AINews Portal

💲 LLM API Pricing

Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 12h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.

Sort:Input $Output $Arena EloBest valueContextName328 models match · showing 50
Cost calculator — what would your workload cost on each model?
ModelInput $/MOutput $/M
llama-v2-13b-chatfireworks_ai$0.20$0.20
llama-v3p2-11b-vision-instructfireworks_ai$0.20$0.20
llama-v2-13bfireworks_ai$0.20$0.20
llama-guard-3-8bfireworks_ai$0.20$0.20
firesearch-ocr-v6fireworks_ai$0.20$0.20
firellava-13bfireworks_ai$0.20$0.20
mythomax-l2-13b💬fireworks_ai$0.20$0.20
nous-capybara-7b-v1p9fireworks_ai$0.20$0.20
nous-hermes-llama2-13bfireworks_ai$0.20$0.20
dobby-mini-unhinged-plus-llama-3-1-8bfireworks_ai$0.20$0.20
nous-hermes-llama2-7bfireworks_ai$0.20$0.20
nvidia-nemotron-nano-12b-v2fireworks_ai$0.20$0.20
nvidia-nemotron-nano-9b-v2fireworks_ai$0.20$0.20
openchat-3p5-0106-7bfireworks_ai$0.20$0.20
openhermes-2-mistral-7bfireworks_ai$0.20$0.20
openhermes-2p5-mistral-7bfireworks_ai$0.20$0.20
gpt-oss-120b💬fireworks_ai$0.15$0.60
gpt-oss-120b💬fireworks_ai$0.15$0.60
ultramarine-1-flash-usfireworks_ai$0.15$0.50
glm-flash-latest💬fireworks_ai$0.15$0.50
qwen3-coder-30b-a3b-instruct💻fireworks_ai$0.15$0.60
deepseek-v4p1-flash-1017-spotfireworks_ai$0.15$0.60
qwen3-vl-30b-a3b-instruct👁️fireworks_ai$0.15$0.60
qwen3-vl-30b-a3b-thinking🧮fireworks_ai$0.15$0.60
deepseek-v4p1-flash-1017-flexfireworks_ai$0.15$0.60
deepseek-v4p1-flash-spotfireworks_ai$0.15$0.60
qwen3-30b-a3b💬fireworks_ai$0.15$0.60
glm-5p3-flashfireworks_ai$0.15$0.50
minimax-m3p1-flashfireworks_ai$0.15$0.60
llama4-scout-instruct-basicfireworks_ai$0.15$0.60
glm-5p3-flashfireworks_ai$0.15$0.50
deepseek-v4-flash💬fireworks_ai$0.14$0.28
deepseek-v4-flash💬fireworks_ai$0.14$0.28
deepseek-r1-distill-qwen-1p5bfireworks_ai$0.10$0.10
llama-v3p1-70b-instruct-1bfireworks_ai$0.10$0.10
llama-v3p1-405b-instruct-longfireworks_ai$0.10$0.10
llama-v3p1-8b-instructfireworks_ai$0.10$0.10
qwen2-vl-2b-instructfireworks_ai$0.10$0.10
qwen2p5-0p5b-instructfireworks_ai$0.10$0.10
qwen2p5-1p5b-instructfireworks_ai$0.10$0.10
llama-v2-70bfireworks_ai$0.10$0.10
deepseek-coder-1b-basefireworks_ai$0.10$0.10
qwen2p5-coder-0p5bfireworks_ai$0.10$0.10
qwen2p5-coder-0p5b-instructfireworks_ai$0.10$0.10
llama-v3p2-1b-instructfireworks_ai$0.10$0.10
flux-1-schnellfireworks_ai$0.10$0.10
flux-1-devfireworks_ai$0.10$0.10
qwen3-0p6bfireworks_ai$0.10$0.10
qwen3-1p7bfireworks_ai$0.10$0.10
nemotron-nano-v2-12b-vlfireworks_ai$0.10$0.10
Recent price changes

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