Reference

AI Model Pricing

Current pricing for 762 AI models across 86 providers, including OpenAI, Anthropic, Google Gemini, xAI, DeepSeek, Deepgram, and ElevenLabs. Token rates are USD per 1M tokens (input, output, and cached input); audio and image models are shown in their natural billing unit.

Generated from the SuperPenguin pricing catalog. Rates last updated September 1, 2026.

762 models

Language models (per 1M tokens)

ModelProviderInputOutputCache readInput (audio)Output (audio)
fw-gpt-oss-120bOpenAI$0.15$0.6$0.015
fw-gpt-oss-20bOpenAI$0.07$0.3$0.035
gpt-3.5-turbo-instructOpenAI$1.50$2.00
gpt-4.1OpenAI$2.00$8.00$0.5
gpt-4.1-miniOpenAI$0.4$1.60$0.1
gpt-4.1-nanoOpenAI$0.1$0.4$0.025
gpt-4oOpenAI$2.50$10.00$1.25
gpt-4o-audioOpenAI$2.50$10.00$40.00$80.00
gpt-4o-miniOpenAI$0.15$0.6$0.075
gpt-4o-mini-transcribeOpenAI$1.25$5.00
gpt-4o-mini-ttsOpenAI$0.6$12.00
gpt-4o-transcribeOpenAI$2.50$10.00
gpt-5OpenAI$1.25$10.00$0.125
gpt-5-codexOpenAI$1.25$10.00$0.125
gpt-5-fastOpenAI$2.50$20.00$0.25
gpt-5-miniOpenAI$0.25$2.00$0.025
gpt-5-nanoOpenAI$0.05$0.4$0.005
gpt-5-proOpenAI$15.00$120.00
gpt-5.1OpenAI$1.25$10.00$0.125
gpt-5.1-codexOpenAI$1.25$10.00$0.125
gpt-5.1-codex-maxOpenAI$1.25$10.00$0.125
gpt-5.1-codex-miniOpenAI$0.25$2.00$0.025
gpt-5.2OpenAI$1.75$14.00$0.175
gpt-5.2-codexOpenAI$1.75$14.00$0.175
gpt-5.2-proOpenAI$21.00$168.00
gpt-5.3-codexOpenAI$1.75$14.00$0.175
gpt-5.4*OpenAI$2.50$15.00$0.25
gpt-5.4-miniOpenAI$0.75$4.50$0.075
gpt-5.4-nanoOpenAI$0.2$1.25$0.02
gpt-5.4-pro*OpenAI$30.00$180.00
gpt-5.5*OpenAI$5.00$30.00$0.5
gpt-5.5-pro*OpenAI$30.00$180.00
gpt-5.6-luna*OpenAI$1.00$6.00$0.1
gpt-5.6-sol*OpenAI$5.00$30.00$0.5
gpt-5.6-terra*OpenAI$2.50$15.00$0.25
gpt-image-1OpenAI$5.00$40.00$1.25
gpt-image-2OpenAI$5.00$30.00$1.25
gpt-oss-120bOpenAI$0.15$0.6
gpt-oss-20bOpenAI$0.05$0.2
gpt-realtime-1.5OpenAI$4.00$16.00$0.4$32.00$64.00
gpt-realtime-2OpenAI$4.00$24.00$0.4$32.00$64.00
o3OpenAI$2.00$8.00$0.5
o4-miniOpenAI$1.10$4.40$0.275
omni-moderationOpenAI$0$0
text-embedding-3-largeOpenAI$0.13$0
text-embedding-3-smallOpenAI$0.02$0
text-embedding-ada-002OpenAI$0.1$0
claude-4-sonnet-1mAnthropic$6.00$22.50$0.6
claude-4.6-opus-fastAnthropic$30.00$150.00$3.00
claude-fable-5Anthropic$10.00$50.00$1.00
claude-haiku-3-5Anthropic$0.8$4.00$0.08
claude-haiku-4-5Anthropic$1.00$5.00$0.1
claude-mythos-5Anthropic$10.00$50.00$1.00
claude-opus-4Anthropic$15.00$75.00$1.50
claude-opus-4-1Anthropic$15.00$75.00$1.50
claude-opus-4-5Anthropic$5.00$25.00$0.5
claude-opus-4-6Anthropic$5.00$25.00$0.5
claude-opus-4-7Anthropic$5.00$25.00$0.5
claude-opus-4-7-fastAnthropic$30.00$150.00$3.00
claude-opus-4-8Anthropic$5.00$25.00$0.5
claude-opus-4-8-fastAnthropic$10.00$50.00$1.00
claude-sonnet-4Anthropic$3.00$15.00$0.3
claude-sonnet-4-5Anthropic$3.00$15.00$0.3
claude-sonnet-4-6Anthropic$3.00$15.00$0.3
claude-sonnet-5Anthropic$3.00$15.00$0.3
gemini-2.0-flashGoogle Gemini$0.1$0.4$0.025
gemini-2.0-flash-liteGoogle Gemini$0.075$0.3
gemini-2.5-flashGoogle Gemini$0.3$2.50$0.03
gemini-2.5-flash-liteGoogle Gemini$0.1$0.4$0.01
gemini-2.5-pro*Google Gemini$1.25$10.00$0.125
gemini-3-flashGoogle Gemini$0.5$3.00$0.05
gemini-3-flash-previewGoogle Gemini$0.5$3.00$0.05
gemini-3-proGoogle Gemini$2.00$12.00$0.2
gemini-3.1-flash-lite-previewGoogle Gemini$0.25$1.50$0.025
gemini-3.1-proGoogle Gemini$2.00$12.00$0.2
gemini-3.1-pro-preview*Google Gemini$2.00$12.00$0.2
gemini-2.5-flash-lite-previewGoogle$0.1$0.4$0.01
gemini-3-pro-image-previewGoogle$2.00$12.00$0.2
gemini-3.1-flash-liteGoogle$0.25$1.50$0.025
gemini-3.5-flashGoogle$1.50$9.00$0.15
grok-3xAI$3.00$15.00
grok-3-fastxAI$5.00$25.00
grok-3-minixAI$0.3$0.5
grok-4.20xAI$2.00$6.00$0.2
grok-4.20-0309-non-reasoningxAI$1.25$2.50$0.2
grok-4.20-0309-reasoningxAI$1.25$2.50$0.2
grok-4.20-multi-agent-0309xAI$1.25$2.50$0.2
grok-4.3xAI$1.25$2.50$0.2
grok-4.5xAI$2.00$6.00$0.5
grok-build-0.1xAI$1.00$2.00$0.2
deepseek-chatDeepSeek$0.2002$0.8001
deepseek-chat-v3-0324DeepSeek$0.24$0.9$0.135
deepseek-chat-v3.1DeepSeek$0.21$0.79$0.13
deepseek-r1DeepSeek$3.00$7.00
deepseek-r1-0528DeepSeek$0.5$2.15$0.35
deepseek-r1-distill-llama-70bDeepSeek$0.8$0.8
deepseek-v3DeepSeek$0.6$1.70
deepseek-v3.1-terminusDeepSeek$0.27$0.95$0.13
deepseek-v3.2DeepSeek$0.2288$0.3432$0.02288
deepseek-v3.2-expDeepSeek$0.27$0.41
deepseek-v4-flashDeepSeek$0.14$0.28$0.028
deepseek-v4-proDeepSeek$1.74$3.48$0.145
DeepSeek-V4-ProDeepSeek$1.74$3.48$0.2
claude-3-5-haikuAWS Bedrock$0.8$4.00
claude-3-5-sonnetAWS Bedrock$3.00$15.00
devstral-2-123bAWS Bedrock$0.4$2.00
gemma-3-12b-itAWS Bedrock$0.09$0.29
gemma-3-27b-itAWS Bedrock$0.23$0.38
gemma-3-4b-itAWS Bedrock$0.04$0.08
gemma-4-26b-a4bAWS Bedrock$0.13$0.4
gemma-4-31bAWS Bedrock$0.14$0.4
gemma-4-e2bAWS Bedrock$0.04$0.08
glm-4-7AWS Bedrock$0.6$2.20
glm-4-7-flashAWS Bedrock$0.07$0.4
glm5AWS Bedrock$1.00$3.20
gpt-5-4AWS Bedrock$3.30$19.80
gpt-oss-120bAWS Bedrock$0.15$0.6
gpt-oss-20bAWS Bedrock$0.07$0.3
gpt-oss-safeguard-120bAWS Bedrock$0.15$0.6
gpt-oss-safeguard-20bAWS Bedrock$0.07$0.2
grok-4-3AWS Bedrock$1.25$2.50
kimi-k2-5AWS Bedrock$0.6$3.00
kimi-k2-thinkingAWS Bedrock$0.6$2.50
llama-3-1-405bAWS Bedrock$3.00$3.00
llama-3-1-70bAWS Bedrock$0.72$0.72
llama-3-1-70b-latency-optimizedAWS Bedrock$0.9$0.9
llama-3-1-8bAWS Bedrock$0.22$0.22
llama-3-2-11bAWS Bedrock$0.16$0.16
llama-3-2-1bAWS Bedrock$0.1$0.1
llama-3-2-3bAWS Bedrock$0.15$0.15
llama-3-2-90bAWS Bedrock$0.72$0.72
llama-3-3-70bAWS Bedrock$0.72$0.72
llama-3-3-70b-customAWS Bedrock$0.72$0.72
llama-3-70bAWS Bedrock$2.65$3.50
llama-3-8bAWS Bedrock$0.3$0.6
llama-4-maverick-17bAWS Bedrock$0.24$0.97
llama-4-scout-17bAWS Bedrock$0.17$0.66
magistral-small-2509AWS Bedrock$0.5$1.50
minimax-m2AWS Bedrock$0.3$1.20
minimax-m2-1AWS Bedrock$0.3$1.20
minimax-m2-5AWS Bedrock$0.3$1.20
ministral-3-14b-instructAWS Bedrock$0.2$0.2
ministral-3-3b-instructAWS Bedrock$0.1$0.1
ministral-3-8b-instructAWS Bedrock$0.15$0.15
mistral-largeAWS Bedrock$4.00$12.00
mistral-large-3-675b-instructAWS Bedrock$0.5$1.50
nemotron-nano-12b-v2AWS Bedrock$0.2$0.6
nemotron-nano-3-30bAWS Bedrock$0.06$0.24
nemotron-nano-9b-v2AWS Bedrock$0.06$0.23
nemotron-super-3-120bAWS Bedrock$0.15$0.65
nova-liteAWS Bedrock$0.06$0.24
nova-proAWS Bedrock$0.8$3.20
nvidia-nemotron-3-super-120b-a12bAWS Bedrock$0.18$0.78
palmyra-vision-7bAWS Bedrock$0.15$0.6
qwen3-235b-a22b-2507AWS Bedrock$0.22$0.88
qwen3-32bAWS Bedrock$0.15$0.6
qwen3-coder-30b-a3bAWS Bedrock$0.15$0.6
qwen3-coder-30b-a3b-instructAWS Bedrock$0.15$0.6
qwen3-coder-480b-a35bAWS Bedrock$0.54$2.18
qwen3-coder-480b-a35b-instructAWS Bedrock$0.45$1.80
qwen3-coder-nextAWS Bedrock$0.5$1.20
qwen3-next-80b-a3b-instructAWS Bedrock$0.14$1.20
qwen3-vl-235b-a22bAWS Bedrock$0.53$2.66
qwen3-vl-235b-a22b-instructAWS Bedrock$0.53$2.66
r1AWS Bedrock$1.35$5.40
titan-text-expressAWS Bedrock$0.2$0.6
v3-1AWS Bedrock$0.58$1.68
v3-2AWS Bedrock$0.62$1.85
voxtral-mini-3b-2507AWS Bedrock$0.04$0.04
voxtral-small-24b-2507AWS Bedrock$0.1$0.3
az-cohere-command-aAzure OpenAI$2.50$10.00
az-cohere-command-a-plusAzure OpenAI$0.8$3.20
az-computer-useAzure OpenAI$3.00$12.00
az-deepseek-mai-ds-r1Azure OpenAI$1.35$5.40
az-deepseek-r1Azure OpenAI$1.35$5.40
az-deepseek-v3Azure OpenAI$1.14$4.56
az-deepseek-v3.1Azure OpenAI$1.23$4.94
az-deepseek-v3.2Azure OpenAI$0.58$1.68
az-deepseek-v3.2-spAzure OpenAI$0.58$1.68
az-deepseek-v4-flashAzure OpenAI$0.19$0.51$0.028
az-deepseek-v4-proAzure OpenAI$1.74$3.48$0.145
az-fireworks-fw-deepseek-v3.2Azure OpenAI$0.62$1.85
az-fireworks-fw-deepseek-v4-proAzure OpenAI$1.93$3.83
az-fireworks-fw-glm-5Azure OpenAI$1.10$3.52$0.22
az-fireworks-fw-glm-5.1Azure OpenAI$1.54$4.84$0.286
az-fireworks-fw-gpt-oss-120bAzure OpenAI$0.165$0.66$0.082
az-fireworks-fw-kimi-k2.5Azure OpenAI$0.66$3.30$0.11
az-fireworks-fw-kimi-k2.6Azure OpenAI$1.05$4.40$0.176
az-fireworks-fw-minimax-2.7Azure OpenAI$0.33$1.32$0.066
az-fireworks-fw-minimax-m2.5Azure OpenAI$0.33$1.32$0.033
az-gpt-35-turboAzure OpenAI$0.5$1.50
az-gpt-35-turbo-1106Azure OpenAI$1.00$2.00
az-gpt-35-turbo-16kAzure OpenAI$3.00$4.00
az-gpt-35-turbo-4kAzure OpenAI$1.50$2.00
az-gpt-35-turbo-instructAzure OpenAI$1.50$2.00
az-gpt-35-turbo16kAzure OpenAI$3.00$4.00
az-gpt-35-turbo4kAzure OpenAI$1.50$2.00
az-gpt-4-32kAzure OpenAI$60.00$120.00
az-gpt-4-8kAzure OpenAI$30.00$60.00
az-gpt-4-turboAzure OpenAI$10.00$30.00
az-gpt-4-turbo-128kAzure OpenAI$10.00$30.00
az-gpt-4-turbo-vision-128kAzure OpenAI$10.00$30.00
az-gpt-4.1Azure OpenAI$2.00$8.00$0.5
az-gpt-4.1-miniAzure OpenAI$0.4$1.60$0.1
az-gpt-4.1-nanoAzure OpenAI$0.1$0.4$0.025
az-gpt-4.5Azure OpenAI$75.00$150.00$37.50
az-gpt-4oAzure OpenAI$2.50$10.00$1.25
az-gpt-4o-miniAzure OpenAI$0.15$0.6$0.075
az-gpt-5Azure OpenAI$1.25$10.00$0.125
az-gpt-5-chatAzure OpenAI$1.25$10.00$0.125
az-gpt-5-miniAzure OpenAI$0.25$2.00$0.025
az-gpt-5-nanoAzure OpenAI$0.05$0.4$0.005
az-gpt-oss-120bAzure OpenAI$0.15$0.6
az-grok-3Azure OpenAI$3.00$15.00
az-grok-3-miniAzure OpenAI$0.25$1.27
az-grok-4Azure OpenAI$3.00$15.00
az-grok-4.1Azure OpenAI$0.2$0.5
az-grok-4.2Azure OpenAI$1.25$2.50
az-grok-4.3Azure OpenAI$1.25$2.50$0.2
az-grok-4.3-lAzure OpenAI$2.50$5.00$0.4
az-grok-code-fast-1Azure OpenAI$0.2$1.50
az-grok4-fastAzure OpenAI$0.2$0.5
az-kimi-k2-thinkingAzure OpenAI$0.6$2.50
az-kimi-k2.5-thinkingAzure OpenAI$0.6$3.00
az-kimi-k2.6-thinkingAzure OpenAI$0.95$4.00
az-kimi-k2.7-codeAzure OpenAI$0.95$4.00$0.19
az-llama-3.3-70bAzure OpenAI$0.71$0.71
az-llama-4-maverick-17bAzure OpenAI$0.25$1.00
az-mistral-codestralAzure OpenAI$0.3$0.9
az-mistral-large-3Azure OpenAI$0.5$1.50
az-mistral-mm3.5Azure OpenAI$1.50$7.50
az-o1Azure OpenAI$15.00$60.00$7.50
az-o1-miniAzure OpenAI$1.10$4.40$0.55
az-o1-previewAzure OpenAI$15.00$60.00$7.50
az-o1-proAzure OpenAI$150.00$600.00$75.00
az-o3Azure OpenAI$2.00$8.00$0.5
az-o3-miniAzure OpenAI$1.10$4.40$0.55
az-o3-proAzure OpenAI$20.00$80.00
az-o4-miniAzure OpenAI$1.10$4.40$0.275
az-phi-3-medium-128k-instructAzure OpenAI$0.17$0.68
az-phi-3-medium-4k-instructAzure OpenAI$0.17$0.68
az-phi-3-mini-128k-instructAzure OpenAI$0.13$0.52
az-phi-3-mini-4k-instructAzure OpenAI$0.13$0.52
az-phi-3-small-128k-instructAzure OpenAI$0.15$0.6
az-phi-3-small-8k-instructAzure OpenAI$0.15$0.6
az-phi-3.5-mini-128k-instructAzure OpenAI$0.13$0.52
az-phi-3.5-moe-instructAzure OpenAI$0.16$0.64
az-phi-3.5-v-128k-instructAzure OpenAI$0.13$0.52
az-phi-4Azure OpenAI$0.125$0.5
az-phi-4-miniAzure OpenAI$0.075$0.3
az-phi-4-mini-mmAzure OpenAI$0.08$0.32
az-phi-4-mini-reasoningAzure OpenAI$0.075$0.3
az-phi-4-reasoningAzure OpenAI$0.125$0.5
az-phi-4-reasoning-plusAzure OpenAI$0.125$0.5
az-text-embedding-3-largeAzure OpenAI$0.13$0
az-text-embedding-3-smallAzure OpenAI$0.02$0
az-text-embedding-ada-002Azure OpenAI$0.1$0
kimi-k2.6Azure OpenAI$0.95$4.00$0.16
codestral-2508Mistral$0.3$0.9$0.03
devstral-2512Mistral$0.4$2.00$0.04
ministral-14b-2512Mistral$0.2$0.2$0.02
ministral-3b-2512Mistral$0.1$0.1$0.01
ministral-8b-2512Mistral$0.15$0.15$0.015
mistral-large-2407Mistral$2.00$6.00$0.2
mistral-large-2512Mistral$0.5$1.50$0.05
mistral-medium-3Mistral$0.4$2.00$0.04
mistral-medium-3-5Mistral$1.50$7.50
mistral-medium-3.1Mistral$0.4$2.00$0.04
mistral-nemoMistral$0.02$0.03
mistral-sabaMistral$0.2$0.6$0.02
mistral-small-24b-instruct-2501Mistral$0.05$0.08
mistral-small-2603Mistral$0.15$0.6$0.015
mistral-small-3Mistral$0.1$0.3
mistral-small-3.1-24b-instructMistral$0.351$0.555
mistral-small-3.2-24b-instructMistral$0.075$0.2
voxtral-small-24b-2507Mistral$0.1$0.3$0.01
llama-3-8b-instructMeta$0.14$0.14
llama-3.1-70b-instructMeta$0.4$0.4
llama-3.1-8b-instructMeta$0.02$0.03
llama-3.2-11b-vision-instructMeta$0.345$0.345
llama-3.2-1b-instructMeta$0.027$0.201
llama-3.2-3b-instructMeta$0.05$0.33
llama-3.3-70bMeta$1.04$1.04
llama-3.3-70b-instructMeta$0.1$0.32
llama-4-maverickMeta$0.27$0.35
llama-4-scoutMeta$0.18$0.59
llama-guard-4-12bMeta$0.18$0.18
Llama-Guard-4-12BMeta$0.2$0.2
Meta-Llama-3-8B-Instruct-LiteMeta$0.14$0.14
autoCursor$1.25$6.00$0.25
claude-4-sonnetCursor$3.00$15.00$0.3
claude-4-sonnet-1mCursor$6.00$22.50$0.6
claude-4.5-haikuCursor$1.00$5.00$0.1
claude-4.5-opusCursor$5.00$25.00$0.5
claude-4.5-sonnetCursor$3.00$15.00$0.3
claude-4.6-opusCursor$5.00$25.00$0.5
claude-4.6-sonnetCursor$3.00$15.00$0.3
claude-4.7-opusCursor$5.00$25.00$0.5
claude-fable-5Cursor$10.00$50.00$1.00
claude-opus-4-7-fastCursor$30.00$150.00$3.00
claude-opus-4-8Cursor$5.00$25.00$0.5
claude-sonnet-5Cursor$3.00$15.00$0.3
composer-1Cursor$1.25$10.00$0.125
composer-1.5Cursor$3.50$17.50$0.35
composer-2Cursor$0.5$2.50$0.2
composer-2-fastCursor$1.50$7.50$0.2
composer-2.5Cursor$0.5$2.50$0.2
composer-2.5-fastCursor$3.00$15.00$0.3
cursor-smallCursor$0.1$0.4$0.01
gemini-2.5-flashCursor$0.3$2.50$0.03
gemini-3-flashCursor$0.5$3.00$0.05
gemini-3-proCursor$2.00$12.00$0.2
gemini-3-pro-image-previewCursor$2.00$12.00$0.2
gemini-3.1-proCursor$2.00$12.00$0.2
gemini-3.5-flashCursor$1.50$9.00$0.15
glm-5.2Cursor$1.40$4.40$0.26
gpt-5Cursor$1.25$10.00$0.125
gpt-5-codexCursor$1.25$10.00$0.125
gpt-5-fastCursor$2.50$20.00$0.25
gpt-5-miniCursor$0.25$2.00$0.025
gpt-5.1-codexCursor$1.25$10.00$0.125
gpt-5.1-codex-maxCursor$1.25$10.00$0.125
gpt-5.1-codex-miniCursor$0.25$2.00$0.025
gpt-5.2Cursor$1.75$14.00$0.175
gpt-5.2-codexCursor$1.75$14.00$0.175
gpt-5.3-codexCursor$1.75$14.00$0.175
gpt-5.4Cursor$2.50$15.00$0.25
gpt-5.4-miniCursor$0.75$4.50$0.075
gpt-5.4-nanoCursor$0.2$1.25$0.02
gpt-5.5Cursor$5.00$30.00$0.5
grok-4.5Cursor$2.00$6.00$0.5
kimi-k2.7-codeCursor$0.95$4.00$0.19
claude-fable-latest~anthropic$10.00$50.00$1.00
claude-haiku-latest~anthropic$1.00$5.00$0.1
claude-opus-latest~anthropic$5.00$25.00$0.5
claude-sonnet-latest~anthropic$2.00$10.00$0.2
gemini-flash-latest~google$1.50$9.00$0.15
gemini-pro-latest~google$2.00$12.00$0.2
kimi-latest~moonshotai$0.65$3.41$0.14
gpt-latest~openai$5.00$30.00$0.5
gpt-mini-latest~openai$0.75$4.50$0.075
grok-latest~x-ai$2.00$6.00$0.5
jamba-large-1.7Ai21$2.00$8.00
aion-2.0Aion-labs$0.8$1.60$0.2
aion-3.0Aion-labs$3.00$6.00$0.75
aion-3.0-miniAion-labs$0.7$1.40$0.18
aion-rp-llama-3.1-8bAion-labs$0.8$1.60
qwen3-embedding-8bAlibaba$0.1$0
qwen3-reranker-8bAlibaba$0.2$0
qwen3p6-plusAlibaba$0.5$3.00$0.1
qwen3p7-plusAlibaba$0.4$1.60$0.08
olmo-3-32b-thinkAllenai$0.15$0.5
nova-2-lite-v1Amazon$0.3$2.50
nova-lite-v1Amazon$0.06$0.24
nova-micro-v1Amazon$0.035$0.14
nova-premier-v1Amazon$2.50$12.50$0.625
nova-pro-v1Amazon$0.8$3.20
magnum-v4-72bAnthracite-org$3.00$5.00
coder-largeArcee-ai$0.5$0.8
trinity-large-thinkingArcee-ai$0.25$0.8$0.06
trinity-miniArcee-ai$0.045$0.15
virtuoso-largeArcee-ai$0.75$1.20
ernie-4.5-vl-424b-a47bBaidu$0.42$1.25
ui-tars-1.5-7bByteDance$0.1$0.2$0.1
seed-1.6Bytedance-seed$0.25$2.00
seed-1.6-flashBytedance-seed$0.075$0.3
seed-2.0-liteBytedance-seed$0.25$2.00
seed-2.0-miniBytedance-seed$0.1$0.4
command-aCohere$2.50$10.00
command-r-08-2024Cohere$0.15$0.6
command-r-plus-08-2024Cohere$2.50$10.00
command-r7b-12-2024Cohere$0.0375$0.15
cogito-v2-1-671bDeepCogito$1.25$1.25
cogito-v2.1-671bDeepCogito$1.25$1.25
rnj-1-instructEssential AI$0.15$0.15
firefunction-v2Fireworks AI$0.9$0.9
fw-deepseek-r1Fireworks AI$3.00$8.00
fw-deepseek-v3Fireworks AI$0.56$1.68
llama-v3p1-405b-instructFireworks AI$0.9$0.9
llama-v3p1-8b-instructFireworks AI$0.1$0.1
llama-v3p3-70b-instructFireworks AI$0.9$0.9
mixtral-8x22b-instructFireworks AI$1.20$1.20
mixtral-8x7b-instructFireworks AI$0.5$0.5
nemotron-3-ultra-nvfp4Fireworks AI$0.6$2.40$0.12
qwen2p5-72b-instructFireworks AI$0.9$0.9
gemma-3n-E4B-itGemma$0.06$0.12
gemma-4-31B-itGemma$0.39$0.97
gemma-4-31b-it-pearlGemma$0.28$0.86
mythomax-l2-13bGryphe$0.06$0.06
granite-4.0-h-microIbm-granite$0.017$0.112
granite-4.1-8bIbm-granite$0.05$0.1$0.05
mercury-2Inception$0.25$0.75$0.025
ling-2.6-1tInclusionai$0.075$0.625$0.015
ling-2.6-flashInclusionai$0.01$0.03$0.002
ring-2.6-1tInclusionai$0.075$0.625$0.015
inflection-3-piInflection$2.50$10.00
inflection-3-productivityInflection$2.50$10.00
multilingual-e5-large-instructintfloat$0.02$0.02
kat-coder-pro-v2Kwaipilot$0.3$1.20$0.06
LFM2-24B-A2BLiquid AI$0.03$0.12
weaverMancer$0.75$1.00
phi-4Microsoft$0.07$0.14
wizardlm-2-8x22bMicrosoft$0.62$0.62
minimax-01MiniMax$0.2$1.10
minimax-m1MiniMax$0.4$2.20
minimax-m2MiniMax$0.255$1.02
minimax-m2-herMiniMax$0.3$1.20$0.03
minimax-m2.1MiniMax$0.3$1.20$0.03
minimax-m2.5MiniMax$0.15$0.9$0.05
minimax-m2.7MiniMax$0.24$0.96
MiniMax-M2.7MiniMax$0.3$1.20$0.06
minimax-m2p5MiniMax$0.3$1.20$0.03
minimax-m2p7MiniMax$0.3$1.20$0.06
minimax-m3MiniMax$0.3$1.20$0.06
minimax-m3MiniMax$0.3$1.20$0.06
kimi-k2.5Moonshot$0.375$2.03$0.203
Kimi-K2.5Moonshot$0.5$2.80
Kimi-K2.6Moonshot$1.20$4.50$0.2
kimi-k2.7-codeMoonshot$0.72$3.50$0.15
Kimi-K2.7-CodeMoonshot$0.95$4.00$0.19
kimi-k2p5Moonshot$0.6$3.00$0.1
kimi-k2p6Moonshot$0.95$4.00$0.16
kimi-k2p7-codeMoonshot$0.95$4.00$0.19
kimi-k2Moonshotai$0.57$2.30
kimi-k2-0905Moonshotai$0.6$2.50
morph-v3-fastMorph$0.8$1.20
morph-v3-largeMorph$0.9$1.90
nex-n2-miniNex-agi$0.025$0.1$0.0025
nex-n2-proNex-agi$0.25$1.00$0.025
hermes-3-llama-3.1-405bNous$1.00$1.00
hermes-3-llama-3.1-70bNous$0.7$0.7
hermes-4-405bNous$1.00$3.00
hermes-4-70bNous$0.13$0.4
llama-3.3-nemotron-super-49b-v1.5NVIDIA$0.4$0.4
nemotron-3-nano-30b-a3bNVIDIA$0.05$0.2
nemotron-3-super-120b-a12bNVIDIA$0.08$0.45
nemotron-3-ultra-550b-a55bNVIDIA$0.5$2.20$0.1
bodybuilderOpenRouter$-1000000$-1000000
fusionOpenRouter$-1000000$-1000000
pareto-codeOpenRouter$-1000000$-1000000
perceptron-mk1Perceptron$0.15$1.50
sonarPerplexity$1.00$1.00
sonar-deep-researchPerplexity$2.00$8.00
sonar-proPerplexity$3.00$15.00
sonar-pro-searchPerplexity$3.00$15.00
sonar-reasoning-proPerplexity$2.00$8.00
laguna-m.1Poolside$0.2$0.4$0.1
laguna-xs-2.1Poolside$0.06$0.12$0.03
qwen-2.5-72b-instructQwen$0.36$0.4
qwen-2.5-7b-instructQwen$0.04$0.1
qwen-2.5-coder-32b-instructQwen$0.66$1.00
qwen-plusQwen$0.26$0.78$0.052
qwen-plus-2025-07-28Qwen$0.26$0.78
qwen2.5-7b-instruct-turboQwen$0.3$0.3
qwen2.5-vl-72b-instructQwen$0.8$1.00$0.4
qwen3-14bQwen$0.1$0.24
qwen3-235b-a22bQwen$0.2$0.6
Qwen3-235B-A22B-Instruct-2507-tputQwen$0.2$0.6
qwen3-235b-a22b-thinking-2507Qwen$0.1495$1.50
qwen3-30b-a3bQwen$0.12$0.5
qwen3-30b-a3b-instruct-2507Qwen$0.04815$0.19305
qwen3-30b-a3b-thinking-2507Qwen$0.13$1.56
qwen3-32bQwen$0.08$0.28
qwen3-8bQwen$0.117$0.455
qwen3-coderQwen$0.22$1.80
qwen3-coder-30b-a3b-instructQwen$0.07$0.27
Qwen3-Coder-480B-A35B-Instruct-FP8Qwen$2.00$2.00
qwen3-coder-flashQwen$0.195$0.975$0.039
qwen3-coder-plusQwen$0.65$3.25$0.13
qwen3-maxQwen$0.78$3.90$0.156
qwen3-max-thinkingQwen$0.78$3.90
qwen3-next-80b-a3b-instructQwen$0.09$1.10
qwen3-next-80b-a3b-thinkingQwen$0.0975$0.78
qwen3-vl-235b-a22b-instructQwen$0.2$0.88$0.11
qwen3-vl-235b-a22b-thinkingQwen$0.26$2.60
qwen3-vl-30b-a3b-instructQwen$0.13$0.52
qwen3-vl-30b-a3b-thinkingQwen$0.13$1.56
qwen3-vl-32b-instructQwen$0.104$0.416
qwen3-vl-8b-instructQwen$0.117$0.455
qwen3-vl-8b-thinkingQwen$0.117$1.37
qwen3.5-122b-a10bQwen$0.26$2.08
qwen3.5-27bQwen$0.195$1.56
qwen3.5-35b-a3bQwen$0.14$1.00$0.05
qwen3.5-397b-a17bQwen$0.385$2.45$0.111
Qwen3.5-397B-A17BQwen$0.6$3.60$0.35
qwen3.5-9bQwen$0.1$0.15
Qwen3.5-9BQwen$0.17$0.25
qwen3.5-flash-02-23Qwen$0.065$0.26
qwen3.5-plus-02-15Qwen$0.26$1.56
qwen3.5-plus-20260420Qwen$0.3$1.80
qwen3.6-27bQwen$0.285$2.40$0.15
qwen3.6-35b-a3bQwen$0.14$1.00
qwen3.6-flashQwen$0.1875$1.13
qwen3.6-max-previewQwen$1.04$6.24
qwen3.6-plusQwen$0.325$1.95
Qwen3.6-PlusQwen$0.5$3.00
qwen3.7-maxQwen$1.25$3.75$0.25
qwen3.7-plusQwen$0.32$1.28$0.064
reka-edgeRekaai$0.1$0.1
reka-flash-3Rekaai$0.1$0.2
relace-apply-3Relace$0.85$1.25
relace-searchRelace$1.00$3.00
fugu-ultraSakana$5.00$30.00$0.5
l3-lunaris-8bSao10k$0.04$0.05
l3.1-70b-hanami-x1Sao10k$3.00$3.00
l3.1-euryale-70bSao10k$0.85$0.85
l3.3-euryale-70bSao10k$0.65$0.75
step-3.5-flashStepfun$0.1$0.3
step-3.7-flashStepfun$0.2$1.15$0.04
hunyuan-a13b-instructTencent$0.14$0.57
hy3Tencent$0.14$0.58$0.035
hy3-previewTencent$0.063$0.21$0.021
cydonia-24b-v4.1Thedrummer$0.3$0.5$0.15
rocinante-12bThedrummer$0.25$0.5
skyfall-36b-v2Thedrummer$0.55$0.8$0.25
unslopnemo-12bThedrummer$0.4$0.4
bge-base-en-v1.5Together AI$0.008$0.008
deepseek-coder-33b-instructTogether AI$0.8$0.8
DeepSeek-R1-Distill-Llama-70BTogether AI$2.00$2.00
DeepSeek-R1-Distill-Qwen-1.5BTogether AI$0.18$0.18
DeepSeek-R1-Distill-Qwen-14BTogether AI$1.60$1.60
gemma-2-27b-itTogether AI$0.8$0.8
gemma-4-31b-itTogether AI$0.28$0.86
GLM-4.5-Air-FP8Together AI$0.2$1.10
GLM-4.6Together AI$0.6$2.20
GLM-4.7Together AI$0.45$2.00
GLM-5.2Together AI$1.40$4.40$0.26
Kimi-K2.5-fp4Together AI$0.5$2.80
LFM2.5-8B-A1BTogether AI$0.03$0.12
Llama-3-8b-chat-hfTogether AI$0.2$0.2
Llama-3.1-405B-InstructTogether AI$3.50$3.50
Llama-3.1-Nemotron-70B-Instruct-HFTogether AI$0.88$0.88
Llama-3.2-1B-InstructTogether AI$0.06$0.06
Llama-3.2-3B-InstructTogether AI$0.06$0.06
Llama-Rank-V1Together AI$0.1$0.1
Meta-Llama-3-70B-Instruct-TurboTogether AI$0.88$0.88
Meta-Llama-3-8B-InstructTogether AI$0.2$0.2
Meta-Llama-3.1-70B-Instruct-TurboTogether AI$0.88$0.88
Meta-Llama-3.1-8BTogether AI$0.2$0.2
Meta-Llama-3.1-8B-Instruct-TurboTogether AI$0.18$0.18
MiniMax-M3Together AI$0.3$1.20$0.06
Ministral-3-14B-Instruct-2512Together AI$0.2$0.2
Mistral-7B-Instruct-v0.1Together AI$0.2$0.2
Mistral-7B-Instruct-v0.3Together AI$0.2$0.2
Mixtral-8x7B-Instruct-v0.1Together AI$0.6$0.6
nemotron-3-ultra-550b-a55bTogether AI$0.6$3.60$0.2
Nous-Hermes-2-Mixtral-8x7B-DPOTogether AI$0.6$0.6
NVIDIA-Nemotron-Nano-9B-v2Together AI$0.06$0.25
qwen-2-1.5b-instructTogether AI$0.1$0.1
Qwen2-1.5B-InstructTogether AI$0.02$0.02
Qwen2-72B-InstructTogether AI$0.9$0.9
Qwen2-VL-72B-InstructTogether AI$1.20$1.20
Qwen2.5-14B-InstructTogether AI$0.8$0.8
Qwen2.5-72B-InstructTogether AI$1.20$1.20
Qwen2.5-72B-Instruct-TurboTogether AI$1.20$1.20
Qwen2.5-Coder-32B-InstructTogether AI$0.8$0.8
Qwen2.5-VL-72B-InstructTogether AI$1.95$8.00
Qwen3-Coder-Next-FP8Together AI$0.5$1.20
Qwen3-Next-80B-A3B-InstructTogether AI$0.15$1.50
Qwen3-Next-80B-A3B-ThinkingTogether AI$0.15$1.50
Qwen3-VL-32B-InstructTogether AI$0.5$1.50
Qwen3-VL-8B-InstructTogether AI$0.18$0.68
Qwen3.7-MaxTogether AI$1.25$3.75$0.125
Qwen3.7-PlusTogether AI$0.32$1.28
QwQ-32BTogether AI$1.20$1.20
rime-arcana-v2Together AI$0.27
trinity-miniTogether AI$0.045$0.15
remm-slerp-l2-13bUndi95$0.45$0.65
solar-pro-3Upstage$0.15$0.6$0.015
palmyra-x5Writer$0.6$6.00
mimo-v2.5Xiaomi$0.105$0.28$0.028
mimo-v2.5-proXiaomi$0.435$0.87$0.0036
glm-4.5Z.ai$0.6$2.20$0.11
glm-4.5-airZ.ai$0.13$0.85$0.025
glm-4.5vZ.ai$0.6$1.80$0.11
glm-4.6Z.ai$0.43$1.74$0.08
glm-4.6vZ.ai$0.3$0.9$0.055
glm-4.7Z.ai$0.4$1.75$0.08
glm-4.7-flashZ.ai$0.06$0.4$0.01
glm-5Z.ai$0.6$1.92$0.12
GLM-5Z.ai$1.00$3.20
glm-5-turboZ.ai$1.20$4.00$0.24
glm-5.1Z.ai$0.966$3.04$0.1794
GLM-5.1Z.ai$1.40$4.40$0.26
glm-5.2Z.ai$0.546$1.72$0.1014
glm-5p1Z.ai$1.40$4.40$0.26
glm-5p2Z.ai$1.40$4.40$0.14
glm-5v-turboZ.ai$1.20$4.00$0.24

Audio, image, and other models

ModelProviderPriceUnit
gpt-image-1.5OpenAI$0.034per image
sora-2OpenAI$0.8per request
sora-2-proOpenAI$3.00per request
whisper-large-v3OpenAI$0.0015per minute
flash-image-2.5Google Gemini$0.039per image
flash-image-3.1Google Gemini$0.04657per image
gemini-3-pro-imageGoogle Gemini$0.134per image
grok-imagine-image-proxAI$0.07per image
addon-diarizationDeepgram$0.002per minute
addon-diarization-growthDeepgram$0.0017per minute
addon-entity-detection-prerecordedDeepgram$0.0017per minute
addon-entity-detection-prerecorded-growthDeepgram$0.0017per minute
addon-keyterm-promptingDeepgram$0.0013per minute
addon-keyterm-prompting-growthDeepgram$0.0012per minute
addon-keyterm-prompting-prerecordedDeepgram$0.0017per minute
addon-keyterm-prompting-prerecorded-growthDeepgram$0.0017per minute
addon-redactionDeepgram$0.002per minute
addon-redaction-growthDeepgram$0.0017per minute
addon-redaction-prerecordedDeepgram$0.002per minute
addon-redaction-prerecorded-growthDeepgram$0.0017per minute
aura-1Deepgram$0.015per 1K chars
aura-1-growthDeepgram$0.0135per 1K chars
aura-2Deepgram$0.03per 1K chars
aura-2-growthDeepgram$0.027per 1K chars
baseDeepgram$0.0145per minute
base-growthDeepgram$0.0105per minute
base-prerecordedDeepgram$0.0125per minute
base-prerecorded-growthDeepgram$0.0095per minute
enhancedDeepgram$0.0165per minute
enhanced-growthDeepgram$0.0136per minute
enhanced-prerecordedDeepgram$0.0145per minute
enhanced-prerecorded-growthDeepgram$0.0115per minute
fluxDeepgram$0.0065per minute
flux-growthDeepgram$0.0057per minute
nova-2Deepgram$0.0058per minute
nova-2-growthDeepgram$0.0047per minute
nova-2-prerecordedDeepgram$0.0043per minute
nova-2-prerecorded-growthDeepgram$0.0035per minute
nova-3-monolingualDeepgram$0.0048per minute
nova-3-monolingual-growthDeepgram$0.0042per minute
nova-3-monolingual-prerecordedDeepgram$0.0043per minute
nova-3-monolingual-prerecorded-growthDeepgram$0.0036per minute
nova-3-multilingualDeepgram$0.0058per minute
nova-3-multilingual-growthDeepgram$0.005per minute
nova-3-multilingual-prerecordedDeepgram$0.0052per minute
nova-3-multilingual-prerecorded-growthDeepgram$0.0043per minute
voice-agent-advancedDeepgram$0.163per minute
voice-agent-advanced-byo-ttsDeepgram$0.122per minute
voice-agent-advanced-byo-tts-growthDeepgram$0.11per minute
voice-agent-advanced-growthDeepgram$0.146per minute
voice-agent-custom-byo-llmDeepgram$0.056per minute
voice-agent-custom-byo-llm-growthDeepgram$0.059per minute
voice-agent-custom-byo-llm-ttsDeepgram$0.05per minute
voice-agent-custom-byo-llm-tts-growthDeepgram$0.041per minute
voice-agent-standardDeepgram$0.075per minute
voice-agent-standard-byo-ttsDeepgram$0.065per minute
voice-agent-standard-byo-tts-growthDeepgram$0.051per minute
voice-agent-standard-growthDeepgram$0.068per minute
whisper-large-prerecordedDeepgram$0.0048per minute
whisper-large-prerecorded-growthDeepgram$0.0048per minute
dubbing-v1ElevenLabs$0.5per minute
dubbing-v1-watermarkedElevenLabs$0.33per minute
eleven_flash_v2ElevenLabs$0.05per 1K chars
eleven_flash_v2_5ElevenLabs$0.05per 1K chars
eleven_multilingual_v2ElevenLabs$0.1per 1K chars
eleven_turbo_v2ElevenLabs$0.05per 1K chars
eleven_turbo_v2_5ElevenLabs$0.05per 1K chars
eleven_v3ElevenLabs$0.1per 1K chars
music_v1ElevenLabs$0.15per minute
scribe_v1ElevenLabs$0.003667per minute
scribe_v2ElevenLabs$0.003667per minute
scribe_v2_realtimeElevenLabs$0.0065per minute
scribe-addon-entity-detectionElevenLabs$0.001167per minute
scribe-addon-keyterm-promptingElevenLabs$0.000833per minute
sound-effectsElevenLabs$0.12per event
voice-changerElevenLabs$0.12per minute
voice-isolatorElevenLabs$0.12per minute
agent-session-minuteLiveKit$0.01per minute
agent-session-recording-minuteLiveKit$0.005per minute
data-transfer-gbLiveKit$0.12per GB
observability-eventLiveKit$0.00003per event
sip-trunk-minuteLiveKit$0.004per minute
track-egress-minuteLiveKit$0.001per minute
transcode-audio-minuteLiveKit$0.005per minute
transcode-video-minuteLiveKit$0.02per minute
us-local-inbound-minuteLiveKit$0.01per minute
us-local-phone-numberLiveKit$1.00per month
us-toll-free-inbound-minuteLiveKit$0.02per minute
us-toll-free-phone-numberLiveKit$2.00per month
voice-isolation-minuteLiveKit$0.0012per minute
webrtc-minuteLiveKit$0.0005per minute
cursor-planCursor$0per request
happyhorse-1.0-t2vAlibaba$0.24per request
Seedance-1.0-liteByteDance$0.143per request
Seedance-1.0-proByteDance$0.565per request
Seedance-2.0ByteDance$0.16per request
Seedream-3.0ByteDance$0.018per image
Seedream-4.0ByteDance$0.03per image
orpheus-3b-0.1-ftCanopy Labs$15,000.00per 1K chars
sonicCartesia$65,000.00per 1K chars
sonic-2Cartesia$65,000.00per 1K chars
sonic-3Cartesia$65,000.00per 1K chars
flux-1-schnellFLUX$0.0027per image
flux-2-devFLUX$0.0154per image
flux-2-proFLUX$0.03per image
FLUX.1-kontext-maxFLUX$0.08per image
FLUX.1-kontext-proFLUX$0.04per image
FLUX.1-krea-devFLUX$0.025per image
FLUX.1.1-proFLUX$0.04per image
FLUX.2-flexFLUX$0.03per image
FLUX.2-maxFLUX$0.07per image
veo-2.0Google Veo$2.50per request
veo-3.0Google Veo$1.60per request
veo-3.0-audioGoogle Veo$3.20per request
veo-3.0-fastGoogle Veo$0.8per request
veo-3.0-fast-audioGoogle Veo$1.20per request
HiDream-I1-DevHiDream$0.0045per image
HiDream-I1-FastHiDream$0.0032per image
HiDream-I1-FullHiDream$0.009per image
ideogram-3.0Ideogram$0.06per image
imagen-4.0-fastImagen$0.02per image
imagen-4.0-previewImagen$0.04per image
imagen-4.0-ultraImagen$0.06per image
Kokoro-82MKokoro$4,000.00per 1K chars
kling-1.6-proKuaishou$0.32per request
kling-1.6-standardKuaishou$0.185per request
kling-2.0-masterKuaishou$0.92per request
kling-2.1-masterKuaishou$0.924per request
kling-2.1-proKuaishou$0.3234per request
kling-2.1-standardKuaishou$0.1848per request
DreamShaperLykon$0.0006per image
hailuo-02MiniMax$0.56per request
video-01-directorMiniMax$0.28per request
computeModal$0.06582per minute
cpuModal$0.000786per minute
gpu-a100-40gbModal$0.03498per minute
gpu-a100-80gbModal$0.04164per minute
gpu-a10gModal$0.01836per minute
gpu-b200Modal$0.10416per minute
gpu-h100Modal$0.06582per minute
gpu-h200Modal$0.07566per minute
gpu-l4Modal$0.01332per minute
gpu-l40sModal$0.03252per minute
gpu-rtx-pro-6000Modal$0.05052per minute
gpu-t4Modal$0.00984per minute
modal-planModal$0per request
parakeet-tdt-0.6b-v3NVIDIA$0.0015per minute
pixverse-v5PixVerse$0.299per request
pixverse-v5.6PixVerse$0.1326per request
pixverse-v6PixVerse$0.09per request
Qwen-ImageQwen$0.0058per image
Qwen-Image-2.0Qwen$0.035per image
Qwen-Image-2.0-ProQwen$0.075per image
Juggernaut-Lightning-FluxRunDiffusion$0.0017per image
Juggernaut-pro-fluxRunDiffusion$0.0049per image
stable-diffusion-3-mediumStability AI$0.0019per image
stable-diffusion-xl-base-1.0Stability AI$0.0019per image
flash-image-3.1-liteTogether AI$0.069per image
ideogram-4.0Together AI$0.06per image
nemotron-3-asr-streaming-0.6bTogether AI$0.0015per minute
nemotron-3.5-asr-streaming-0.6bTogether AI$0.0015per minute
nova-3-enTogether AI$0.0015per minute
nova-3-multiTogether AI$0.0015per minute
Seedream-5.0-liteTogether AI$0.035per image
vidu-2.0Vidu$0.8per request
vidu-q1Vidu$0.22per request
vidu-q3Vidu$0.0975per request
vidu-q3-turboVidu$0.195per request
Wan2.2-I2V-A14BWan AI$0.31per request
Wan2.2-T2V-A14BWan AI$0.66per request
Wan2.6-imageWan AI$0.03per image
wan2.7-i2vWan AI$0.1per request
wan2.7-r2vWan AI$0.1per request
wan2.7-t2vWan AI$0.1per request

* Tiered pricing; base-tier rate shown. Token rates are USD per 1,000,000 tokens. Audio rates shown per minute; speech synthesis per 1,000 characters.

Frequently asked questions

Where does this AI model pricing data come from?

It is generated from SuperPenguin's live pricing catalog, the same rate cards used to calculate per-request costs inside the product. It is not a hand-maintained copy.

How often is the pricing updated?

Continuously. This page reflects the current catalog and regenerates hourly, so published provider price changes appear shortly after they are recorded.

What does 'per 1M tokens' mean?

Token-billed model rates are shown in US dollars per 1,000,000 tokens, split into input (prompt), output (completion), and cached-input read rates where the provider offers them.

How are audio and speech models priced?

Audio transcription models are shown per minute and speech synthesis per 1,000 characters, converted from the catalog's underlying per-second or per-character rates.