From 5a511b6fcc4c267317b48e70dac6541ad7f86b3f Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 12 Nov 2026 08:03:26 -0800 Subject: [PATCH] chore(cost-map): rolling registry audit 2026-11-12 (#51395) Absorb #51347, #51222, #51357 and #51275 with the GMI large-context tier. Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 82 +++++++++++++++++-- model_prices_and_context_window.json | 82 +++++++++++++++++-- .../test_model_latest_aliases.py | 2 +- 3 files changed, 149 insertions(+), 17 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 5a7e4e95764..66bffc90701 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -26230,6 +26230,9 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/text-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/text-to-video" + }, "fal_ai/bytedance/seedance-2.5/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", @@ -26248,6 +26251,9 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/image-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/image-to-video" + }, "fal_ai/bytedance/seedance-2.5/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", @@ -26266,6 +26272,9 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/reference-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/reference-to-video" + }, "fal_ai/minimax/h3/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, @@ -56747,6 +56756,9 @@ "comment": "Output: 20/30/68 credits per second at 480p/720p/1080p @ $0.01 per credit; input video billed additionally at 10/15/34 credits per input second and the 80 credit minimum per task are not modeled" } }, + "runwayml/seedance-latest": { + "alias_of": "runwayml/seedance2_5" + }, "runwayml/hailuo3": { "litellm_provider": "runwayml", "mode": "video_generation", @@ -68564,10 +68576,12 @@ "xai/grok-imagine-image-quality": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", - "input_cost_per_image": 0.05, + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" @@ -68583,10 +68597,12 @@ "xai/grok-imagine-image-quality-20260403": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", - "input_cost_per_image": 0.05, + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" @@ -68602,10 +68618,12 @@ "xai/grok-imagine-image-quality-latest": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", - "input_cost_per_image": 0.05, + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" @@ -68621,10 +68639,12 @@ "xai/grok-imagine-image-pro": { "deprecation_date": "2026-05-15", "deprecation_source": "https://docs.x.ai/developers/migration/may-15-retirement", - "input_cost_per_image": 0.05, + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" @@ -77928,6 +77948,9 @@ "tpm": 4000000.0, "web_search_billing_unit": "per_query" }, + "gemini/nano-banana-latest": { + "alias_of": "gemini/gemini-nano-banana-2.1" + }, "gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, @@ -78022,6 +78045,9 @@ "supports_web_search": true, "web_search_billing_unit": "per_query" }, + "vertex_ai/nano-banana-latest": { + "alias_of": "vertex_ai/gemini-nano-banana-2.1" + }, "azure_ai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, @@ -86829,6 +86855,15 @@ "output_cost_per_token": 1e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, + "gmi/google/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, "gmi/google/gemma-4-26b-a4b-it": { "input_cost_per_token": 1.3e-07, "litellm_provider": "gmi", @@ -87162,6 +87197,18 @@ "output_cost_per_token": 6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, + "gmi/xai/grok4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "gmi", + "max_input_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, "gmi/zai-org/GLM-4.5-Air-FP8": { "input_cost_per_token": 2e-07, "litellm_provider": "gmi", @@ -97755,6 +97802,9 @@ "output_cost_per_image_4K": 0.1134, "source": "https://replicate.com/google/nano-banana-2.1" }, + "replicate/google/nano-banana-latest": { + "alias_of": "replicate/google/nano-banana-2.1" + }, "replicate/heygen/avatar-iv": { "litellm_provider": "replicate", "mode": "video_generation", @@ -100827,5 +100877,21 @@ "supports_vision": true, "supports_web_search": false, "tpm": 1000000 + }, + "runwayml/kling_4": { + "litellm_provider": "runwayml", + "metadata": {"comment":"Promo rate through 2026-11-30 UTC: 12.56 credits per second (720p) and 18.8 (1080p) without input video @ $0.01 per credit = $0.1256 and $0.188 per second; list rate 15.7/23.5 credits per second applies from 2026-12-01 UTC (ruling runwayml-kling-4-promo-rate). The with-input-video rate (7.52/11.28 credits per output second plus the same per second of the greater of input and output duration) and rounding up to the next credit are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.1256, + "output_cost_per_second_1080p": 0.188, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 5a7e4e95764..66bffc90701 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -26230,6 +26230,9 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/text-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/text-to-video" + }, "fal_ai/bytedance/seedance-2.5/image-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", @@ -26248,6 +26251,9 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/image-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/image-to-video" + }, "fal_ai/bytedance/seedance-2.5/reference-to-video": { "litellm_provider": "fal_ai", "mode": "video_generation", @@ -26266,6 +26272,9 @@ "video" ] }, + "fal_ai/bytedance/seedance-latest/reference-to-video": { + "alias_of": "fal_ai/bytedance/seedance-2.5/reference-to-video" + }, "fal_ai/minimax/h3/text-to-video": { "litellm_provider": "fal_ai", "metadata": {"comment":"per second of generated video by resolution; output_cost_per_second is the default resolution 2k rate"}, @@ -56747,6 +56756,9 @@ "comment": "Output: 20/30/68 credits per second at 480p/720p/1080p @ $0.01 per credit; input video billed additionally at 10/15/34 credits per input second and the 80 credit minimum per task are not modeled" } }, + "runwayml/seedance-latest": { + "alias_of": "runwayml/seedance2_5" + }, "runwayml/hailuo3": { "litellm_provider": "runwayml", "mode": "video_generation", @@ -68564,10 +68576,12 @@ "xai/grok-imagine-image-quality": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", - "input_cost_per_image": 0.05, + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" @@ -68583,10 +68597,12 @@ "xai/grok-imagine-image-quality-20260403": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", - "input_cost_per_image": 0.05, + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" @@ -68602,10 +68618,12 @@ "xai/grok-imagine-image-quality-latest": { "deprecation_date": "2026-11-02", "deprecation_source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", - "input_cost_per_image": 0.05, + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" @@ -68621,10 +68639,12 @@ "xai/grok-imagine-image-pro": { "deprecation_date": "2026-05-15", "deprecation_source": "https://docs.x.ai/developers/migration/may-15-retirement", - "input_cost_per_image": 0.05, + "input_cost_per_image": 0.04, "litellm_provider": "xai", "mode": "image_generation", - "source": "https://docs.x.ai/docs/models", + "output_cost_per_image_1K": 0.04, + "output_cost_per_image_2K": 0.06, + "source": "https://docs.x.ai/developers/migration/imagine-image-quality-nov-2", "successor_model": "xai/grok-imagine-image-2.0", "supported_endpoints": [ "/v1/images/generations" @@ -77928,6 +77948,9 @@ "tpm": 4000000.0, "web_search_billing_unit": "per_query" }, + "gemini/nano-banana-latest": { + "alias_of": "gemini/gemini-nano-banana-2.1" + }, "gemini-nano-banana-2.1": { "cache_read_input_token_cost": 1.5e-07, "cache_read_input_token_cost_batches": 7.5e-08, @@ -78022,6 +78045,9 @@ "supports_web_search": true, "web_search_billing_unit": "per_query" }, + "vertex_ai/nano-banana-latest": { + "alias_of": "vertex_ai/gemini-nano-banana-2.1" + }, "azure_ai/grok-4.7": { "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_200k_tokens": 1e-06, @@ -86829,6 +86855,15 @@ "output_cost_per_token": 1e-05, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, + "gmi/google/gemini-4-carbon": { + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "gmi", + "max_input_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, "gmi/google/gemma-4-26b-a4b-it": { "input_cost_per_token": 1.3e-07, "litellm_provider": "gmi", @@ -87162,6 +87197,18 @@ "output_cost_per_token": 6e-06, "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" }, + "gmi/xai/grok4.7": { + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "gmi", + "max_input_tokens": 500000, + "mode": "chat", + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, + "source": "https://ie-api.gmicloud.ai/v1/artifact/get_public_artifacts" + }, "gmi/zai-org/GLM-4.5-Air-FP8": { "input_cost_per_token": 2e-07, "litellm_provider": "gmi", @@ -97755,6 +97802,9 @@ "output_cost_per_image_4K": 0.1134, "source": "https://replicate.com/google/nano-banana-2.1" }, + "replicate/google/nano-banana-latest": { + "alias_of": "replicate/google/nano-banana-2.1" + }, "replicate/heygen/avatar-iv": { "litellm_provider": "replicate", "mode": "video_generation", @@ -100827,5 +100877,21 @@ "supports_vision": true, "supports_web_search": false, "tpm": 1000000 + }, + "runwayml/kling_4": { + "litellm_provider": "runwayml", + "metadata": {"comment":"Promo rate through 2026-11-30 UTC: 12.56 credits per second (720p) and 18.8 (1080p) without input video @ $0.01 per credit = $0.1256 and $0.188 per second; list rate 15.7/23.5 credits per second applies from 2026-12-01 UTC (ruling runwayml-kling-4-promo-rate). The with-input-video rate (7.52/11.28 credits per output second plus the same per second of the greater of input and output duration) and rounding up to the next credit are not modeled"}, + "mode": "video_generation", + "output_cost_per_second": 0.1256, + "output_cost_per_second_1080p": 0.188, + "source": "https://docs.dev.runwayml.com/guides/pricing/", + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "video" + ] } } diff --git a/tests/unit/litellm_core_utils/test_model_latest_aliases.py b/tests/unit/litellm_core_utils/test_model_latest_aliases.py index c6def915640..a6bb3f23a1d 100644 --- a/tests/unit/litellm_core_utils/test_model_latest_aliases.py +++ b/tests/unit/litellm_core_utils/test_model_latest_aliases.py @@ -38,7 +38,7 @@ def test_latest_aliases_price_and_route_like_their_targets() -> None: alias_key: Final = prefixed if prefixed in litellm.model_cost else alias target_key: Final = f"{provider}/{target}" if f"{provider}/{target}" in litellm.model_cost else target entry: Final = litellm.model_cost[alias_key] - assert entry["mode"] in ("chat", "responses") + assert entry["mode"] in ("chat", "responses", "video_generation", "image_generation") assert entry == litellm.model_cost[target_key] assert resolve_model_latest_alias(alias, provider) == target if provider in PROVIDERS_THAT_AUTHENTICATE_ON_PROVIDER_INFO: