AINews Portal

💲 LLM API Pricing

Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 16h. 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
kimi-k2-instruct-0905fireworks_ai$0.60$2.50
kimi-k2-instructfireworks_ai$0.60$2.50
qwen3.5-397b-a17b💬streamlake$0.60$3.60
Qwen3.6-27B💬wandb$0.60$3.60
qwen.qwen3-coder-nextbedrock$0.60$1.44
glm-4p7fireworks_ai$0.60$2.20
Kimi-K2.7-Code💻wandb$0.60$3.00
qwen.qwen3-coder-nextbedrock$0.60$1.44
GLM-4.5-FP8gmi$0.60$2.20
GLM-4.6💬together_ai$0.60$2.20
qwen3.6-27b💬streamlake$0.60$3.60
qwen.qwen3-coder-nextbedrock_mantle$0.60$1.44
qwen.qwen3-coder-nextbedrock$0.60$1.44
glm-4.5v💬novita$0.60$1.80
Meta-Llama-3.3-70B-Instructsambanova$0.60$1.20
MiniMax-M2.7💬sambanova$0.60$2.40
deepseek.v3-v1:0bedrock_converse$0.60$1.74
qwen.qwen3-coder-nextbedrock$0.60$1.44
gpt-audio-mini-2025-10-06azure$0.60$2.40
gpt-audio-mini🎙️azure$0.60$2.40
Llama-3.1-Nemotron-70B-Instructdeepinfra$0.60$0.60
deepseek.v3.1bedrock_mantle$0.60$1.74
nemotron-3-ultra-550b-a55b💬together_ai$0.60$3.60
qwen3.5-397b-a17b💬novita$0.60$3.60
kimi-k2.5💬novita$0.60$3.00
qwen.qwen3-coder-nextbedrock$0.60$1.44
Mixtral-8x7B-Instruct-v0.1together_ai$0.60$0.60
glm-4.7-hnovita$0.60$2.20
DeepSeek-V3.1together_ai$0.60$1.70
sonar-medium-chatperplexity$0.60$1.80
qwen.qwen3-coder-nextbedrock_mantle$0.60$1.44
qwen.qwen3-coder-nextbedrock$0.60$1.44
Qwen3.5-397B-A17B💬together_ai$0.60$3.60
mistral.magistral-small-2509bedrock_mantle$0.60$1.80
moonshotai.kimi-k2.5bedrock$0.60$3.00
moonshotai.kimi-k2-thinkingbedrock$0.60$2.50
qwen.qwen3-coder-nextbedrock$0.60$1.44
minimax-m2.5-highspeednovita$0.60$2.40
xai.grok-3-mini-fastoci$0.60$4.00
kimi-k2-thinking🧮azure_ai$0.60$2.50
qwen3.5-397b-a17b💬scaleway$0.60$3.60
Qwen3.5-397B-A17B💬nebius$0.60$3.60
DeepSeek-V4.1-Flash-Fastbaseten$0.60$2.40
Qwen3.5-397B-A17B💬gmi$0.60$3.60
kimi-k2.5💬azure_ai$0.60$3.00
Llama-3_1-Nemotron-Ultra-253B-v1nebius$0.60$1.80
minimax-m2.7-highspeednovita$0.60$2.40
Llama-3.1-Nemotron-Ultra-253B-v1nebius$0.60$1.80
glm-4.5💬novita$0.60$2.20
NVIDIA-Nemotron-3-Ultra-550B-A55Bbaseten$0.60$2.40
Recent price changes

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