Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 27 additions & 0 deletions providers/alibaba-cn/models/kimi-k3.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# Sources (accessed 2026-09-15):
# https://www.alibabacloud.com/help/en/model-studio/kimi-k3 (China/Beijing USD
# pricing, limits, capability table)
# https://www.alibabacloud.com/help/zh/model-studio/qwen-api-via-openai-chat-completions
# (reasoning_effort) and /help/en/model-studio/kimi-api (text+image input only,
# no video; reasoning_content streamed in deltas)
# Effort: reasoning_effort = low|high|max (default max). Thinking is always on:
# enable_thinking only accepts true (passing false errors), no thinking_budget.
base_model = "moonshotai/kimi-k3"

[[reasoning_options]]
type = "effort"
values = ["low", "high", "max"]

[interleaved]
field = "reasoning_content"

[cost]
input = 2.827
output = 14.133
cache_read = 0.283

[modalities]
input = ["text", "image"]

[limit]
output = 1_048_576
27 changes: 27 additions & 0 deletions providers/alibaba/models/kimi-k3.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
# Sources (accessed 2026-09-15):
# https://www.qwencloud.com/models/kimi-k3 (Singapore/international pricing, limits)
# https://www.alibabacloud.com/help/en/model-studio/kimi-k3 (limits, capability table)
# https://www.alibabacloud.com/help/zh/model-studio/qwen-api-via-openai-chat-completions
# (reasoning_effort) and /help/en/model-studio/kimi-api (text+image input only,
# no video; reasoning_content streamed in deltas)
# Effort: reasoning_effort = low|high|max (default max). Thinking is always on:
# enable_thinking only accepts true (passing false errors), no thinking_budget.
base_model = "moonshotai/kimi-k3"

[[reasoning_options]]
type = "effort"
values = ["low", "high", "max"]

[interleaved]
field = "reasoning_content"

[cost]
input = 3.0
output = 15.0
cache_read = 0.3

[modalities]
input = ["text", "image"]

[limit]
output = 1_048_576
Loading