AINews Portal

💲 LLM API Pricing

Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 15h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.

Sort:Input $Output $Arena EloBest valueContextName275 models match · showing 50
Cost calculator — what would your workload cost on each model?
ModelInput $/MOutput $/M
minimax.minimax-m2.1bedrock$0.30$1.20
cohere.command-light-text-v14bedrock$0.30$0.60
meta.llama3-8b-instruct-v1:0bedrock$0.30$0.60
minimax.minimax-m2.1bedrock$0.30$1.20
minimax.minimax-m2.5bedrock$0.30$1.20
minimax.minimax-m2.1bedrock$0.30$1.20
amazon.titan-text-lite-v1bedrock$0.30$0.40
minimax.minimax-m2.5bedrock$0.30$1.20
meta.llama3-8b-instruct-v1:0bedrock$0.30$0.60
meta.llama3-8b-instruct-v1:0bedrock$0.30$0.60
meta.llama3-8b-instruct-v1:0bedrock$0.30$0.60
meta.llama3-8b-instruct-v1:0bedrock$0.30$2.65
amazon.titan-text-lite-v1bedrock$0.30$0.40
mistral.mistral-7b-instruct-v0:2bedrock$0.25$0.34
nvidia.nemotron-nano-12b-v2bedrock$0.24$0.72
nvidia.nemotron-nano-12b-v2bedrock$0.24$0.72
qwen.qwen3-next-80b-a3bbedrock$0.23$1.86
nvidia.nemotron-super-3-120bbedrock$0.23$1.01
us.meta.llama3-1-8b-instruct-v1:0bedrock$0.22$0.22
meta.llama3-1-8b-instruct-v1:0bedrock$0.22$0.22
ai21.jamba-1-5-mini-v1:0bedrock$0.20$0.40
mistral.mistral-7b-instruct-v0:2bedrock$0.20$0.26
mistral.mistral-7b-instruct-v0:2bedrock$0.20$0.26
mistral.mistral-7b-instruct-v0:2bedrock$0.20$0.26
amazon.titan-text-express-v1bedrock$0.20$0.60
meta.llama3-2-3b-instruct-v1:0bedrock$0.20$0.20
eu.meta.llama3-2-3b-instruct-v1:0bedrock$0.20$0.20
meta.llama3-2-3b-instruct-v1:0bedrock$0.19$0.19
eu.meta.llama3-2-3b-instruct-v1:0bedrock$0.19$0.19
qwen.qwen3-next-80b-a3bbedrock$0.18$1.41
qwen.qwen3-next-80b-a3bbedrock$0.18$1.41
qwen.qwen3-next-80b-a3bbedrock$0.18$1.45
nvidia.nemotron-super-3-120bbedrock$0.18$0.78
openai.gpt-oss-120b-1:0bedrock$0.18$0.72
openai.gpt-oss-120b-1:0bedrock$0.18$0.72
mistral.mistral-7b-instruct-v0:2bedrock$0.18$0.24
qwen.qwen3-next-80b-a3bbedrock$0.18$1.45
nvidia.nemotron-super-3-120bbedrock$0.18$0.78
meta.llama3-2-3b-instruct-v1:0bedrock$0.17$0.17
mistral.mistral-7b-instruct-v0:2bedrock$0.17$0.23
eu.meta.llama3-2-3b-instruct-v1:0bedrock$0.17$0.17
meta.llama3-2-11b-instruct-v1:0bedrock$0.16$0.16
us.meta.llama3-2-11b-instruct-v1:0bedrock$0.16$0.16
mistral.voxtral-small-24b-2507bedrock$0.16$0.47
mistral.mistral-7b-instruct-v0:2bedrock$0.16$0.22
qwen.qwen3-next-80b-a3bbedrock$0.15$1.24
mistral.mistral-7b-instruct-v0:2bedrock$0.15$0.20
meta.llama3-2-3b-instruct-v1:0bedrock$0.15$0.15
us.meta.llama3-2-3b-instruct-v1:0bedrock$0.15$0.15
mistral.mistral-7b-instruct-v0:2bedrock$0.15$0.20
Recent price changes

Price cuts are green — they make AI cheaper for everyone.