Evan
23621ef25e
* docs(byteplus): warn that `byteplus` is per-token, not Coding Plan Self-followup on PR #78. The BytePlus official docs explicitly warn: Do not use the standard model endpoint (https://ark.ap-southeast.bytepluses.com/api/v3) [for Coding Plan workloads], as requests there bypass Coding Plan quota and incur separate charges. — https://docs.byteplus.com/en/docs/ModelArk/1928261 Without this warning visible to users, anyone with a Coding Plan subscription who picks `provider = "byteplus"` will silently bill against their per-token USD balance instead of consuming the subscription quota they paid for. Adds a prominent "BILLING — READ BEFORE USE" block to byteplus.toml making the per-token vs subscription split unambiguous, and a companion note in byteplus-coding.toml pointing back so the choice is discoverable from either side. Also calls out which capabilities are unique to the standard endpoint (image / video) so the choice isn't "just use Coding Plan for everything". No model definitions or pricing changed. * chore(byteplus): drop superseded model entries (21 → 11) (#81) The original byteplus.toml from PR #78 enumerated every BytePlus ModelArk endpoint that returned HTTP 200, regardless of whether a sane user would still pick it. Trims to the current per-family flagship plus useful fast/preview tiers. Removed (10): Text: seed-2-0-lite-260228 — superseded by seed-2-0-mini in the fast/cheap niche seed-1-8-251228 — superseded by seed-2-0 family seed-translation-250915 — too narrow; chat models cover this deepseek-v3-1-250821 — superseded by deepseek-v3-2 Image: seedream-3-0-t2i-250415 — superseded by seedream-4-5 / 5-0-lite seedream-4-0-250828 — same Video: seedance-1-0-lite-i2v-250428 — superseded by 1-5 / dreamina-2-0 seedance-1-0-lite-t2v-250428 — same seedance-1-0-pro-250528 — same seedance-1-0-pro-fast-251015 — same Kept (11): Text (6): seed-2-0-pro/mini/code-preview, glm-4-7, deepseek-v3-2, gpt-oss-120b Image (2): seedream-4-5, seedream-5-0 (lite) Video (3): seedance-1-5-pro, dreamina-seedance-2-0, dreamina-seedance-2-0-fast Also corrects two per-piece / per-K price comments that the trim left orphaned over the wrong [[models]] block (4-5 = $0.0400, not $0.0300; 1-5-pro = $0.0024/$0.0012 with/without audio, not $0.0018/K) and updates the header capability list to match the new model set.
135 lines
3.4 KiB
TOML
135 lines
3.4 KiB
TOML
# BytePlus ModelArk — Coding Plan (Anthropic-compatible) — https://www.byteplus.com/en/product/ModelArk
|
|
# International edition's Claude Code-compatible endpoint with friendly model aliases.
|
|
# Models: 9 (auto-routed alias + 8 named models)
|
|
#
|
|
# 💡 BILLING — calls here count against your **Coding Plan
|
|
# subscription quota**, not your per-token ModelArk USD balance. If you
|
|
# don't have a Coding Plan or want per-token billing instead, use the
|
|
# `byteplus` provider in byteplus.toml. The Coding Plan endpoint also
|
|
# does not expose image / video / embedding models — only the text
|
|
# models listed below.
|
|
#
|
|
# Pricing fields below mirror the underlying versioned snapshots in
|
|
# byteplus.toml for catalog accounting purposes; actual subscription
|
|
# consumption is tracked by the BytePlus console, not these numbers.
|
|
#
|
|
# The Coding Plan endpoint exposes friendly stable names that route to
|
|
# the current production snapshot, so versions advance silently without
|
|
# config changes (use `ark-code-latest` to always get the best current
|
|
# routing).
|
|
|
|
[provider]
|
|
id = "byteplus_coding"
|
|
display_name = "BytePlus ModelArk Coding Plan"
|
|
api_key_env = "BYTEPLUS_API_KEY"
|
|
base_url = "https://ark.ap-southeast.bytepluses.com/api/coding"
|
|
key_required = true
|
|
|
|
[[models]]
|
|
id = "ark-code-latest"
|
|
display_name = "Ark Code (auto-routed)"
|
|
tier = "frontier"
|
|
context_window = 196608
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 1.00
|
|
output_cost_per_m = 6.00
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = ["ark-coding"]
|
|
|
|
[[models]]
|
|
id = "bytedance-seed-code"
|
|
display_name = "ByteDance Seed Code"
|
|
tier = "frontier"
|
|
context_window = 196608
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 1.00
|
|
output_cost_per_m = 6.00
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "dola-seed-2.0-pro"
|
|
display_name = "Dola Seed 2.0 Pro"
|
|
tier = "frontier"
|
|
context_window = 196608
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 1.00
|
|
output_cost_per_m = 6.00
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "dola-seed-2.0-code"
|
|
display_name = "Dola Seed 2.0 Code"
|
|
tier = "smart"
|
|
context_window = 196608
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 1.00
|
|
output_cost_per_m = 6.00
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "dola-seed-2.0-lite"
|
|
display_name = "Dola Seed 2.0 Lite"
|
|
tier = "smart"
|
|
context_window = 196608
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.50
|
|
output_cost_per_m = 4.00
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "kimi-k2.5"
|
|
display_name = "Kimi K2.5"
|
|
tier = "frontier"
|
|
context_window = 196608
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.60
|
|
output_cost_per_m = 2.50
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "glm-4.7"
|
|
display_name = "GLM-4.7"
|
|
tier = "smart"
|
|
context_window = 196608
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.60
|
|
output_cost_per_m = 2.20
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "glm-5.1"
|
|
display_name = "GLM-5.1"
|
|
tier = "frontier"
|
|
context_window = 196608
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.80
|
|
output_cost_per_m = 3.00
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = []
|
|
|
|
[[models]]
|
|
id = "gpt-oss-120b"
|
|
display_name = "GPT-OSS 120B"
|
|
tier = "smart"
|
|
context_window = 131072
|
|
max_output_tokens = 8192
|
|
input_cost_per_m = 0.10
|
|
output_cost_per_m = 0.50
|
|
supports_tools = true
|
|
supports_streaming = true
|
|
aliases = []
|