feat(ai-gateway): replace Step 3.5 Flash with Step 3.7 Flash (free) (#3587)

* feat(ai-gateway): replace Step 3.5 Flash with Step 3.7 Flash (free)

Rename the disabled StepFun free model to Step 3.7 Flash, add the vision
flag, and keep the old 3.5 free slug in forbiddenFreeModelIds.

* docs(ai-gateway): update Step 3.7 Flash model description

---------

Co-authored-by: kiloconnect[bot] <240665456+kiloconnect[bot]@users.noreply.github.com>

Author: kilo-code-bot[bot]

apps/web/src/lib/ai-gateway/models.ts

@@ -36,7 +36,7 @@ import {
   qwen36_plus_model,
   qwen36_plus_stealth_model,
 } from '@/lib/ai-gateway/providers/qwen';
-import { stepfun_35_flash_free_model } from '@/lib/ai-gateway/providers/stepfun';
+import { stepfun_37_flash_free_model } from '@/lib/ai-gateway/providers/stepfun';
 import { isGrokModel } from '@/lib/ai-gateway/providers/xai';
 import { isClaudeModel } from '@/lib/ai-gateway/providers/anthropic.constants';
 import { GPT_CURRENT_MODEL_ID, isOpenAiModel } from '@/lib/ai-gateway/providers/openai';
@@ -48,7 +48,7 @@ export const PRIMARY_DEFAULT_MODEL = CLAUDE_SONNET_CURRENT_MODEL_ID;
 export const autoFreeModels = [
   'nvidia/nemotron-3-super-120b-a12b:free',
   'poolside/laguna-m.1:free',
-  stepfun_35_flash_free_model.status === 'public' ? stepfun_35_flash_free_model.public_id : null,
+  stepfun_37_flash_free_model.status === 'public' ? stepfun_37_flash_free_model.public_id : null,
 ].filter(m => m !== null);
 
 export const preferredModels = [
@@ -96,7 +96,7 @@ export const kiloExclusiveModels = [
   claude_opus_4_7_stealth_model,
   claude_sonnet_4_6_stealth_model,
   claude_opus_4_6_stealth_model,
-  stepfun_35_flash_free_model,
+  stepfun_37_flash_free_model,
 ] as KiloExclusiveModel[];
 
 export function requiresKiloDataCollection(model: string): boolean {

apps/web/src/lib/ai-gateway/providers/stepfun.ts

@@ -4,17 +4,17 @@ export function isStepModel(requestedModel: string) {
   return requestedModel.includes('step-');
 }
 
-export const stepfun_35_flash_free_model: KiloExclusiveModel = {
-  public_id: 'stepfun/step-3.5-flash:free',
-  display_name: 'StepFun: Step 3.5 Flash (free)',
+export const stepfun_37_flash_free_model: KiloExclusiveModel = {
+  public_id: 'stepfun/step-3.7-flash:free',
+  display_name: 'StepFun: Step 3.7 Flash (free)',
   description:
-    "Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. It is a reasoning model that is incredibly speed efficient even at long contexts.",
+    "Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning.\n\nDesigned for coding, agentic workflows, structured outputs, and long-context productivity tasks.",
   context_length: 262_144,
   max_completion_tokens: 262_144,
   status: 'disabled',
-  flags: ['reasoning'],
+  flags: ['reasoning', 'vision'],
   gateway: 'openrouter',
-  internal_id: 'stepfun/step-3.5-flash',
+  internal_id: 'stepfun/step-3.7-flash',
   pricing: null,
   exclusive_to: [],
   inference_provider_restriction: ['stepfun'],