Skip to content

chore(pricing): refresh models.dev snapshot - #570

Open
github-actions[bot] wants to merge 1 commit into
mainfrom
automation/models-dev-pricing
Open

github-actions[bot] wants to merge 1 commit into
mainfrom
automation/models-dev-pricing

Conversation

@github-actions

@github-actions github-actions Bot commented Sep 21, 2026 •

Copy link
Copy Markdown
Contributor

Refreshes the vendored models.dev pricing snapshot from the upstream API.

Providers: 195 → 226. Models: 7293 → 8388.

Validation

  • The refreshed payload parsed as JSON and passed provider/model count and critical-model integrity checks.
  • cargo test -p relayburn-sdk passed with the refreshed snapshot embedded.
  • This PR is created with GITHUB_TOKEN, so GitHub does not automatically trigger pull_request workflows for it; the full SDK suite ran in the update workflow instead.

Primary-provider models added (23)

  • anthropic/claude-fable-5-1
  • anthropic/claude-opus-5-5
  • anthropic/claude-sonnet-5-5
  • google-vertex/claude-fable-5-1@default
  • google-vertex/claude-opus-5-5@default
  • google-vertex/claude-sonnet-5-5@default
  • google-vertex/gemini-3.8-flash
  • google-vertex/xai/grok-4.1-fast-non-reasoning
  • google-vertex/xai/grok-4.1-fast-reasoning
  • google-vertex/xai/grok-4.20-non-reasoning
  • google-vertex/xai/grok-4.20-reasoning
  • google-vertex/xai/grok-4.3
  • google-vertex/xai/grok-4.6
  • google-vertex/zai-org/glm-5.2-maas
  • google/gemini-3.8-flash
  • openai/gpt-6-astra
  • openai/gpt-6-luna
  • openai/gpt-6-sol
  • openai/gpt-6.1-sol
  • openai/gpt-daybreak-blue-latest
  • openai/gpt-daybreak-red-latest
  • xai/grok-4.7
  • xai/grok-imagine-video-1.5-lite

Other models added (1752)

  • 302ai/MiniMax-M2.5
  • 302ai/MiniMax-M3
  • 302ai/claude-fable-5
  • 302ai/claude-fable-5-1
  • 302ai/claude-opus-4-7-thinking
  • 302ai/claude-opus-4-8
  • 302ai/claude-opus-5
  • 302ai/claude-opus-5-5
  • 302ai/claude-opus-5-thinking
  • 302ai/claude-sonnet-5
  • 302ai/claude-sonnet-5-5
  • 302ai/deepseek-flash
  • 302ai/gemini-3.1-flash-lite
  • 302ai/gemini-3.1-flash-lite-preview
  • 302ai/gemini-3.1-pro-preview
  • 302ai/gemini-3.5-flash
  • 302ai/gemini-3.5-flash-lite
  • 302ai/gemini-3.5-flash-thinking
  • 302ai/gemini-3.6-flash
  • 302ai/gemini-3.7-flash
  • 302ai/gemini-3.8-flash
  • 302ai/glm-5.2
  • 302ai/glm-5.3
  • 302ai/glm-5.3-flash
  • 302ai/gpt-5.3-chat-latest
  • 302ai/gpt-5.5
  • 302ai/gpt-5.6-luna
  • 302ai/gpt-5.6-luna-pro
  • 302ai/gpt-5.6-sol
  • 302ai/gpt-5.6-sol-pro
  • 302ai/gpt-5.6-terra
  • 302ai/gpt-5.6-terra-pro
  • 302ai/gpt-6-astra
  • 302ai/gpt-6-luna
  • 302ai/gpt-6-sol
  • 302ai/grok-4.3
  • 302ai/grok-4.5
  • 302ai/grok-4.6
  • 302ai/grok-4.7
  • 302ai/kimi-k2.5
  • 302ai/kimi-k2.6
  • 302ai/kimi-k2.7-code
  • 302ai/kimi-k3
  • 302ai/o3
  • 302ai/qwen3.5-35b-a3b
  • 302ai/qwen3.5-plus
  • 302ai/qwen3.6-35b-a3b
  • 302ai/qwen3.6-flash
  • 302ai/qwen3.6-plus
  • 302ai/qwen3.7-max
  • 302ai/qwen3.7-max-2026-06-08
  • 302ai/qwen3.7-plus
  • 302ai/qwen3.8-flash
  • 302ai/qwen3.8-max
  • abliteration-ai/abliterated-model-large-v2
  • above/deepseek-v4-flash
  • above/deepseek-v4-pro
  • above/deepseek-v4.1-flash
  • above/glm-5.2
  • above/glm-5.2-fast
  • above/glm-5.3-flash
  • above/mimo-v2.6-flash
  • above/mimo-v2.6-pro
  • above/mimo-v2.6-pro-ultraspeed
  • above/qwen3.8-max
  • agentrouter/deepseek-v4-flash
  • agentrouter/glm-5.3
  • agnes/agnes-2.0-flash
  • agnes/agnes-2.5-flash
  • agnes/agnes-2.5-pro-alpha
  • ai21/jamba-large
  • ai21/jamba-mini
  • aiand/deepseek-ai/deepseek-v4.1-flash
  • aiand/qwen/qwen3.8-27b
  • aiand/zai-org/glm-5.3
  • aiand/zai-org/glm-5.3-flash
  • aihubmix/claude-fable-5-1
  • aihubmix/claude-haiku-4-5
  • aihubmix/claude-opus-4-5
  • aihubmix/claude-opus-5-5
  • aihubmix/claude-sonnet-4-5
  • aihubmix/deepseek-v4-flash-0731
  • aihubmix/deepseek-v4-flash-0731-fast
  • aihubmix/deepseek-v4-flash-vision-exp
  • aihubmix/deepseek-v4-pro-0813
  • aihubmix/deepseek-v4.1-flash
  • aihubmix/gemini-2.5-flash-image
  • aihubmix/gemini-2.5-flash-lite
  • aihubmix/gemini-3-pro-image
  • aihubmix/gemini-3.1-flash-image
  • aihubmix/gemini-3.1-flash-lite-image
  • aihubmix/gemini-3.5-flash-lite
  • aihubmix/gemini-3.6-flash
  • aihubmix/gemini-3.8-flash
  • aihubmix/glm-4.5v
  • aihubmix/glm-4.6
  • aihubmix/glm-4.6v
  • aihubmix/glm-4.7
  • aihubmix/glm-5.3
  • aihubmix/glm-5.3-flash
  • …and 1652 more

Primary-provider models removed (2)

  • google/gemini-robotics-er-1.6-preview
  • xai/grok-imagine-image-2.0

Other models removed (678)

  • 302ai/MiniMax-M2.7-highspeed
  • 302ai/chatgpt-4o-latest
  • 302ai/claude-3-5-haiku-20241022
  • 302ai/claude-3-5-haiku-latest
  • 302ai/claude-opus-4-20250514
  • 302ai/claude-opus-4-5
  • 302ai/claude-opus-4-5-20251101-thinking
  • 302ai/claude-opus-4-6
  • 302ai/claude-opus-4-6-thinking
  • 302ai/claude-sonnet-4-20250514
  • 302ai/claude-sonnet-4-5
  • 302ai/deepseek-chat
  • 302ai/deepseek-reasoner
  • 302ai/doubao-seed-code-preview-251028
  • 302ai/glm-4.5-air
  • 302ai/glm-4.5-airx
  • 302ai/glm-4.5-x
  • 302ai/glm-4.7-flashx
  • 302ai/glm-for-coding
  • 302ai/gpt-5.4-mini-2026-03-17
  • 302ai/gpt-5.4-nano-2026-03-17
  • 302ai/gpt-5.4-pro
  • 302ai/grok-4-1-fast-non-reasoning
  • 302ai/grok-4.20-beta-0309-non-reasoning
  • 302ai/grok-4.20-multi-agent-beta-0309
  • 302ai/kimi-k2-thinking-turbo
  • 302ai/qwen-flash
  • 302ai/qwen-max-latest
  • 302ai/qwen-plus
  • aki-io/kimi-k2.7-code-1100b
  • alibaba-coding-plan-cn/qwen3.6-flash
  • alibaba-coding-plan-cn/qwen3.7-max
  • alibaba-coding-plan/qwen3.6-flash
  • alibaba-coding-plan/qwen3.7-max
  • berget/meta-llama/Llama-3.3-70B-Instruct
  • berget/mistralai/Mistral-Medium-3.5-128B
  • berget/moonshotai/Kimi-K2.6
  • berget/openai/gpt-oss-120b
  • berget/zai-org/GLM-4.7
  • blueclaw/Qwen/Qwen3.6-35B-A3B-FP8
  • blueclaw/Qwen3.6-27B
  • cerebras/gemma-4-31b
  • cloudflare-ai-gateway/openai/gpt-3.5-turbo
  • cloudflare-ai-gateway/openai/gpt-4
  • cloudflare-ai-gateway/openai/gpt-4-turbo
  • cloudflare-ai-gateway/openai/gpt-5-pro
  • cloudflare-ai-gateway/openai/gpt-5.2
  • cloudflare-ai-gateway/openai/gpt-5.2-chat-latest
  • cloudflare-ai-gateway/openai/gpt-5.2-pro
  • cloudflare-ai-gateway/openai/gpt-5.3-chat-latest
  • cloudflare-ai-gateway/openai/gpt-5.3-codex
  • cloudflare-ai-gateway/openai/gpt-5.3-codex-spark
  • cloudflare-ai-gateway/openai/gpt-5.6
  • cloudflare-ai-gateway/openai/o1
  • cloudflare-ai-gateway/openai/o1-pro
  • cloudflare-ai-gateway/openai/o3-pro
  • cloudflare-ai-gateway/workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it
  • cloudflare-ai-gateway/workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b
  • cloudflare-ai-gateway/workers-ai/@cf/google/gemma-4-26b-a4b-it
  • cloudflare-ai-gateway/workers-ai/@cf/ibm-granite/granite-4.0-h-micro
  • cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8
  • cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-11b-vision-instruct
  • cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-1b-instruct
  • cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-3b-instruct
  • cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast
  • cloudflare-ai-gateway/workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct
  • cloudflare-ai-gateway/workers-ai/@cf/meta/llama-guard-3-8b
  • cloudflare-ai-gateway/workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct
  • cloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.6
  • cloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.7-code
  • cloudflare-ai-gateway/workers-ai/@cf/nvidia/nemotron-3-120b-a12b
  • cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-120b
  • cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-20b
  • cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct
  • cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-30b-a3b-fp8
  • cloudflare-ai-gateway/workers-ai/@cf/qwen/qwq-32b
  • cloudflare-ai-gateway/workers-ai/@cf/zai-org/glm-4.7-flash
  • cloudflare-ai-gateway/workers-ai/@cf/zai-org/glm-5.2
  • cohere/c4ai-aya-expanse-8b
  • cohere/c4ai-aya-vision-8b
  • coralbricks/glm-5.2-fp4
  • coralbricks/gpt-oss-120b
  • coralbricks/kimi-k3
  • cortecs/cosmos3-super-reasoner
  • cortecs/deepseek-r1-0528
  • cortecs/glm-4.7
  • cortecs/glm-5
  • cortecs/glm-5-turbo
  • cortecs/glm-5v-turbo
  • cortecs/hermes-4-70b
  • cortecs/kimi-k2.5
  • cortecs/llama-3.1-405b-instruct
  • cortecs/llama-3.1-nemotron-ultra-253b-v1
  • cortecs/minimax-m2.7
  • cortecs/mistral-medium-2508
  • cortecs/nvidia-nemotron-3-nano-omni
  • cortecs/qwen3-next-80b-a3b-thinking
  • cortecs/qwen3.5-122b-a10b
  • crof/deepseek-v4-pro-lightning
  • crossmodel/moonshot/kimi-k2.5
  • …and 578 more

Primary-provider price fields changed (2)

  • openai/gpt-5.6 — cache_read: 0.5 → 0.4; cache_write: 6.25 → 5; context_over_200k: {"input":10,"output":45,"cache_read":1,"cache_write":12.5} → {"input":8,"output":30,"cache_read":0.8,"cache_write":10}; input: 5 → 4; output: 30 → 20; tiers: [{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}] → [{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}]
  • openai/gpt-5.6-sol — cache_read: 0.5 → 0.4; cache_write: 6.25 → 5; context_over_200k: {"input":10,"output":45,"cache_read":1,"cache_write":12.5} → {"input":8,"output":30,"cache_read":0.8,"cache_write":10}; input: 5 → 4; output: 30 → 20; tiers: [{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}] → [{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}]

Other price fields changed (684)

  • 302ai/glm-5.1 — input: 0.86 → 1.4; output: 3.5 → 4.4
  • aiand/deepseek-ai/deepseek-v4-flash — cache_read: missing → 0.08
  • aiand/deepseek-ai/deepseek-v4-pro — cache_read: missing → 0.25
  • aiand/google/gemma-4-31b-it — cache_read: missing → 0.05
  • aiand/moonshotai/kimi-k2.7-code — cache_read: missing → 0.2
  • aiand/motif-technologies/motif-3 — cache_read: missing → 0.2
  • aiand/openai/gpt-oss-120b — cache_read: missing → 0.08
  • aiand/qwen/qwen3.6-27b — cache_read: missing → 0.2
  • aiand/zai-org/glm-5.2 — cache_read: missing → 0.3
  • alibaba-cn/glm-5 — input: 0.86 → 0.573; output: 3.15 → 2.58; tiers: missing → [{"input":0.86,"output":3.154,"tier":{"type":"context","size":32000}}]
  • alibaba-cn/glm-5.1 — input: 0.87 → 0.825; output: 3.48 → 3.301; tiers: missing → [{"input":1.1,"output":3.851,"tier":{"type":"context","size":32000}}]
  • alibaba-cn/qwen-vl-ocr — input: 0.717 → 0.043; output: 0.717 → 0.072
  • alibaba-cn/qwen3-coder-30b-a3b-instruct — tiers: missing → [{"input":0.323,"output":1.291,"tier":{"type":"context","size":32000}},{"input":0.538,"output":2.151,"tier":{"type":"context","size":128000}}]
  • alibaba-cn/qwen3-coder-480b-a35b-instruct — tiers: missing → [{"input":1.291,"output":5.161,"tier":{"type":"context","size":32000}},{"input":2.151,"output":8.602,"tier":{"type":"context","size":128000}}]
  • alibaba-cn/qwen3-coder-plus — input: 1 → 0.574; output: 5 → 2.296; tiers: missing → [{"input":0.861,"output":3.444,"tier":{"type":"context","size":32000}},{"input":1.435,"output":5.74,"tier":{"type":"context","size":128000}},{"input":2.87,"output":28.7,"tier":{"type":"context","size":256000}}]
  • alibaba-cn/qwen3-max — input: 0.861 → 0.359; output: 3.441 → 1.434; reasoning: missing → 1.434; tiers: missing → [{"input":0.574,"output":2.294,"reasoning":2.294,"tier":{"type":"context","size":32000}},{"input":1.004,"output":4.014,"reasoning":4.014,"tier":{"type":"context","size":128000}}]
  • alibaba-cn/qwen3.5-397b-a17b — input: 0.43 → 0.172; output: 2.58 → 1.032; reasoning: 2.58 → 1.032; tiers: missing → [{"input":0.43,"output":2.58,"reasoning":2.58,"tier":{"type":"context","size":128000}}]
  • alibaba-cn/qwen3.5-flash — input: 0.172 → 0.029; output: 1.72 → 0.287; reasoning: 1.72 → 0.287; tiers: missing → [{"input":0.115,"output":1.147,"reasoning":1.147,"tier":{"type":"context","size":128000}},{"input":0.172,"output":1.72,"reasoning":1.72,"tier":{"type":"context","size":256000}}]
  • alibaba-cn/qwen3.5-plus — input: 0.573 → 0.115; output: 3.44 → 0.688; reasoning: 3.44 → 0.688; tiers: missing → [{"input":0.287,"output":1.72,"reasoning":1.72,"tier":{"type":"context","size":128000}},{"input":0.573,"output":3.44,"reasoning":3.44,"tier":{"type":"context","size":256000}}]
  • alibaba/qwen3-coder-30b-a3b-instruct — tiers: missing → [{"input":0.75,"output":3.75,"tier":{"type":"context","size":32000}},{"input":1.2,"output":6,"tier":{"type":"context","size":128000}}]
  • alibaba/qwen3-coder-480b-a35b-instruct — tiers: missing → [{"input":2.7,"output":13.5,"tier":{"type":"context","size":32000}},{"input":4.5,"output":22.5,"tier":{"type":"context","size":128000}}]
  • alibaba/qwen3.7-plus — cache_read: 0.05 → 0.04; cache_write: 0.625 → 0.5; context_over_200k: {"input":2,"output":6,"cache_read":0.2,"cache_write":2.5} → {"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5}; input: 0.5 → 0.4; output: 3 → 1.6; tiers: [{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}] → [{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5,"tier":{"type":"context","size":256000}}]
  • amazon-bedrock/amazon.nova-2-lite-v1:0 — cache_read: missing → 0.0825; cache_write: missing → 0.33
  • amazon-bedrock/amazon.nova-lite-v1:0 — cache_write: missing → 0.06
  • amazon-bedrock/amazon.nova-micro-v1:0 — cache_write: missing → 0.035
  • amazon-bedrock/amazon.nova-pro-v1:0 — cache_write: missing → 0.8
  • amazon-bedrock/anthropic.claude-opus-4-6-v1 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/anthropic.claude-sonnet-4-6 — cache_read: 0.3 → 0.33; cache_write: 3.75 → 4.125; input: 3 → 3.3; output: 15 → 16.5
  • amazon-bedrock/au.anthropic.claude-haiku-4-5-20251001-v1:0 — cache_read: 0.1 → 0.11; cache_write: 1.25 → 1.375; input: 1 → 1.1; output: 5 → 5.5
  • amazon-bedrock/au.anthropic.claude-opus-4-6-v1 — cache_read: 1.65 → 0.55; cache_write: 20.625 → 6.875; input: 16.5 → 5.5; output: 82.5 → 27.5
  • amazon-bedrock/au.anthropic.claude-opus-4-8 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/au.anthropic.claude-opus-5 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/au.anthropic.claude-sonnet-4-5-20250929-v1:0 — cache_read: 0.3 → 0.33; cache_write: 3.75 → 4.125; input: 3 → 3.3; output: 15 → 16.5
  • amazon-bedrock/au.anthropic.claude-sonnet-5 — cache_read: 0.2 → 0.22; cache_write: 2.5 → 2.75; input: 2 → 2.2; output: 10 → 11
  • amazon-bedrock/global.openai.gpt-5.6-luna — cache_read: 0.022 → 0.02; cache_write: 0.275 → 0.25; context_over_200k: {"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55} → {"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}; input: 0.22 → 0.2; output: 1.32 → 1.2; tiers: [{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55,"tier":{"type":"context","size":272000}}] → [{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}]
  • amazon-bedrock/global.openai.gpt-5.6-sol — cache_read: 0.55 → 0.4; cache_write: 6.875 → 5; context_over_200k: {"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75} → {"input":8,"output":30,"cache_read":0.8,"cache_write":10}; input: 5.5 → 4; output: 33 → 20; tiers: [{"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75,"tier":{"type":"context","size":272000}}] → [{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}]
  • amazon-bedrock/global.openai.gpt-5.6-terra — cache_read: 0.22 → 0.2; cache_write: 2.75 → 2.5; context_over_200k: {"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5} → {"input":4,"output":18,"cache_read":0.4,"cache_write":5}; input: 2.2 → 2; output: 13.2 → 12; tiers: [{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}] → [{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}]
  • amazon-bedrock/google.gemma-3-12b-it — input: 0.049999999999999996 → 0.09; output: 0.09999999999999999 → 0.29
  • amazon-bedrock/google.gemma-3-27b-it — input: 0.12 → 0.23; output: 0.2 → 0.38
  • amazon-bedrock/jp.anthropic.claude-haiku-4-5-20251001-v1:0 — cache_read: 0.1 → 0.11; cache_write: 1.25 → 1.375; input: 1 → 1.1; output: 5 → 5.5
  • amazon-bedrock/jp.anthropic.claude-opus-4-7 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/jp.anthropic.claude-opus-4-8 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/jp.anthropic.claude-opus-5 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/jp.anthropic.claude-sonnet-4-5-20250929-v1:0 — cache_read: 0.3 → 0.33; cache_write: 3.75 → 4.125; input: 3 → 3.3; output: 15 → 16.5
  • amazon-bedrock/jp.anthropic.claude-sonnet-4-6 — cache_read: 0.3 → 0.33; cache_write: 3.75 → 4.125; input: 3 → 3.3; output: 15 → 16.5
  • amazon-bedrock/jp.anthropic.claude-sonnet-5 — cache_read: 0.2 → 0.22; cache_write: 2.5 → 2.75; input: 2 → 2.2; output: 10 → 11
  • amazon-bedrock/mistral.voxtral-small-24b-2507 — input: 0.15 → 0.1; output: 0.35 → 0.3
  • amazon-bedrock/openai.gpt-5.6-sol — cache_read: 0.55 → 0.44; cache_write: 6.875 → 5.5; context_over_200k: {"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75} → {"input":8.8,"output":33,"cache_read":0.88,"cache_write":11}; input: 5.5 → 4.4; output: 33 → 22; tiers: [{"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75,"tier":{"type":"context","size":272000}}] → [{"input":8.8,"output":33,"cache_read":0.88,"cache_write":11,"tier":{"type":"context","size":272000}}]
  • amazon-bedrock/qwen.qwen3-coder-480b-a35b-v1:0 — input: 0.22 → 0.45
  • amazon-bedrock/qwen.qwen3-coder-next — input: 0.22 → 0.5; output: 1.8 → 1.2
  • amazon-bedrock/qwen.qwen3-next-80b-a3b — input: 0.14 → 0.15; output: 1.4 → 1.2
  • amazon-bedrock/qwen.qwen3-vl-235b-a22b — input: 0.3 → 0.53; output: 1.5 → 2.66
  • amazon-bedrock/us.anthropic.claude-fable-5 — cache_read: 1 → 1.1; cache_write: 12.5 → 13.75; input: 10 → 11; output: 50 → 55
  • amazon-bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0 — cache_read: 0.1 → 0.11; cache_write: 1.25 → 1.375; input: 1 → 1.1; output: 5 → 5.5
  • amazon-bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/us.anthropic.claude-opus-4-6-v1 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/us.anthropic.claude-opus-4-7 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/us.anthropic.claude-opus-4-8 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/us.anthropic.claude-opus-5 — cache_read: 0.5 → 0.55; cache_write: 6.25 → 6.875; input: 5 → 5.5; output: 25 → 27.5
  • amazon-bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0 — cache_read: 0.3 → 0.33; cache_write: 3.75 → 4.125; input: 3 → 3.3; output: 15 → 16.5
  • amazon-bedrock/us.anthropic.claude-sonnet-4-6 — cache_read: 0.3 → 0.33; cache_write: 3.75 → 4.125; input: 3 → 3.3; output: 15 → 16.5
  • amazon-bedrock/us.anthropic.claude-sonnet-5 — cache_read: 0.2 → 0.22; cache_write: 2.5 → 2.75; input: 2 → 2.2; output: 10 → 11
  • azure/gpt-5.6-sol — input: 5 → 4; output: 30 → 20
  • chutes/Qwen/Qwen3.8-27B-TEE — cache_read: 0.03499999999999999 → 0.023999999999999994; input: 0.35 → 0.24; output: 2.75 → 2.2
  • chutes/deepseek-ai/DeepSeek-V4-Flash-0731-TEE — cache_read: 0.013999999999999999 → 0.04399999999999999; input: 0.14 → 0.44; output: 0.28 → 1.32
  • chutes/moonshotai/Kimi-K2.6-TEE — cache_read: 0.05799999999999998 → 0.04999999999999999; input: 0.58 → 0.5; output: 3.4 → 2.85
  • cloudflare-ai-gateway/openai/gpt-5.4 — context_over_200k: {"input":5,"output":22.5,"cache_read":0.5} → missing; tiers: [{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}] → missing
  • cloudflare-ai-gateway/openai/gpt-5.4-pro — context_over_200k: {"input":60,"output":270} → missing; tiers: [{"input":60,"output":270,"tier":{"type":"context","size":272000}}] → missing
  • cloudflare-ai-gateway/openai/gpt-5.5 — cache_read: 0.5 → missing; context_over_200k: {"input":10,"output":45,"cache_read":1} → missing; tiers: [{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}] → missing
  • cloudflare-ai-gateway/openai/gpt-5.5-pro — context_over_200k: {"input":60,"output":270} → missing; tiers: [{"input":60,"output":270,"tier":{"type":"context","size":272000}}] → missing
  • cloudflare-ai-gateway/openai/gpt-5.6-luna — context_over_200k: {"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5} → missing; tiers: [{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}] → missing
  • cloudflare-ai-gateway/openai/gpt-5.6-sol — cache_read: 0.5 → 0.25; cache_write: 6.25 → 3.125; context_over_200k: {"input":10,"output":45,"cache_read":1,"cache_write":12.5} → missing; input: 5 → 2; output: 30 → 10; tiers: [{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}] → missing
  • cloudflare-ai-gateway/openai/gpt-5.6-terra — context_over_200k: {"input":4,"output":18,"cache_read":0.4,"cache_write":5} → missing; tiers: [{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}] → missing
  • cloudflare-workers-ai/@cf/google/gemma-4-26b-a4b-it — cache_read: missing → 0.05
  • cortecs/claude-sonnet-4 — cache_read: 0.29 → 0.296; cache_write: 3.624 → 3.707; input: 2.898 → 2.989; output: 14.493 → 14.945
  • cortecs/codestral-2508 — cache_read: 0.033 → 0.037; input: 0.334 → 0.368; output: 1.003 → 1.103
  • cortecs/deepseek-v3.2 — cache_read: 0.075 → 0.15; input: 0.296 → 0.5; output: 0.495 → 1.499
  • cortecs/deepseek-v4-flash-0731 — cache_read: 0.03 → 0.014; input: 0.13 → 0.09; output: 0.28 → 0.17
  • cortecs/deepseek-v4-pro — cache_read: 0.432 → 0.15; input: 1.73 → 1.7; output: 3.46 → 3.4
  • cortecs/devstral-2512 — input: 0.446 → 0.478; output: 2.228 → 2.392
  • cortecs/gemini-3.5-flash-lite — cache_write: missing → 0.082
  • cortecs/glm-5.2 — cache_read: 0.26 → 0.189; input: 1.2 → 0.9; output: 4.2 → 3.24
  • cortecs/gpt-5.6-sol — cache_read: 0.55 → 0.44; cache_write: 6.879 → 5.5; input: 5.5 → 4.399; output: 32.998 → 21.998
  • cortecs/kimi-k2.6 — cache_read: 0.193 → 0.1; input: 0.773 → 0.475; output: 3.38 → 2.97
  • cortecs/kimi-k2.7-code — cache_read: 0.201 → 0.18; input: 0.75 → 0.656; output: 3.5 → 3.3
  • cortecs/llama-3.3-70b-instruct — input: 0.129 → 0.724; output: 0.399 → 0.724
  • cortecs/minimax-m2.5 — input: 0.296 → 0.348; output: 1.186 → 1.39
  • cortecs/minimax-m3 — cache_read: 0.099 → 0.06; input: 0.395 → 0.3; output: 1.977 → 1.2
  • cortecs/ministral-14b-2512 — input: 0.223 → 0.24; output: 0.223 → 0.24
  • cortecs/ministral-3b-2512 — cache_read: 0.011 → 0.012; input: 0.111 → 0.123; output: 0.111 → 0.123
  • cortecs/ministral-8b-2512 — input: 0.167 → 0.179; output: 0.167 → 0.179
  • cortecs/mistral-large-2512 — cache_read: 0.056 → 0.061; input: 0.557 → 0.613; output: 1.671 → 1.838
  • cortecs/mistral-medium-3.5 — cache_read: missing → 0.154; input: 1.671 → 1.532; output: 5.57 → 7.843
  • cortecs/mistral-small-2603 — cache_read: 0.014 → 0.016; input: 0.143 → 0.156; output: 0.568 → 0.625
  • cortecs/qwen2.5-vl-72b-instruct — input: 0.25 → 1.014; output: 0.747 → 1.014
  • cortecs/qwen3-235b-a22b-instruct-2507 — input: 0.069 → 0.199; output: 0.455 → 0.598
  • cortecs/qwen3-32b — input: 0.099 → 0.179; output: 0.299 → 0.697
  • cortecs/qwen3.8-27b — cache_read: 0.111 → 0.04; input: 0.334 → 0.1; output: 2.451 → 0.4
  • cortecs/voxtral-small-2507 — cache_read: 0.011 → 0.012; input: 0.111 → 0.123; output: 0.334 → 0.368
  • crof/deepseek-v4-flash-0731 — input: 0.12 → 0.08; output: 0.21 → 0.1
  • …and 584 more

An extended generated list is available in the workflow run summary.

Generated automatically by the weekly pricing refresh workflow.


Note

Medium Risk
Bulk pricing snapshot changes directly affect cost calculations and model lookup; scope is large but routine and test-validated.

Overview
Refreshes the embedded models.dev.json pricing catalog in relayburn-sdk from the upstream models.dev API (weekly workflow). The SDK loads this snapshot at compile time via include_str! for token/cost estimation.

Catalog size: providers 195 → 226, models 7293 → 8388. The update adds many new first-party and reseller entries (e.g. Claude 5.x, GPT-6 variants, gemini-3.8-flash, Grok 4.7) and drops retired listings (e.g. google/gemini-robotics-er-1.6-preview, xai/grok-imagine-image-2.0).

Pricing deltas: hundreds of models have revised tariffs—notably openai/gpt-5.6 and openai/gpt-5.6-sol (lower input/output/cache and updated context-over-200k tiers)—plus widespread tier/cache_read additions and Bedrock/Alibaba adjustments. The append-only primary-model-ids.json union keeps historical primary IDs so retired first-party models do not silently pick up reseller rates.

Validation noted in the PR: JSON parse, provider/model counts, critical-model integrity checks, and cargo test -p relayburn-sdk.

Reviewed by Cursor Bugbot for commit 3b07d92. Bugbot is set up for automated code reviews on this repo. Configure here.

@coderabbitai

coderabbitai Bot commented Sep 21, 2026 •

Copy link
Copy Markdown

Important

Review skipped

Bot user detected.

To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration
  • Configuration used: Organization UI
  • Review profile: CHILL
  • Plan: Advanced
  • Run ID: a01d0551-4d79-4a08-968a-9effc92fc62d

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review
  • Autopilot · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@devin-ai-integration devin-ai-integration Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

✅ Devin Review: No Issues Found

Devin Review analyzed this PR and found no bugs or issues to report.

Devin Review

@github-actions
github-actions Bot force-pushed the automation/models-dev-pricing branch from 3cf25ea to 7d85cf7 Compare September 28, 2026 09:41
@github-actions
github-actions Bot force-pushed the automation/models-dev-pricing branch from 7d85cf7 to 3b07d92 Compare October 5, 2026 09:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant