Evan
62bdd04901
Adds two providers for BytePlus ModelArk, the international edition of
Volcano Engine, distinct from the existing cn-only `volcengine` provider:
- `byteplus`: standard `/api/v3` endpoint, 21 models total
- Text (10): Seed 2.0 Pro/Mini/Lite/Code, Seed 1.8, Seed Translation,
GLM-4.7, DeepSeek V3.2/V3.1, GPT-OSS-120B
- Image (4): Seedream 3.0/4.0/4.5/5.0-lite (per-piece pricing in comments)
- Video (7): Seedance 1.0/1.5 family + Dreamina Seedance 2.0/fast
- `byteplus_coding`: `/api/coding` Anthropic-compatible endpoint with
9 friendly aliases (ark-code-latest auto-router, bytedance-seed-code,
dola-seed-2.0-{pro,code,lite}, kimi-k2.5, glm-4.7, glm-5.1, gpt-oss-120b).
Both use BYTEPLUS_API_KEY env var. All listed model IDs were verified
to return HTTP 200 against the live ap-southeast endpoint. Pricing is the
standard real-time tier from the BytePlus console (a discounted batch tier
exists at roughly half the rate, not modeled here).
Excluded for follow-up (schema doesn't currently support these modalities):
- Skylark embedding-vision (no `embedding` modality in schema)
- Hyper3D-Gen2, Hitem3D-2.0 (no `3d` modality in schema)
124 lines
2.9 KiB
TOML
124 lines
2.9 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)
|
|
#
|
|
# Pricing matches the underlying versioned snapshots in byteplus.toml. 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 = []
|