GET

/v1/models/fal/fal-fal-ai-bytedance-seed-v2-mini

provider falstatus activefirst seen Mar 17, 2026last seen 6m ago
rawIdfal-ai/bytedance/seed/v2/mini
displayNameBytedance Seed V2 Mini
idfal-fal-ai-bytedance-seed-v2-mini
activitychat
schemaEndpointIdfal-ai/bytedance/seed/v2/mini
releasedAt1773744832 — Mar 17, 2026
firstSeenAt1773744832 — Mar 17, 2026
lastSeenAt1795372248 — 6m ago
pricing
$0.1 / 1M input · $0.4 / 1M output · base rate; long prompts re-quote → open calculator
input_tokens (usage) · output_tokens (usage)
$0.0001 — Your request will cost **$0.0001** per 1000 units. For inputs under 128k tokens, the units per input token is 1. For inputs of over 128k tokens, 2 units will be charged per token. Similarly, each output token costs 4 units, provided the total output length (reasoning + output) is under 128k tokens, and 8 units per token otherwise.
$0.0004 — Your request will cost **$0.0001** per 1000 units. For inputs under 128k tokens, the units per input token is 1. For inputs of over 128k tokens, 2 units will be charged per token. Similarly, each output token costs 4 units, provided the total output length (reasoning + output) is under 128k tokens, and 8 units per token otherwise.
$0.0128 — Your request will cost **$0.0001** per 1000 units. For inputs under 128k tokens, the units per input token is 1. For inputs of over 128k tokens, 2 units will be charged per token. Similarly, each output token costs 4 units, provided the total output length (reasoning + output) is under 128k tokens, and 8 units per token otherwise.
$0.0256 — Your request will cost **$0.0001** per 1000 units. For inputs under 128k tokens, the units per input token is 1. For inputs of over 128k tokens, 2 units will be charged per token. Similarly, each output token costs 4 units, provided the total output length (reasoning + output) is under 128k tokens, and 8 units per token otherwise.
$0.1024 — Your request will cost **$0.0001** per 1000 units. For inputs under 128k tokens, the units per input token is 1. For inputs of over 128k tokens, 2 units will be charged per token. Similarly, each output token costs 4 units, provided the total output length (reasoning + output) is under 128k tokens, and 8 units per token otherwise.
contextWindow256000
maxOutput65536
modalities{"input":["text","image","video"],"output":["text"]}
capabilities{"reasoning_effort":true,"reasoning":true,"top_p":true,"max_tokens":true,"temperature":true}
requestMap{"thinking":{"on":{"thinking":"enabled","reasoning_effort":"high"},"off":{"thinking":"disabled"},"levels":{"off":null,"minimal":"minimal","low":"low","medium":"medium","high":"high","xhigh":null,"max":null}},"maxTokensField":"max_completion_tokens","developerRole":null,"replayReasoningContent":null,"store":null,"strictTools":null,"sessionAffinity":null,"cacheControl":null,"toolStream":null,"reasoningEffort":true}
providerMetadata{"category":"llm"}
knowledgeCutoff · openWeights · weightsUrlnot published by this provider’s list endpoint

Endpoints & schemas

GET /v1/schemas/fal →

endpoints matching this model — the provider has more, see /v1/schemas/fal

Use it

shell
$ curl https://modelschemas.com/v1/schemas/fal/chat/fal-ai/bytedance/seed/v2/mini # request schema
$ curl -X POST https://modelschemas.com/v1/validate -d '{"provider":"fal","endpointId":"fal-ai/bytedance/seed/v2/mini","payload":{…}}'
$ curl -X POST https://modelschemas.com/v1/estimate -d '{"provider":"fal","model":"fal-ai/bytedance/seed/v2/mini","usage":{"input_tokens":1200,"output_tokens":400}}'