Skip to content

fix(registry): veo 3.1 pricing tiers + roll up open registry PRs (glm-5.2, Qwen3.8-Flash, gemma-4-31b, scribe_v2, fireworks/databricks deepseek v4) + deprecation dates #38990

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
mateo-berri merged 8 commits into from
Sep 1, 2026
Merged

fix(registry): veo 3.1 pricing tiers + roll up open registry PRs (glm-5.2, Qwen3.8-Flash, gemma-4-31b, scribe_v2, fireworks/databricks deepseek v4) + deprecation dates #38990

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
7b4b92f
fix(registry): update veo 3.1 pricing with resolution tiers
devin-ai-integration[bot] Aug 31, 2026
7667e9e
Merge remote-tracking branch 'origin/litellm_internal_staging' into d…
devin-ai-integration[bot] Aug 31, 2026
c344c7a
fix(registry): add zai/glm-5.2, together Qwen3.8-Flash, cerebras/gemm…
devin-ai-integration[bot] Aug 31, 2026
4073835
Merge remote-tracking branch 'origin/litellm_internal_staging' into d…
devin-ai-integration[bot] Sep 1, 2026
7bfa0d7
Registry audit: Fireworks DeepSeek V4 Flash 0731 pricing, Databricks …
devin-ai-integration[bot] Sep 1, 2026
5263570
Add cerebras/zai-glm-4.7 deprecation_date per Cerebras deprecations page
devin-ai-integration[bot] Sep 1, 2026
9a1aebc
fix(registry): declare databricks deepseek cache-write rate at the in…
devin-ai-integration[bot] Sep 1, 2026
06d4521
fix(registry): add vertex veo 3.1 resolution tier pricing per vertex …
mateo-berri Sep 1, 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
155 changes: 140 additions & 15 deletions litellm/model_prices_and_context_window_backup.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -554,6 +554,7 @@
"supports_vision": true
},
"amazon.nova-sonic-v1:0": {
"deprecation_date": "2026-09-14",
"input_cost_per_audio_token": 3.4e-06,
"input_cost_per_token": 6e-08,
"litellm_provider": "bedrock",
Expand Down Expand Up @@ -3045,6 +3046,7 @@
"prompt_cache_min_tokens": 2048
},
"azure_ai/claude-fable-5": {
"deprecation_date": "2027-12-05",
"supports_mid_conversation_system": true,
"input_cost_per_token": 1e-05,
"output_cost_per_token": 5e-05,
Expand Down Expand Up @@ -3078,6 +3080,7 @@
"prompt_cache_min_tokens": 512
},
"azure_ai/claude-opus-5": {
"deprecation_date": "2027-07-08",
"supports_mid_conversation_system": true,
"supports_adaptive_thinking": true,
"input_cost_per_token": 5e-06,
Expand Down Expand Up @@ -3110,6 +3113,7 @@
"prompt_cache_min_tokens": 512
},
"azure_ai/claude-opus-4-8": {
"deprecation_date": "2027-09-01",
"supports_mid_conversation_system": true,
"supports_adaptive_thinking": true,
"input_cost_per_token": 5e-06,
Expand Down Expand Up @@ -3188,6 +3192,7 @@
"prompt_cache_min_tokens": 1024
},
"azure_ai/claude-sonnet-5": {
"deprecation_date": "2027-06-30",
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_1hr": 4e-06,
Expand Down Expand Up @@ -12287,6 +12292,7 @@
"supports_tool_choice": true
},
"cerebras/zai-glm-4.7": {
"deprecation_date": "2026-08-17",
"input_cost_per_token": 2.25e-06,
"litellm_provider": "cerebras",
"max_input_tokens": 128000,
Expand Down Expand Up @@ -15101,6 +15107,62 @@
"supports_tool_choice": true,
"supports_vision": true
},
"databricks/databricks-deepseek-v4-flash-0731": {
"cache_creation_input_token_cost": 1.4e-07,
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.4e-07,
"input_dbu_cost_per_token": 2e-06,
"litellm_provider": "databricks",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"metadata": {
"notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)."
},
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"output_dbu_cost_per_token": 4e-06,
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": false
},
"databricks/databricks-deepseek-v4-pro-0813": {
"cache_creation_input_token_cost": 1.31999e-06,
"cache_read_input_token_cost": 1.3202e-07,
"input_cost_per_token": 1.31999e-06,
"input_dbu_cost_per_token": 1.8857e-05,
"litellm_provider": "databricks",
"max_input_tokens": 1000000,
"max_output_tokens": 393216,
"max_tokens": 393216,
"metadata": {
"notes": "Input/output cost per token is dbu cost * $0.070. Billing reads the per-token dollar fields; the '*_dbu_cost_per_token' fields are the published Databricks rates, kept for reference. Context/max output are the DeepSeek-published model limits (1M context, 384K max output)."
},
"mode": "chat",
"output_cost_per_token": 3.95997e-06,
"output_dbu_cost_per_token": 5.6571e-05,
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": false
},
"databricks/databricks-gemini-2-5-flash": {
"cache_creation_input_token_cost": 3.0002e-07,
"cache_read_input_token_cost": 3.0002e-08,
Expand Down Expand Up @@ -20631,6 +20693,7 @@
"supports_image_size": false
},
"gemini-live-2.5-flash-native-audio": {
"deprecation_date": "2026-12-13",
"input_cost_per_audio_token": 3e-06,
"input_cost_per_token": 5e-07,
"litellm_provider": "vertex_ai-language-models",
Expand Down Expand Up @@ -23852,8 +23915,10 @@
"max_input_tokens": 1024,
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.15,
"source": "https://ai.google.dev/gemini-api/docs/video",
"output_cost_per_second": 0.1,
"output_cost_per_second_1080p": 0.12,
"output_cost_per_second_4k": 0.3,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_modalities": [
"text"
],
Expand All @@ -23867,7 +23932,8 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.4,
"source": "https://ai.google.dev/gemini-api/docs/video",
"output_cost_per_second_4k": 0.6,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_modalities": [
"text"
],
Expand Down Expand Up @@ -23895,8 +23961,10 @@
"max_input_tokens": 1024,
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.15,
"source": "https://ai.google.dev/gemini-api/docs/video",
"output_cost_per_second": 0.1,
"output_cost_per_second_1080p": 0.12,
"output_cost_per_second_4k": 0.3,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_modalities": [
"text"
],
Expand All @@ -23910,7 +23978,8 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.4,
"source": "https://ai.google.dev/gemini-api/docs/video",
"output_cost_per_second_4k": 0.6,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_modalities": [
"text"
],
Expand Down Expand Up @@ -43440,7 +43509,8 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.4,
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"output_cost_per_second_4k": 0.6,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_modalities": [
"text"
],
Expand All @@ -43453,8 +43523,10 @@
"max_input_tokens": 1024,
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.15,
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"output_cost_per_second": 0.1,
"output_cost_per_second_1080p": 0.12,
"output_cost_per_second_4k": 0.3,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_modalities": [
"text"
],
Expand All @@ -43469,7 +43541,8 @@
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.4,
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"output_cost_per_second_4k": 0.6,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_modalities": [
"text"
],
Expand All @@ -43483,8 +43556,10 @@
"max_input_tokens": 1024,
"max_tokens": 1024,
"mode": "video_generation",
"output_cost_per_second": 0.15,
"source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate",
"output_cost_per_second": 0.1,
"output_cost_per_second_1080p": 0.12,
"output_cost_per_second_4k": 0.3,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"supported_modalities": [
"text"
],
Expand Down Expand Up @@ -52231,14 +52306,14 @@
"supports_vision": true
},
"fireworks_ai/deepseek-v4-flash-0731": {
"cache_read_input_token_cost": 2.8e-08,
"input_cost_per_token": 1.4e-07,
"cache_read_input_token_cost": 7e-09,
"input_cost_per_token": 2.2e-07,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 2.8e-07,
"output_cost_per_token": 6.6e-07,
"source": "https://docs.fireworks.ai/serverless/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
Expand Down Expand Up @@ -55124,5 +55199,55 @@
"max_tokens": 40960,
"mode": "embedding",
"source": "https://docs.fireworks.ai/serverless/pricing"
},
"zai/glm-5.2": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.4e-06,
"source": "https://docs.z.ai/guides/overview/pricing",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"together_ai/Qwen/Qwen3.8-Flash": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 1000000,
"max_tokens": 1000000,
"mode": "chat",
"output_cost_per_token": 4.7e-07,
"source": "https://docs.together.ai/docs/serverless-models"
},
"cerebras/gemma-4-31b": {
"input_cost_per_token": 9.9e-07,
"litellm_provider": "cerebras",
"max_input_tokens": 131072,
"max_output_tokens": 40960,
"max_tokens": 40960,
"mode": "chat",
"output_cost_per_token": 1.49e-06,
"source": "https://api.cerebras.ai/public/v1/models/gemma-4-31b",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true
},
"elevenlabs/scribe_v2": {
"input_cost_per_second": 6.11e-05,
"litellm_provider": "elevenlabs",
"mode": "audio_transcription",
"output_cost_per_second": 0.0,
"source": "https://elevenlabs.io/pricing/api",
"supported_endpoints": [
"/v1/audio/transcriptions"
]
}
}
Loading
Loading