AI model pricing

Chat and embedding models are priced per token, image models per image. There is no minimum and no reservation: you pay for what a call actually delivered, from the credit in your account. Conversations in sven are charged at the same prices as the API.

amazon/nova-2-lite-v1

Chat input $0.375 per 1M input tokens
Chat output $3.125 per 1M output tokens

amazon/nova-lite-v1

Chat input $0.075 per 1M input tokens
Chat output $0.30 per 1M output tokens

amazon/nova-micro-v1

Chat input $0.04375 per 1M input tokens
Chat output $0.175 per 1M output tokens

amazon/nova-premier-v1

Chat input $3.125 per 1M input tokens
Chat output $15.625 per 1M output tokens

amazon/nova-pro-v1

Chat input $1.00 per 1M input tokens
Chat output $4.00 per 1M output tokens

anthracite-org/magnum-v4-72b

Chat input $3.125 per 1M input tokens
Chat output $6.25 per 1M output tokens

bytedance-seed/seed-2-1-turbo

Chat input $0.625 per 1M input tokens
Chat output $3.125 per 1M output tokens

bytedance/ui-tars-1.5-7b

Chat input $0.125 per 1M input tokens
Chat output $0.25 per 1M output tokens

cognitivecomputations/dolphin-mistral-24b-venice-edition

Chat input $0.25 per 1M input tokens
Chat output $1.125 per 1M output tokens

cohere/command-a-plus

Chat input $0.375 per 1M input tokens
Chat output $1.875 per 1M output tokens

deepseek/deepseek-chat

Chat input $0.40 per 1M input tokens
Chat output $1.1125 per 1M output tokens

deepseek/deepseek-chat-v3-0324

Chat input $0.3125 per 1M input tokens
Chat output $1.25 per 1M output tokens

deepseek/deepseek-chat-v3.1

Chat input $0.8125 per 1M input tokens
Chat output $2.125 per 1M output tokens

deepseek/deepseek-r1-0528

Chat input $0.625 per 1M input tokens
Chat output $2.725 per 1M output tokens

deepseek/deepseek-v3.1-terminus

Chat input $0.3375 per 1M input tokens
Chat output $1.25 per 1M output tokens

deepseek/deepseek-v3.2

Chat input $3.75 per 1M input tokens
Chat output $5.625 per 1M output tokens

deepseek/deepseek-v3.2-exp

Chat input $0.3375 per 1M input tokens
Chat output $0.5125 per 1M output tokens

deepseek/deepseek-v4-flash

Chat input $0.75 per 1M input tokens
Chat output $1.65 per 1M output tokens

deepseek/deepseek-v4-flash-0731

Chat input $0.55 per 1M input tokens
Chat output $1.65 per 1M output tokens

deepseek/deepseek-v4-flash-vision-exp

Chat input $0.55 per 1M input tokens
Chat output $1.65 per 1M output tokens

deepseek/deepseek-v4-pro

Chat input $2.3875 per 1M input tokens
Chat output $4.7875 per 1M output tokens

deepseek/deepseek-v4-pro-0813

Chat input $2.0625 per 1M input tokens
Chat output $10.00 per 1M output tokens

deepseek/deepseek-v4.1-flash

Chat input $0.5625 per 1M input tokens
Chat output $2.25 per 1M output tokens

elorian/glimpse

Chat input $0.75 per 1M input tokens
Chat output $3.75 per 1M output tokens

fireworks/ember-1

Chat input $3.75 per 1M input tokens
Chat output $18.75 per 1M output tokens

google/gemma-2-27b-it

Chat input $0.8125 per 1M input tokens
Chat output $0.8125 per 1M output tokens

google/gemma-3-12b-it

Chat input $0.09375 per 1M input tokens
Chat output $0.28125 per 1M output tokens

google/gemma-3-27b-it

Chat input $0.14875 per 1M input tokens
Chat output $0.5625 per 1M output tokens

google/gemma-3-4b-it

Chat input $0.0625 per 1M input tokens
Chat output $0.125 per 1M output tokens

google/gemma-4-26b-a4b-it

Chat input $0.1875 per 1M input tokens
Chat output $0.75 per 1M output tokens

google/gemma-4-31b-it

Chat input $0.9375 per 1M input tokens
Chat output $1.4375 per 1M output tokens

gryphe/mythomax-l2-13b

Chat input $0.4375 per 1M input tokens
Chat output $0.75 per 1M output tokens

ibm-granite/granite-4.2-8b

Chat input $0.075 per 1M input tokens
Chat output $0.3125 per 1M output tokens

inception/mercury-2

Chat input $0.3125 per 1M input tokens
Chat output $0.9375 per 1M output tokens

inception/mercury-2.5

Chat input $0.05 per 1M input tokens
Chat output $0.1875 per 1M output tokens

inception/mercury-3

Chat input $0.125 per 1M input tokens
Chat output $0.4375 per 1M output tokens

inclusionai/ling-3.0-flash

Chat input $0.075 per 1M input tokens
Chat output $0.225 per 1M output tokens

inclusionai/ling-3.0-flash-vl

Chat input $0.075 per 1M input tokens
Chat output $0.225 per 1M output tokens

inclusionai/ling-3.1-flash

Chat input $0.09375 per 1M input tokens
Chat output $0.28125 per 1M output tokens

inference-net/schematron-v2-small

Chat input $0.0625 per 1M input tokens
Chat output $0.2875 per 1M output tokens

inference-net/schematron-v2-turbo

Chat input $0.0375 per 1M input tokens
Chat output $0.1875 per 1M output tokens

liquid/lfm-2.5-24b-a2b

Chat input $0.0625 per 1M input tokens
Chat output $0.875 per 1M output tokens

mancer/weaver

Chat input $0.50 per 1M input tokens
Chat output $0.9375 per 1M output tokens

meta-llama/llama-3.1-70b-instruct

Chat input $0.90 per 1M input tokens
Chat output $0.90 per 1M output tokens

meta-llama/llama-3.1-8b-instruct

Chat input $0.275 per 1M input tokens
Chat output $0.35875 per 1M output tokens

meta-llama/llama-3.2-1b-instruct

Chat input $0.03375 per 1M input tokens
Chat output $0.25125 per 1M output tokens

meta-llama/llama-3.2-3b-instruct

Chat input $0.063625 per 1M input tokens
Chat output $0.41875 per 1M output tokens

meta-llama/llama-3.3-70b-instruct

Chat input $0.90 per 1M input tokens
Chat output $2.81625 per 1M output tokens

meta-llama/llama-4-maverick

Chat input $0.4375 per 1M input tokens
Chat output $1.4375 per 1M output tokens

meta-llama/llama-4-scout

Chat input $0.3125 per 1M input tokens
Chat output $0.875 per 1M output tokens

meta-llama/llama-guard-4-12b

Chat input $0.3375 per 1M input tokens
Chat output $0.3375 per 1M output tokens

meta/muse-glimmer-30b

Chat input $0.375 per 1M input tokens
Chat output $1.50 per 1M output tokens

meta/muse-spark-open

Chat input $1.5625 per 1M input tokens
Chat output $5.3125 per 1M output tokens

microsoft/phi-4

Chat input $0.0875 per 1M input tokens
Chat output $0.175 per 1M output tokens

minimax/minimax-m1

Chat input $0.6875 per 1M input tokens
Chat output $2.75 per 1M output tokens

minimax/minimax-m2

Chat input $0.31875 per 1M input tokens
Chat output $1.275 per 1M output tokens

minimax/minimax-m2.1

Chat input $0.375 per 1M input tokens
Chat output $3.00 per 1M output tokens

minimax/minimax-m2.5

Chat input $0.75 per 1M input tokens
Chat output $3.00 per 1M output tokens

minimax/minimax-m2.7

Chat input $0.75 per 1M input tokens
Chat output $3.00 per 1M output tokens

minimax/minimax-m3

Chat input $0.75 per 1M input tokens
Chat output $3.00 per 1M output tokens

mistralai/codestral-2508

Chat input $0.4125 per 1M input tokens
Chat output $1.2375 per 1M output tokens

mistralai/devstral-2512

Chat input $0.50 per 1M input tokens
Chat output $2.50 per 1M output tokens

mistralai/ministral-14b-2512

Chat input $0.275 per 1M input tokens
Chat output $0.275 per 1M output tokens

mistralai/ministral-3b-2512

Chat input $0.1375 per 1M input tokens
Chat output $0.1375 per 1M output tokens

mistralai/ministral-8b-2512

Chat input $0.20625 per 1M input tokens
Chat output $0.20625 per 1M output tokens

mistralai/mistral-large

Chat input $2.75 per 1M input tokens
Chat output $8.25 per 1M output tokens

mistralai/mistral-large-2407

Chat input $2.75 per 1M input tokens
Chat output $8.25 per 1M output tokens

mistralai/mistral-large-2512

Chat input $0.6875 per 1M input tokens
Chat output $2.0625 per 1M output tokens

mistralai/mistral-large-4-0

Chat input $0.9625 per 1M input tokens
Chat output $2.8875 per 1M output tokens

mistralai/mistral-medium-3

Chat input $0.55 per 1M input tokens
Chat output $2.75 per 1M output tokens

mistralai/mistral-medium-3-5

Chat input $2.0625 per 1M input tokens
Chat output $10.3125 per 1M output tokens

mistralai/mistral-medium-3.1

Chat input $0.55 per 1M input tokens
Chat output $2.75 per 1M output tokens

mistralai/mistral-nemo

Chat input $0.1875 per 1M input tokens
Chat output $0.1875 per 1M output tokens

mistralai/mistral-saba

Chat input $0.275 per 1M input tokens
Chat output $0.825 per 1M output tokens

mistralai/mistral-small-24b-instruct-2501

Chat input $0.0625 per 1M input tokens
Chat output $0.10 per 1M output tokens

mistralai/mistral-small-2603

Chat input $0.20625 per 1M input tokens
Chat output $0.825 per 1M output tokens

mistralai/mistral-small-3.1-24b-instruct

Chat input $0.43875 per 1M input tokens
Chat output $0.69375 per 1M output tokens

mistralai/mistral-small-3.2-24b-instruct

Chat input $0.125 per 1M input tokens
Chat output $0.375 per 1M output tokens

mistralai/mixtral-8x22b-instruct

Chat input $2.75 per 1M input tokens
Chat output $8.25 per 1M output tokens

moondream/moondream3-preview

Chat input $0.375 per 1M input tokens
Chat output $3.125 per 1M output tokens

moondream/moondream3.1-9b-a2b

Chat input $0.375 per 1M input tokens
Chat output $3.125 per 1M output tokens

moonshotai/kimi-k2

Chat input $0.7125 per 1M input tokens
Chat output $2.875 per 1M output tokens

moonshotai/kimi-k2-0905

Chat input $0.75 per 1M input tokens
Chat output $3.125 per 1M output tokens

moonshotai/kimi-k2-thinking

Chat input $0.75 per 1M input tokens
Chat output $3.125 per 1M output tokens

moonshotai/kimi-k2.5

Chat input $0.75 per 1M input tokens
Chat output $4.15625 per 1M output tokens

moonshotai/kimi-k2.6

Chat input $1.3625 per 1M input tokens
Chat output $5.75 per 1M output tokens

moonshotai/kimi-k2.7-code

Chat input $2.375 per 1M input tokens
Chat output $10.00 per 1M output tokens

moonshotai/kimi-k3

Chat input $5.625 per 1M input tokens
Chat output $28.125 per 1M output tokens

moonshotai/kimi-k3.1-pro

Chat input $5.00 per 1M input tokens
Chat output $25.00 per 1M output tokens

morph/morph-v3-fast

Chat input $1.00 per 1M input tokens
Chat output $1.50 per 1M output tokens

morph/morph-v3-large

Chat input $1.125 per 1M input tokens
Chat output $2.375 per 1M output tokens

nousresearch/hermes-3-llama-3.1-405b

Chat input $1.25 per 1M input tokens
Chat output $1.25 per 1M output tokens

nousresearch/hermes-3-llama-3.1-70b

Chat input $0.875 per 1M input tokens
Chat output $0.875 per 1M output tokens

nousresearch/hermes-4-405b

Chat input $1.25 per 1M input tokens
Chat output $3.75 per 1M output tokens

nvidia/nemotron-3-nano-30b-a3b

Chat input $0.075 per 1M input tokens
Chat output $0.30 per 1M output tokens

nvidia/nemotron-3-super-120b-a12b

Chat input $0.375 per 1M input tokens
Chat output $3.00 per 1M output tokens

nvidia/nemotron-3-ultra-550b-a55b

Chat input $0.78125 per 1M input tokens
Chat output $3.90625 per 1M output tokens

nvidia/nemotron-3.5-content-safety

Chat input $0.25 per 1M input tokens
Chat output $0.25 per 1M output tokens

nvidia/nemotron-3.5-lightning

Chat input $0.0875 per 1M input tokens
Chat output $0.25 per 1M output tokens

nvidia/nemotron-3.5-super-vl

Chat input $0.25 per 1M input tokens
Chat output $0.625 per 1M output tokens

openai/gpt-3.5-turbo-0613

Chat input $1.25 per 1M input tokens
Chat output $2.50 per 1M output tokens

openai/gpt-3.5-turbo-16k

Chat input $3.75 per 1M input tokens
Chat output $5.00 per 1M output tokens

openai/gpt-4

Chat input $37.50 per 1M input tokens
Chat output $75.00 per 1M output tokens

openai/gpt-4o

Chat input $3.125 per 1M input tokens
Chat output $12.50 per 1M output tokens

openai/gpt-4o-2024-05-13

Chat input $6.25 per 1M input tokens
Chat output $18.75 per 1M output tokens

openai/gpt-4o-2024-08-06

Chat input $3.125 per 1M input tokens
Chat output $12.50 per 1M output tokens

openai/gpt-4o-mini

Chat input $0.20625 per 1M input tokens
Chat output $0.825 per 1M output tokens

openai/gpt-oss-120b

Chat input $0.4375 per 1M input tokens
Chat output $1.1875 per 1M output tokens

openai/gpt-oss-120b:batch

Chat input $0.4375 per 1M input tokens
Chat output $1.1875 per 1M output tokens

openai/gpt-oss-20b

Chat input $0.09375 per 1M input tokens
Chat output $0.375 per 1M output tokens

openai/gpt-oss-20b:batch

Chat input $0.09375 per 1M input tokens
Chat output $0.375 per 1M output tokens

openai/gpt-oss-safeguard-20b

Chat input $0.09375 per 1M input tokens
Chat output $0.375 per 1M output tokens

particle-ai/particle-1

Chat input $0.0625 per 1M input tokens
Chat output $0.625 per 1M output tokens

perceptron/perceptron-mk1

Chat input $0.1875 per 1M input tokens
Chat output $1.875 per 1M output tokens

perceptron/perceptron-mk1.5

Chat input $0.1875 per 1M input tokens
Chat output $1.875 per 1M output tokens

qwen/qwen-2.5-72b-instruct

Chat input $0.45 per 1M input tokens
Chat output $0.50 per 1M output tokens

qwen/qwen-2.5-7b-instruct

Chat input $0.125 per 1M input tokens
Chat output $0.25 per 1M output tokens

qwen/qwen-2.5-coder-32b-instruct

Chat input $0.825 per 1M input tokens
Chat output $1.25 per 1M output tokens

qwen/qwen2.5-vl-72b-instruct

Chat input $1.00 per 1M input tokens
Chat output $1.25 per 1M output tokens

qwen/qwen3-14b

Chat input $0.15 per 1M input tokens
Chat output $0.30 per 1M output tokens

qwen/qwen3-235b-a22b-2507

Chat input $0.1875 per 1M input tokens
Chat output $1.00 per 1M output tokens

qwen/qwen3-235b-a22b-thinking-2507

Chat input $0.5625 per 1M input tokens
Chat output $4.375 per 1M output tokens

qwen/qwen3-30b-a3b

Chat input $0.15 per 1M input tokens
Chat output $0.625 per 1M output tokens

qwen/qwen3-30b-a3b-instruct-2507

Chat input $0.125 per 1M input tokens
Chat output $0.375 per 1M output tokens

qwen/qwen3-32b

Chat input $0.175 per 1M input tokens
Chat output $0.7125 per 1M output tokens

qwen/qwen3-coder

Chat input $0.4375 per 1M input tokens
Chat output $1.875 per 1M output tokens

qwen/qwen3-coder-30b-a3b-instruct

Chat input $0.1875 per 1M input tokens
Chat output $0.75 per 1M output tokens

qwen/qwen3-coder-next

Chat input $0.15 per 1M input tokens
Chat output $1.00 per 1M output tokens

qwen/qwen3-next-80b-a3b-instruct

Chat input $0.16875 per 1M input tokens
Chat output $2.0625 per 1M output tokens

qwen/qwen3-vl-235b-a22b-instruct

Chat input $0.2625 per 1M input tokens
Chat output $2.375 per 1M output tokens

qwen/qwen3-vl-30b-a3b-instruct

Chat input $0.3625 per 1M input tokens
Chat output $1.25 per 1M output tokens

qwen/qwen3-vl-30b-a3b-thinking

Chat input $0.3625 per 1M input tokens
Chat output $1.25 per 1M output tokens

qwen/qwen3-vl-8b-instruct

Chat input $0.3125 per 1M input tokens
Chat output $0.9375 per 1M output tokens

qwen/qwen3.5-122b-a10b

Chat input $0.50 per 1M input tokens
Chat output $4.00 per 1M output tokens

qwen/qwen3.5-27b

Chat input $0.375 per 1M input tokens
Chat output $3.25 per 1M output tokens

qwen/qwen3.5-35b-a3b

Chat input $0.30 per 1M input tokens
Chat output $2.25 per 1M output tokens

qwen/qwen3.5-397b-a17b

Chat input $0.9375 per 1M input tokens
Chat output $5.625 per 1M output tokens

qwen/qwen3.5-9b

Chat input $0.2125 per 1M input tokens
Chat output $0.3125 per 1M output tokens

qwen/qwen3.6-27b

Chat input $0.40625 per 1M input tokens
Chat output $4.0625 per 1M output tokens

qwen/qwen3.6-35b-a3b

Chat input $0.30 per 1M input tokens
Chat output $2.25 per 1M output tokens

qwen/qwen3.8-2.4t-a95b

Chat input $2.50 per 1M input tokens
Chat output $7.50 per 1M output tokens

qwen/qwen3.8-27b

Chat input $1.2375 per 1M input tokens
Chat output $4.00 per 1M output tokens

reflection/beam-1.0-501b-a23b

Chat input $0.50 per 1M input tokens
Chat output $1.50 per 1M output tokens

rekaai/reka-edge

Chat input $0.125 per 1M input tokens
Chat output $0.125 per 1M output tokens

rekaai/reka-flash-3

Chat input $0.125 per 1M input tokens
Chat output $0.25 per 1M output tokens

relace/relace-apply-3

Chat input $1.0625 per 1M input tokens
Chat output $1.5625 per 1M output tokens

relace/relace-search

Chat input $1.25 per 1M input tokens
Chat output $3.75 per 1M output tokens

sao10k/l3-lunaris-8b

Chat input $0.05 per 1M input tokens
Chat output $0.0625 per 1M output tokens

sao10k/l3.1-euryale-70b

Chat input $1.0625 per 1M input tokens
Chat output $1.0625 per 1M output tokens

scaledown/extract

Chat input $0.05 per 1M input tokens
Chat output $0.00 per 1M output tokens

scaledown/summarize

Chat input $0.05 per 1M input tokens
Chat output $0.00 per 1M output tokens

stepfun/step-3.5-flash

Chat input $0.125 per 1M input tokens
Chat output $0.375 per 1M output tokens

stepfun/step-3.7-flash

Chat input $0.25 per 1M input tokens
Chat output $1.4375 per 1M output tokens

stepfun/step-5-preview

Chat input $1.25 per 1M input tokens
Chat output $3.375 per 1M output tokens

tencent/hunyuan-a13b-instruct

Chat input $0.175 per 1M input tokens
Chat output $0.7125 per 1M output tokens

tencent/hy-mt2-1.8b

Chat input $0.055 per 1M input tokens
Chat output $0.22125 per 1M output tokens

tencent/hy-mt2-30b-a3b

Chat input $0.0925 per 1M input tokens
Chat output $0.36875 per 1M output tokens

tencent/hy-mt2-7b

Chat input $0.0925 per 1M input tokens
Chat output $0.36875 per 1M output tokens

thedrummer/cydonia-24b-v4.1

Chat input $0.375 per 1M input tokens
Chat output $0.625 per 1M output tokens

thedrummer/skyfall-36b-v2

Chat input $0.6875 per 1M input tokens
Chat output $1.00 per 1M output tokens

thedrummer/unslopnemo-12b

Chat input $0.50 per 1M input tokens
Chat output $0.50 per 1M output tokens

thinkingmachines/inkling

Chat input $1.25 per 1M input tokens
Chat output $5.0625 per 1M output tokens

thinkingmachines/inkling-small

Chat input $0.5625 per 1M input tokens
Chat output $1.50 per 1M output tokens

unbiased/pareto-26.10

Chat input $1.00 per 1M input tokens
Chat output $4.00 per 1M output tokens

undi95/remm-slerp-l2-13b

Chat input $0.4375 per 1M input tokens
Chat output $0.8125 per 1M output tokens

upstage/solar-mini4

Chat input $0.0625 per 1M input tokens
Chat output $0.25 per 1M output tokens

upstage/solar-pro4

Chat input $0.1875 per 1M input tokens
Chat output $0.75 per 1M output tokens

writer/palmyra-x5

Chat input $0.75 per 1M input tokens
Chat output $7.50 per 1M output tokens

xiaomi/mimo-v2.5

Chat input $0.50 per 1M input tokens
Chat output $2.50 per 1M output tokens

xiaomi/mimo-v2.5-pro

Chat input $0.60 per 1M input tokens
Chat output $2.25 per 1M output tokens

xiaomi/mimo-v2.6-flash

Chat input $0.21875 per 1M input tokens
Chat output $0.4375 per 1M output tokens

xiaomi/mimo-v2.6-pro

Chat input $0.54375 per 1M input tokens
Chat output $1.0875 per 1M output tokens

z-ai/glm-4.5

Chat input $0.75 per 1M input tokens
Chat output $2.75 per 1M output tokens

z-ai/glm-4.5-air

Chat input $0.25 per 1M input tokens
Chat output $1.375 per 1M output tokens

z-ai/glm-4.5v

Chat input $0.75 per 1M input tokens
Chat output $2.25 per 1M output tokens

z-ai/glm-4.6

Chat input $0.75 per 1M input tokens
Chat output $2.75 per 1M output tokens

z-ai/glm-4.6v

Chat input $0.375 per 1M input tokens
Chat output $1.125 per 1M output tokens

z-ai/glm-4.7

Chat input $0.875 per 1M input tokens
Chat output $3.125 per 1M output tokens

z-ai/glm-4.7-flash

Chat input $0.0875 per 1M input tokens
Chat output $0.50 per 1M output tokens

z-ai/glm-5

Chat input $1.50 per 1M input tokens
Chat output $5.00 per 1M output tokens

z-ai/glm-5-turbo

Chat input $1.50 per 1M input tokens
Chat output $5.00 per 1M output tokens

z-ai/glm-5.1

Chat input $1.75175 per 1M input tokens
Chat output $5.5055 per 1M output tokens

z-ai/glm-5.2

Chat input $2.625 per 1M input tokens
Chat output $10.00 per 1M output tokens

z-ai/glm-5.3

Chat input $2.625 per 1M input tokens
Chat output $8.25 per 1M output tokens

z-ai/glm-5.3-flash

Chat input $0.4375 per 1M input tokens
Chat output $1.5625 per 1M output tokens

z-ai/glm-5.3-flashx

Chat input $0.4625 per 1M input tokens
Chat output $1.5625 per 1M output tokens

z-ai/glm-5v-turbo

Chat input $1.50 per 1M input tokens
Chat output $5.00 per 1M output tokens

Web search

$10.00 per 1000 searches

Charged once per search, through /v1/search or sven’s web search tool; a search that fails is not charged.

New here? Read the API documentation or create an account.