AINews Portal

💲 LLM API Pricing

Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 19h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.

Sort:Input $Output $Arena EloBest valueContextName4258 models match · showing 50
Cost calculator — what would your workload cost on each model?
ModelInput $/MOutput $/M
qwen.qwen3-next-80b-a3bbedrock$0.18$1.45
qwen.qwen3-next-80b-a3bbedrock$0.18$1.41
nvidia.nemotron-super-3-120bbedrock_converse$0.18$0.78
openai.gpt-oss-120b-1:0bedrock_converse$0.18$0.71
qwen.qwen3-next-80b-a3bbedrock$0.18$1.41
qwen.qwen3-next-80b-a3bbedrock$0.18$1.45
openai.gpt-oss-safeguard-120bbedrock_converse$0.18$0.71
mistral.ministral-3-8b-instructbedrock_mantle$0.18$0.18
gpt-oss-120b💬replicate$0.18$0.72
writer.palmyra-vision-7bbedrock_converse$0.18$0.72
qwen.qwen3-32b-v1:0bedrock_converse$0.18$0.71
nvidia.nemotron-super-3-120bbedrock_mantle$0.18$0.78
openai.gpt-oss-120bbedrock_mantle$0.18$0.70
qwen.qwen3-32b-v1:0bedrock_converse$0.18$0.70
openai.gpt-oss-safeguard-120bbedrock_converse$0.18$0.70
openai.gpt-oss-120b-1:0bedrock_converse$0.18$0.70
writer.palmyra-vision-7bbedrock_converse$0.18$0.72
openai.gpt-oss-safeguard-120bbedrock_mantle$0.18$0.70
qwen.qwen3-32bbedrock_mantle$0.18$0.70
qwen.qwen3-coder-30b-a3b-instructbedrock_mantle$0.18$0.70
writer.palmyra-vision-7bbedrock_mantle$0.18$0.72
nvidia.nemotron-super-3-120bbedrock_converse$0.18$0.78
nvidia.nemotron-super-3-120bbedrock_converse$0.18$0.78
nvidia.nemotron-super-3-120bbedrock_mantle$0.18$0.78
openai.gpt-oss-120bbedrock_mantle$0.18$0.73
openai.gpt-oss-safeguard-120bbedrock_mantle$0.18$0.73
mistral.ministral-3-8b-instructbedrock_converse$0.18$0.18
llama-4-scout-17b-16e-instructnovita$0.18$0.59
nvidia.nemotron-super-3-120bbedrock_mantle$0.18$0.78
nvidia.nemotron-super-3-120bbedrock_converse$0.18$0.78
writer.palmyra-vision-7bbedrock_converse$0.18$0.72
qwen.qwen3-32bbedrock_mantle$0.18$0.73
qwen.qwen3-coder-30b-a3b-instructbedrock_mantle$0.18$0.73
writer.palmyra-vision-7bbedrock_mantle$0.18$0.72
qwen3.8-27b💬clf_ai_gateway$0.18$1.28
writer.palmyra-vision-7bbedrock_converse$0.18$0.72
deepseek-v4.1-flash-1017💬gmi$0.18$0.72
DeepSeek-V4.1-Flash💬gmi$0.18$0.72
openai.gpt-oss-safeguard-120bbedrock_converse$0.18$0.70
nvidia.nemotron-super-3-120bbedrock_converse$0.18$0.78
mistral.ministral-3-8b-instructbedrock_converse$0.18$0.18
nvidia.nemotron-super-3-120bbedrock_mantle$0.18$0.78
mistral.ministral-3-8b-instructbedrock_mantle$0.18$0.18
glm-4.5-air💬kyma$0.18$1.18
deepseek-v4-flash💬clf_ai_gateway$0.18$0.53
glm-5.3-flash💬kyma$0.17$0.57
qwen3-5-397b-a17b💬empiriolabs$0.17$1.03
meta.llama4-scout-17b-instruct-v1:0bedrock_converse$0.17$0.66
us.meta.llama4-scout-17b-instruct-v1:0bedrock_converse$0.17$0.66
eu.meta.llama3-2-3b-instruct-v1:0bedrock$0.17$0.17
Recent price changes

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