2
Apr '26Closed8k1$0.20$0$0.15Google Gemini API5h ago•
MiMo-V2.5
xiaomi/mimo-v2.5
Apr '26Open1M1$0.14$0.28$0.175DeepInfra3h ago
MiMo-V2.5-ProFrontier
xiaomi/mimo-v2.5-pro
Apr '26Open1M1$1.0$3.0$1.5DeepInfra3h ago
Kimi K2.6Frontier
moonshotai/kimi-k2.6
Apr '26Open256k2$0.75$3.5$1.44DeepInfra2h ago
Grok 4.3Frontier
xai/grok-4.3
Apr '26Closed1M3$1.25$2.5$1.56Google Vertex AI2h ago•
Umans Flash
alibaba/qwen3.6-35b-a3b
Apr '26Open262k1$0.10$0.95$0.313DeepInfra3h ago
Claude 4.7 OpusFrontier
anthropic/claude-opus-4-7
Apr '26Closed1M4$5.0$25.0$10.0Anthropic3h ago•
GLM-5.1Frontier
zhipuai/glm-5.1
Apr '26Open200k3$1.05$3.5$1.66DeepInfra2h ago•
Gemma 4 26B A4B IT
google/gemma-4-26b-a4b-it
Apr '26Open262k3$0.07$0.34$0.138DeepInfra3h ago•
Gemma 4
google/gemma-4-31b-it
Apr '26Open131k2$0.09$0.34$0.152DeepInfra3h ago•
Qwen3.6 Plus
alibaba/qwen3.6-plus
Apr '26Closed1M1$0.50$3.0$1.13Together AI5h ago•
Gemma 4 E2B IT
google/gemma-4-e2b-it
Apr '26Open33k1$0.04$0.08$0.05AWS Bedrock5h ago•
Gemma 4 E4B IT
google/gemma-4-e4b-it
Apr '26Open131k1$0.02$0.10$0.04DeepInfra3h ago
MiniMax-M2.7Frontier
minimax/minimax-m2.7
Mar '26Open197k2$0.25$1.0$0.438DeepInfra3h ago•
GPT 5.4 Mini
openai/gpt-5.4-mini
Mar '26Closed400k2$0.75$4.5$1.69OpenAI2h ago•
GPT 5.4 Nano
openai/gpt-5.4-nano
Mar '26Closed400k2$0.20$1.25$0.463Azure AI Foundry2h ago•
Small 4
mistral/mistral-small-2603
Mar '26Open262k1$0.15$0.60$0.263Mistral5h ago•
Mistral Small (latest)
mistral/mistral-small-latest
Mar '26Open256k1$0.15$0.60$0.263Mistral5h ago•
Nemotron 3 Super
nvidia/nemotron-3-super-120b-a12b
Mar '26Open262k1$0.15$0.65$0.275AWS Bedrock5h ago•
Grok 4.20 Non-Reasoning
xai/grok-4.20-0309-non-reasoning
Mar '26Closed2M1$1.25$2.5$1.56Google Vertex AI5h ago•
Grok 4.20Frontier
xai/grok-4.20-0309-reasoning
Mar '26Closed1M1$1.25$2.5$1.56Google Vertex AI5h ago•
GPT 5.4Frontier
openai/gpt-5.4
Mar '26Closed1.1M3$2.5$15.0$5.63OpenAI2h ago•
GPT-5.4 ProFrontier
openai/gpt-5.4-pro
Mar '26Closed1.1M2$30.0$180.0$67.5Azure AI Foundry2h ago•
Gemini 3.1 Flash Lite Preview
google/gemini-3.1-flash-lite-preview
Mar '26Closed1M1$0.25$1.5$0.563Google Gemini API5h ago•
GPT-5.3 Chat Latest
openai/gpt-5.3-chat-latest
Mar '26Closed128k1$1.75$14.0$4.81OpenAI5h ago•
GPT-4o
openai/gpt-4o-2024-11-20
Feb '26Closed128k1$2.5$10.0$4.38OpenAI5h ago•
Qwen3.5 9B
alibaba/qwen3.5-9b
Feb '26Open262k2$0.10$0.15$0.113DeepInfra3h ago•
Qwen3.5 122B-A10B
alibaba/qwen3.5-122b-a10b
Feb '26Open262k1$0.29$2.4$0.818DeepInfra3h ago
Qwen3.5 27B
alibaba/qwen3.5-27b
Feb '26Open262k1$0.26$2.6$0.845DeepInfra3h ago
Qwen3.5 35B-A3B
alibaba/qwen3.5-35b-a3b
Feb '26Open256k1$0.14$1.0$0.355DeepInfra3h ago
Gemini 3.1 Pro PreviewFrontier
google/gemini-3.1-pro-preview
Feb '26Closed1M2$2.0$12.0$4.5Google Gemini API5h ago•
Gemini 3.1 Pro Preview Custom ToolsFrontier
google/gemini-3.1-pro-preview-customtools
Feb '26Closed1M2$2.0$12.0$4.5Google Gemini API5h ago•
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6
Feb '26Closed1M4$3.0$15.0$6.0Google Vertex AI3h ago•
Qwen 3.5 397B
alibaba/qwen3.5-397b-a17b
Feb '26Open128k2$0.45$3.0$1.09DeepInfra3h ago•
Seed 2.0 Code
bytedance-seed/seed-2.0-code
Feb '26Closed256k1$0.50$3.0$1.13DeepInfra3h ago