Skip to content

feat(stepfun): add step-5-preview to StepFun providers #7535

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rekram1-node merged 2 commits into from
Sep 23, 2026
Merged

feat(stepfun): add step-5-preview to StepFun providers #7535

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cf01d60
feat(stepfun): add step-5-preview to StepFun providers
Sep 20, 2026
27f5ef9
Merge remote-tracking branch 'upstream/dev' into feat/stepfun-step-5-…
Sep 22, 2026
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
11 changes: 11 additions & 0 deletions providers/stepfun-ai-step-plan/models/step-5-preview.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# Chat `reasoning_effort` and Messages `output_config.effort` accept
# low/medium/high (accessed 2026-09-20).
# https://platform.stepfun.ai/docs/en/step-plan/integrations/reasoning-api
base_model = "stepfun/step-5-preview"

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

[interleaved]
field = "reasoning_content"
8 changes: 4 additions & 4 deletions providers/stepfun-ai-step-plan/provider.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
name = "StepFun Step Plan (Global)"
env = ["STEPFUN_API_KEY"]
npm = "@ai-sdk/openai-compatible"
# Reasoning HTTP format (accessed 2026-06-25):
# Reasoning HTTP format (accessed 2026-09-20):
# Step Plan exposes POST /step_plan/v1/chat/completions with top-level
# `reasoning_effort` and POST /step_plan/v1/messages with
# `output_config.effort`. step-3.7-flash accepts low/medium/high;
# step-3.5-flash and step-3.5-flash-2603 accept low/high. No plan Responses
# endpoint is listed.
# `output_config.effort`. step-5-preview and step-3.7-flash accept
# low/medium/high; step-3.5-flash and step-3.5-flash-2603 accept low/high.
# No plan Responses endpoint is listed.
# Source:
# https://platform.stepfun.ai/docs/en/step-plan/integrations/reasoning-api
doc = "https://platform.stepfun.ai/docs/en/step-plan/integrations/reasoning-api"
Expand Down
20 changes: 20 additions & 0 deletions providers/stepfun/models/step-5-preview.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
# Chat `reasoning_effort`, Messages `output_config.effort`, and Responses
# `reasoning.effort` accept low/medium/high (accessed 2026-09-20).
# https://platform.stepfun.com/docs/zh/guides/models/step-5-preview
# Cost converted from CNY list price (¥7 / ¥20 / ¥0.35 per 1M tokens) at the
# same 7.2973 CNY/USD rate used by the other stepfun entries (accessed
# 2026-09-20).
# https://platform.stepfun.com/docs/zh/guides/pricing/details
base_model = "stepfun/step-5-preview"

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

[interleaved]
field = "reasoning_content"

[cost]
input = 0.959
output = 2.741
cache_read = 0.048
7 changes: 4 additions & 3 deletions providers/stepfun/provider.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,11 +1,12 @@
name = "StepFun (China)"
env = ["STEPFUN_API_KEY"]
npm = "@ai-sdk/openai-compatible"
# Reasoning HTTP format (accessed 2026-06-25):
# Reasoning HTTP format (accessed 2026-09-20):
# POST /v1/chat/completions uses top-level `reasoning_effort`; POST /v1/messages
# uses `output_config.effort`; POST /v1/responses uses `reasoning.effort`.
# Values are low/medium/high for step-3.7-flash; step-3.5-flash-2603 accepts
# low/high. Responses supports only step-3.7-flash. Chat returns reasoning at
# Values are low/medium/high for step-5-preview and step-3.7-flash;
# step-3.5-flash-2603 accepts low/high. Responses supports only
# step-5-preview and step-3.7-flash. Chat returns reasoning at
# `choices[].message.reasoning` or streamed `choices[].delta.reasoning`;
# `reasoning_format` is general (default) or deepseek-style, the latter using
# `reasoning_content`. Responses streams `response.reasoning_text.delta`.
Expand Down
Loading