Add OpenAI GPT-Image-2.5 (Flare, Sunburst) to the model registry

CLAUDE.md

@@ -120,15 +120,15 @@ Server configuration:
 ### Supported Providers
 
 Model name prefixes determine routing:
-- **OpenAI**: gpt-6-astra, gpt-4.1, gpt-5, gpt-5-mini, gpt-5.2, gpt-5.6-sol/terra/luna, o4-mini; image generation: gpt-image-2
+- **OpenAI**: gpt-6-astra, gpt-4.1, gpt-5, gpt-5-mini, gpt-5.2, gpt-5.6-sol/terra/luna, o4-mini; image generation: gpt-image-2.5-flare, gpt-image-2.5-sunburst, gpt-image-2
 - **Anthropic**: claude-sonnet-4-0/4-5/4-6, claude-sonnet-5, claude-haiku-4-5, claude-opus-4-5/4-6/4-7/4-8, claude-opus-5, claude-fable-5, claude-fable-5-1, claude-3-7-sonnet, claude-3-5-haiku
 - **Google**: gemini-3.8-flash, gemini-3.7-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.5-pro, gemini-3-pro-preview, gemini-3-flash-preview, gemini-3.1-pro-preview, gemini-3.5-flash; image generation: gemini-2.5-flash-image, gemini-3.1-flash-image
 - **xAI**: grok-2, grok-3, grok-3-mini, grok-4, grok-4.3, grok-4.5, grok-4.6, grok-4-fast, grok-4-1-fast; image generation: grok-2-image, grok-imagine-image-2.0
 - **ByteDance** (BytePlus ModelArk, OpenAI-compatible, ap-southeast): seed-1.6, seed-1.8, seed-2.0-lite, deepseek-v4-flash, deepseek-v4-pro, glm-5.2 (Z.ai's model served via a ModelArk deployment endpoint); image generation: seedream-4.0, seedream-5.0-lite, seedance-4.5, seedance-5.0
 - **OpenRouter** (OpenAI-compatible): hermes-4-405b, hermes-4-70b, hy3
 - **Z.ai** (Model API, OpenAI-compatible): image generation: glm-image (glm-5.2 chat is routed through BytePlus ModelArk, see ByteDance above)
 
-Image generation via OpenAI (gpt-image-2), xAI (grok-2-image, grok-imagine-image-2.0), ByteDance
+Image generation via OpenAI (gpt-image-2.5-flare, gpt-image-2.5-sunburst, gpt-image-2), xAI (grok-2-image, grok-imagine-image-2.0), ByteDance
 (seedream-4.0, seedream-5.0-lite, seedance-4.5, seedance-5.0), and Z.ai (glm-image) is served
 through a provider `/images/generations` endpoint rather than the chat path (see
 `image_generation.py`), but is surfaced on `/v1/chat/completions` exactly like

tee_gateway/model_registry.py

@@ -344,6 +344,48 @@ class SupportedModel(Enum):
         image_aspect_ratios=_GPT_IMAGE_ASPECT_SIZES,
         image_aspect_ratio_param="size",
     )
+    # GPT-Image-2.5 Flare — OpenAI's fastest model for high-quality, everyday
+    # image generation (GA 2026-09-08), positioned as the general-purpose
+    # successor to gpt-image-2 (50% lower latency, better reference-photo
+    # fidelity). Same /images/generations + /images/edits endpoints,
+    # b64-only output (response_format omitted, as with gpt-image-2), and
+    # per OpenAI's model page "token rates align with GPT Image 2" — text
+    # $5/$1.25(cached) per MTok, image input $8/$2(cached) per MTok, image
+    # output $30 per MTok — so the same flat per-image approximation as
+    # gpt-image-2 applies.
+    GPT_IMAGE_2_5_FLARE = ModelConfig(
+        provider="openai",
+        api_name="gpt-image-2.5-flare",
+        input_price_usd=Decimal("0"),
+        output_price_usd=Decimal("0"),
+        image_generation=True,
+        per_image_price_usd=Decimal("0.05"),
+        image_response_format=None,
+        image_supports_reference=True,
+        image_edit_endpoint="/images/edits",
+        image_extra_params={"quality": "medium"},
+        image_aspect_ratios=_GPT_IMAGE_ASPECT_SIZES,
+        image_aspect_ratio_param="size",
+    )
+    # GPT-Image-2.5 Sunburst — OpenAI's most capable image model, favoring
+    # editing precision over latency for premium/production workflows (GA
+    # 2026-09-08, same day as Flare). Only reachable via /images/generations
+    # and /images/edits (not chat/Responses/Batch), same request shaping and
+    # token rates as Flare/gpt-image-2.
+    GPT_IMAGE_2_5_SUNBURST = ModelConfig(
+        provider="openai",
+        api_name="gpt-image-2.5-sunburst",
+        input_price_usd=Decimal("0"),
+        output_price_usd=Decimal("0"),
+        image_generation=True,
+        per_image_price_usd=Decimal("0.05"),
+        image_response_format=None,
+        image_supports_reference=True,
+        image_edit_endpoint="/images/edits",
+        image_extra_params={"quality": "medium"},
+        image_aspect_ratios=_GPT_IMAGE_ASPECT_SIZES,
+        image_aspect_ratio_param="size",
+    )
 
     # ── Anthropic ───────────────────────────────────────────────────────
     CLAUDE_SONNET_4_5 = ModelConfig(
@@ -842,6 +884,11 @@ class SupportedModel(Enum):
     "gpt-5.6-luna": SupportedModel.GPT_5_6_LUNA,
     "gpt-6-astra": SupportedModel.GPT_6_ASTRA,
     "gpt-image-2": SupportedModel.GPT_IMAGE_2,
+    "gpt-image-2.5": SupportedModel.GPT_IMAGE_2_5_FLARE,
+    "gpt-image-2.5-flare": SupportedModel.GPT_IMAGE_2_5_FLARE,
+    "gpt-image-2.5-flare-2026-09-08": SupportedModel.GPT_IMAGE_2_5_FLARE,
+    "gpt-image-2.5-sunburst": SupportedModel.GPT_IMAGE_2_5_SUNBURST,
+    "gpt-image-2.5-sunburst-2026-09-08": SupportedModel.GPT_IMAGE_2_5_SUNBURST,
     # Anthropic
     "claude-sonnet-4-5": SupportedModel.CLAUDE_SONNET_4_5,
     "claude-sonnet-4-6": SupportedModel.CLAUDE_SONNET_4_6,

tests/test_pricing.py

@@ -266,6 +266,26 @@ def test_gpt_6_astra_resolves(self):
         self.assertEqual(cfg.output_price_usd, Decimal("0.00005"))
         self.assertTrue(cfg.responses_api_for_tools)
 
+    def test_gpt_image_2_5_flare_resolves(self):
+        cfg = get_model_config("gpt-image-2.5-flare")
+        self.assertEqual(cfg.provider, "openai")
+        self.assertEqual(cfg.api_name, "gpt-image-2.5-flare")
+        self.assertTrue(cfg.image_generation)
+        self.assertEqual(cfg.per_image_price_usd, Decimal("0.05"))
+
+    def test_gpt_image_2_5_bare_alias_resolves_to_flare(self):
+        self.assertEqual(
+            get_model_config("gpt-image-2.5"),
+            get_model_config("gpt-image-2.5-flare"),
+        )
+
+    def test_gpt_image_2_5_sunburst_resolves(self):
+        cfg = get_model_config("gpt-image-2.5-sunburst")
+        self.assertEqual(cfg.provider, "openai")
+        self.assertEqual(cfg.api_name, "gpt-image-2.5-sunburst")
+        self.assertTrue(cfg.image_generation)
+        self.assertEqual(cfg.per_image_price_usd, Decimal("0.05"))
+
     # ── Google ──────────────────────────────────────────────────────────────
 
     def test_gemini_2_5_flash_resolves(self):