Uh oh!
There was an error while loading. Please reload this page.
chore(pricing): refresh models.dev snapshot - #537
Open
github-actions[bot] wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Refreshes the vendored models.dev pricing snapshot from the upstream API.
Providers: 191 → 195. Models: 6728 → 7293.
Validation
cargo test -p relayburn-sdkpassed with the refreshed snapshot embedded.GITHUB_TOKEN, so GitHub does not automatically triggerpull_requestworkflows for it; the full SDK suite ran in the update workflow instead.Primary-provider models added (1)
google-vertex/claude-fable-5@defaultOther models added (624)
agentrouter/claude-opus-4-8agentrouter/claude-opus-5agentrouter/gpt-5.6-solaki-io/deepseek-v4-flash-0731-284baki-io/qwen3.8-27bamazon-bedrock/xai.grok-4.6azure-cognitive-services/claude-opus-4-7azure/claude-opus-4-7crof/qwen3.8-27bcrossmodel/deepseek/deepseek-v4-flash-vision-expcrossmodel/z-ai/glm-5.3deepseek/deepseek-v4-flash-vision-expecho/echoedenai/deepseek/deepseek-v4-flash-vision-expedenai/nebius/deepseek-ai/DeepSeek-V4-Flash-0731edenai/qwen/qwen3.8-27bedenai/zai/glm-5.3empiriolabs/glm-4-6v-flashempiriolabs/glm-5-3google-vertex-anthropic/claude-fable-5@defaulthetzner/Qwen3.8-27Bhuggingface/zai-org/GLM-4.6V-Flashkilo/deepseek/deepseek-v4-flash-vision-expkilo/liquid/lfm-2.5-2.6b:freekilo/meituan/longcat-2.0-freekilo/meta/muse-spark-1.2-contributorkilo/mistralai/ministral-8bkilo/openai/gpt-5.6-sol-discountedkilo/stealth/ox-alphakilo/tencent/hy-mt2-1.8bkilo/tencent/hy-mt2-30b-a3bkilo/tencent/hy-mt2-7bkilo/thinkingmachines/inkling-small:freekilo/thinkingmachines/inkling:freekilo/z-ai/glm-5.3kilo/~z-ai/glm-latestllmgateway-providers/alibaba/deepseek-v4-flashllmgateway-providers/alibaba/deepseek-v4-prollmgateway-providers/alibaba/glm-5llmgateway-providers/alibaba/glm-5.2llmgateway-providers/alibaba/kimi-k2.5llmgateway-providers/alibaba/qwen-coder-plusllmgateway-providers/alibaba/qwen-flashllmgateway-providers/alibaba/qwen-maxllmgateway-providers/alibaba/qwen-omni-turbollmgateway-providers/alibaba/qwen-plusllmgateway-providers/alibaba/qwen-plus-latestllmgateway-providers/alibaba/qwen3-coder-flashllmgateway-providers/alibaba/qwen3-coder-plusllmgateway-providers/alibaba/qwen3-maxllmgateway-providers/alibaba/qwen3-vl-flashllmgateway-providers/alibaba/qwen3-vl-plusllmgateway-providers/alibaba/qwen3.6-35b-a3bllmgateway-providers/alibaba/qwen3.6-flashllmgateway-providers/alibaba/qwen3.6-max-previewllmgateway-providers/alibaba/qwen3.6-plusllmgateway-providers/alibaba/qwen3.7-flashllmgateway-providers/alibaba/qwen3.7-maxllmgateway-providers/alibaba/qwen3.7-plusllmgateway-providers/alibaba/qwen3.8-maxllmgateway-providers/alibaba/qwen35-397b-a17bllmgateway-providers/anthropic/claude-fable-5llmgateway-providers/anthropic/claude-haiku-4-5llmgateway-providers/anthropic/claude-haiku-4-5-20251001llmgateway-providers/anthropic/claude-opus-4-5-20251101llmgateway-providers/anthropic/claude-opus-4-6llmgateway-providers/anthropic/claude-opus-4-7llmgateway-providers/anthropic/claude-opus-4-8llmgateway-providers/anthropic/claude-opus-5llmgateway-providers/anthropic/claude-sonnet-4-5llmgateway-providers/anthropic/claude-sonnet-4-5-20250929llmgateway-providers/anthropic/claude-sonnet-4-6llmgateway-providers/anthropic/claude-sonnet-5llmgateway-providers/aws-bedrock/claude-fable-5llmgateway-providers/aws-bedrock/claude-haiku-4-5llmgateway-providers/aws-bedrock/claude-haiku-4-5-20251001llmgateway-providers/aws-bedrock/claude-opus-4-1-20250805llmgateway-providers/aws-bedrock/claude-opus-4-5-20251101llmgateway-providers/aws-bedrock/claude-opus-4-6llmgateway-providers/aws-bedrock/claude-opus-4-7llmgateway-providers/aws-bedrock/claude-opus-4-8llmgateway-providers/aws-bedrock/claude-opus-5llmgateway-providers/aws-bedrock/claude-sonnet-4-5llmgateway-providers/aws-bedrock/claude-sonnet-4-5-20250929llmgateway-providers/aws-bedrock/claude-sonnet-4-6llmgateway-providers/aws-bedrock/claude-sonnet-5llmgateway-providers/aws-bedrock/grok-4-3llmgateway-providers/aws-bedrock/grok-4-6llmgateway-providers/aws-bedrock/llama-3.1-70b-instructllmgateway-providers/aws-bedrock/llama-4-maverick-17b-instructllmgateway-providers/aws-bedrock/llama-4-scout-17b-instructllmgateway-providers/aws-mantle/gpt-5.6-lunallmgateway-providers/aws-mantle/gpt-5.6-solllmgateway-providers/aws-mantle/gpt-5.6-terrallmgateway-providers/azure-ai-foundry/grok-4-1-fast-non-reasoningllmgateway-providers/azure-ai-foundry/grok-4-1-fast-reasoningllmgateway-providers/azure-ai-foundry/grok-4-3llmgateway-providers/azure/gpt-3.5-turbollmgateway-providers/azure/gpt-4llmgateway-providers/azure/gpt-4-turboPrimary-provider models removed (0)
None.
Other models removed (60)
aki-io/minimax-m2.5-230bcrof/glm-4.7crof/glm-4.7-flashcrof/glm-5crof/kimi-k2.5crof/kimi-k2.5-lightningcrof/minimax-m2.5edenai/deepinfra/tencent/Hy3edenai/tensorx/qwen/qwen3.8-27bhetzner/DeepSeek-V4-Flash-0731hetzner/GLM-5.2-NVFP4hetzner/Kimi-K2.7-Codeinceptron/MiniMaxAI/MiniMax-M2.5kilo/ai21/jamba-large-1.7kilo/deepcogito/cogito-v2.1-671bkilo/deepseek/deepseek-v4-flash:discountedkilo/deepseek/deepseek-v4-pro:discountedkilo/stealth/gpt-5.6-solkilo/z-ai/glm-5.2:freellmgateway/claude-3-opusllmgateway/gpt-4o-mini-search-previewllmgateway/gpt-4o-search-previewllmgateway/seed-2-1-turbonano-gpt/TEE/deepseek-v4-pro-0813nano-gpt/TEE/deepseek-v4-pro-0813:thinkingnano-gpt/amazon/nova-micro-v1openrouter/ai21/jamba-large-1.7openrouter/deepcogito/cogito-v2.1-671bopenrouter/openai/gpt-oss-20b:freescx/MiniMax-M2.7scx/gpt-oss-120bumans-ai-coding-plan/umans-glm-5.1umans-ai/umans-glm-5.1venice/nvidia-nemotron-3-5-lightning-30b-a3bvercel/google/imagen-4.0-fast-generate-001vercel/google/imagen-4.0-generate-001vercel/google/imagen-4.0-ultra-generate-001vercel/xai/grok-4.1-fast-non-reasoningvercel/xai/grok-4.1-fast-reasoningvercel/xai/grok-4.20-multi-agentvercel/xai/grok-4.20-multi-agent-betavercel/xai/grok-4.20-non-reasoningvercel/xai/grok-4.20-non-reasoning-betavercel/xai/grok-4.20-reasoningvercel/xai/grok-4.20-reasoning-betavercel/xai/grok-4.3vercel/xai/grok-4.5vercel/xai/grok-4.6vercel/xai/grok-build-0.1vercel/xai/grok-imagine-imagevercel/xai/grok-imagine-image-2.0vercel/xai/grok-imagine-videovercel/xai/grok-imagine-video-1.5vercel/xai/grok-imagine-video-1.5-previewvercel/xai/grok-sttvercel/xai/grok-ttsvercel/xai/grok-voice-think-fast-1.0vercel/xai/grok-voice-think-fast-2.0vercel/zai/glm-4.6vvercel/zai/glm-4.6v-flashPrimary-provider price fields changed (11)
google-vertex/deepseek-ai/deepseek-v3.1-maas— cache_read:missing→0.06google-vertex/gemini-2.5-flash— cache_read:0.075→0.03; cache_write:0.383→missing; input_audio:missing→1google-vertex/gemini-3-pro-image— cache_read:missing→0.2google-vertex/gemini-3.1-flash-image— cache_read:missing→0.05google-vertex/gemini-3.6-flash— cache_read:0.15→0.075; input:1.5→0.75; input_audio:1.5→0.75; output:7.5→3.75google-vertex/moonshotai/kimi-k2-thinking-maas— cache_read:missing→0.06google-vertex/openai/gpt-oss-20b-maas— cache_read:missing→0.007google-vertex/zai-org/glm-4.7-maas— cache_read:missing→0.06google/gemini-3.6-flash— cache_read:0.15→0.075; input:1.5→0.75; input_audio:1.5→0.75; output:7.5→3.75google/gemini-flash-latest— cache_read:0.15→0.075; input:1.5→0.75; input_audio:1.5→0.75; output:9→3.75google/gemini-flash-lite-latest— cache_read:0.025→0.03; input:0.25→0.3; input_audio:0.5→missing; output:1.5→2.5Other price fields changed (172)
aki-io/kimi-k2.7-code-1100b— cache_read:missing→0.18alibaba-cn/qwen-plus— cache_read:missing→0.012; cache_write:missing→0.144ambient/ambient/large— cache_read:0.2→0.15; input:1.05→0.6; output:4.4→2ambient/deepseek/deepseek-v4-flash-0731— cache_read:0.028→0.016; input:0.14→0.08; output:0.28→0.18ambient/z-ai/glm-5.2— cache_read:0.2→0.15; input:1.05→0.6; output:4.4→2chutes/Qwen/Qwen3.8-27B-TEE— cache_read:0.039999999999999994→0.03499999999999999; input:0.4→0.35; output:3→2.75cortecs/gpt-5.6-luna— cache_read:0.11→0.022; cache_write:1.38→0.275; input:1.1→0.219; output:6.599→1.32cortecs/gpt-5.6-terra— cache_read:0.275→0.219; cache_write:3.437→2.749; input:2.749→2.2; output:16.498→13.199cortecs/minimax-m2.5— cache_read:0.03→0.075; output:1.087→1.186digitalocean/glm-5— input:0.75→1; output:2.4→3.2digitalocean/glm-5.1— input:0.975→1.3digitalocean/kimi-k2.5— input:0.375→0.5; output:2.025→2.7digitalocean/kimi-k2.6— input:0.76→0.95; output:3.2→4digitalocean/minimax-m2.5— input:0.225→0.3; output:0.9→1.2digitalocean/nvidia-nemotron-3-super-120b— input:0.165→0.3; output:0.3575→0.65digitalocean/qwen3.5-397b-a17b— input:0.3025→0.55; output:1.925→3.5edenai/deepseek/deepseek-v4-flash— cache_read:0.007→0.014; input:0.22→0.44; output:0.66→1.32edenai/deepseek/deepseek-v4-pro— cache_read:0.022→0.044; input:0.66→1.32; output:1.98→3.96edenai/fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731— cache_read:0.028→0.007; input:0.14→0.22; output:0.28→0.66edenai/google/gemini-3.7-flash— cache_read:0.075→0.15; cache_write:0.041667→0.083333; input:0.75→1.5; input_audio:0.75→1.5; output:3.75→7.5; reasoning:3.75→7.5edenai/google/gemini-flash-latest— cache_read:0.075→0.15; cache_write:0.041667→0.083333; input:0.75→1.5; input_audio:0.75→1.5; output:3.75→7.5; reasoning:3.75→7.5edenai/ionos/meta-llama/Llama-3.3-70B-Instruct— input:0.753545→0.760435; output:0.753545→0.760435edenai/ionos/openai/gpt-oss-120b— input:0.173895→0.175485; output:0.753545→0.760435edenai/mistral/codestral-latest— input:1→0.3; output:3→0.9edenai/mistral/mistral-small-latest— input:0.06→0.15; output:0.18→0.6edenai/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}}]edenai/openai/gpt-latest— 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}}]edenai/qwen/deepseek-v4-flash-0731— cache_read:0.04→missing; input:0.2→0.352; output:0.4→1.056edenai/qwen/deepseek-v4-pro-0813— input:1.32→1.1616; output:3.96→3.4848edenai/scaleway/deepseek-v4-flash-0731— input:0.46372→0.46796; output:0.927441→0.93592edenai/scaleway/gpt-oss-120b— input:0.173895→0.175485; output:0.69558→0.70194edenai/scaleway/llama-3.3-70b-instruct— input:1.043371→1.05291; output:1.043371→1.05291edenai/vertex/gemini-3.7-flash— cache_read:0.075→0.15; cache_write:0.041667→0.083333; input:0.75→1.5; input_audio:0.75→1.5; output:3.75→7.5; reasoning:3.75→7.5edenai/vertex/gemini-3.7-flash@eu— cache_read:0.075→0.15; cache_write:0.041667→0.083333; input:0.75→1.5; input_audio:0.75→1.5; output:3.75→7.5; reasoning:3.75→7.5edenai/vertex/gemini-3.7-flash@us— cache_read:0.075→0.15; cache_write:0.041667→0.083333; input:0.75→1.5; input_audio:0.75→1.5; output:3.75→7.5; reasoning:3.75→7.5edenai/vertex/gemini-flash-latest— cache_read:0.075→0.15; cache_write:0.041667→0.083333; input:0.75→1.5; input_audio:0.75→1.5; output:3.75→7.5; reasoning:3.75→7.5empiriolabs/deepseek-v4-flash-0731— cache_read:0.14→0.424; input:0.14→0.424; output:0.28→1.272github-copilot/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}→{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25}; input:5→2.5; output:30→15; tiers:[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}]→[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25,"tier":{"type":"context","size":272000}}]hyper/deepseek-v4-flash-0731— cache_read:0.028→0.015243; input:0.13→0.479072; output:0.26→1.437216hyper/deepseek-v4-pro-0813— cache_read:0.132→0.047907; input:1.32→1.437216; output:3.96→4.311648hyper/gemma-4-26b-a4b-it— cache_write:0.062→0.055; input:0.124→0.11; output:0.42→0.408hyper/glm-5— cache_write:0.4→0.455; input:0.8→0.91; output:2.582→2.934hyper/glm-5.1— cache_read:0.283088→missing; cache_write:missing→0.68; input:1.52432→1.36; output:4.79072→4.4hyper/glm-5.2— cache_read:0.28→0.152432; input:1.4→1.52432; output:4.4→4.79072hyper/gpt-oss-120b— cache_read:0.015243→missing; cache_write:missing→0.094; input:0.16332→0.188; output:0.65328→0.7hyper/kimi-k2.5— cache_write:0.255→0.2722; input:0.51→0.5444; output:2.7→2.855hyper/kimi-k2.6— cache_read:0.16→0.174208; input:0.95→1.03436; output:4→4.3552hyper/kimi-k2.7-code— cache_read:0.19→0.206872; input:0.95→1.03436; output:4→4.3552hyper/kimi-k3— cache_read:0.3→0.32664; input:3→3.2664; output:15→16.332hyper/llama-3.3-70b-instruct— cache_write:0.299→0.319; input:0.598→0.638; output:0.738→0.768hyper/minimax-m2.7— cache_write:0.205→0.204; input:0.41→0.408; output:1.52→1.512kilo/deepseek/deepseek-v4-flash-0731— input:0.14→0.44; output:0.28→1.32kilo/google/gemini-3.7-flash— cache_read:0.075→0.15; cache_write:0.041667→0.083333; input:0.75→1.5; output:3.75→7.5; reasoning:3.75→7.5kilo/google/gemma-4-26b-a4b-it— input:0.07→0.042; output:0.34→0.22kilo/meta/muse-glimmer-30b— output:1.2→1.1kilo/mistralai/mistral-small-3.2-24b-instruct— input:0.09375→0.075; output:0.25→0.2kilo/nvidia/nemotron-3-nano-30b-a3b— cache_read:0.03→0.025kilo/openai/gpt-5.6-sol— cache_read:0.5→0.4; cache_write:6.25→5; input:5→4; output:30→20kilo/openai/gpt-5.6-sol-pro— cache_read:0.5→0.4; cache_write:6.25→5; input:5→4; output:30→20kilo/qwen/qwen3.8-27b— cache_read:0.05→0.085; cache_write:missing→0.53125; input:0.45→0.425; output:3.2→2.55kilo/~deepseek/deepseek-v4-flash-latest— cache_read:0.015719→0.008; input:0.078596→0.04; output:0.157192→0.08kilo/~openai/gpt-latest— cache_read:0.25→0.2; cache_write:3.125→2.5; input:2.5→2; output:15→10llmgateway/gpt-oss-20b— input:0.04→0.05; output:0.15→0.2llmgateway/nemotron-3-ultra-550b— cache_read:0.15→0.1; output:2.5→2.2llmgateway/qwen3-coder-480b-a35b-instruct— input:0.3→0.38; output:1.3→1.55llmgateway/qwen3.7-max— cache_read:0.125→0.25merge-gateway/deepseek/deepseek-v4-flash— cache_read:0.0028→0.007; input:0.14→0.22; output:0.28→0.66merge-gateway/deepseek/deepseek-v4-flash-0731— cache_read:0.0028→0.007; input:0.14→0.035; output:0.28→0.07merge-gateway/deepseek/deepseek-v4-pro— cache_read:0.003625→0.022; input:0.435→0.66; output:0.87→1.98merge-gateway/deepseek/deepseek-v4-pro-0813— cache_read:0.003625→0.022; input:0.435→0.66; output:0.87→1.98merge-gateway/openai/gpt-5.6-sol— input:5→4; output:30→24nano-gpt/google/gemini-flash-latest— cache_read:0.075→0.0375; cache_write:0.041667→0.020833; input:0.75→0.375; output:3.75→1.875nano-gpt/google/gemma-4-26b-a4b-it— cache_read:0.065→0.04; input:0.13→0.08; output:0.4→0.33nano-gpt/google/gemma-4-31b-it— cache_read:0.05→0.04; input:0.1→0.08; output:0.35→0.33nano-gpt/openai/gpt-5.6-sol— cache_read:0.5→0.25; cache_write:6.25→3.125; input:5→2.5; output:30→15nano-gpt/openai/gpt-5.6-sol-pro— cache_read:0.5→0.25; cache_write:6.25→3.125; input:5→2.5; output:30→15nano-gpt/openai/gpt-chat-latest— cache_read:0.5→0.25; cache_write:6.25→3.125; input:5→2.5; output:30→15nano-gpt/openai/gpt-latest— cache_read:0.5→0.25; cache_write:6.25→3.125; input:5→2.5; output:30→15nano-gpt/venice-uncensored— cache_read:0.2→0.4; output:0.4→1.8ofox/bailian/qwen3.6-max-preview— cache_write:2→1.17; input:2→2.15; output:12→12.86ofox/google/gemini-3.6-flash— cache_read:0.15→0.075; cache_write:0.083→0.0415; input:1.5→0.75; output:7.5→3.75ofox/openai/gpt-5.6-sol— cache_read:0.5→0.25; cache_write:6.25→3.125; input:5→2.5; output:30→15ofox/volcengine/doubao-seed-2.1-pro— cache_read:0.177→0.1416; cache_write:0.0025→0.002; input:0.884→0.7072; output:4.42→3.536ofox/volcengine/doubao-seed-2.1-turbo— cache_read:0.085→0.068; cache_write:0.0024→0.0019; input:0.442→0.3536; output:2.212→1.7696ofox/z-ai/glm-5.2— cache_read:0.26→0.182; input:1.4→0.98; output:4.4→3.08opencode-go/gpt-5.6-luna— cache_read:0.01→0.02; cache_write:0.125→0.25; context_over_200k:{"input":0.2,"output":0.9,"cache_read":0.02,"cache_write":0.25}→{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}; input:0.1→0.2; output:0.6→1.2; tiers:[{"input":0.2,"output":0.9,"cache_read":0.02,"cache_write":0.25,"tier":{"type":"context","size":272000}}]→[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}]opencode-go/hy3— cache_read:0.035→0.004375; input:0.14→0.0175; output:0.58→0.0725opencode/gpt-5.6-sol— cache_read:0.5→0.2; cache_write:6.25→2.5; context_over_200k:{"input":10,"output":45,"cache_read":1,"cache_write":12.5}→{"input":4,"output":15,"cache_read":0.4,"cache_write":5}; input:5→2; output:30→10; tiers:[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}]→[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}]openrouter/deepseek/deepseek-chat-v3-0324— cache_read:0.135→missing; input:0.27→0.25; output:1.12→1openrouter/deepseek/deepseek-chat-v3.1— cache_read:0.13→0.55; input:0.25→0.55; output:0.95→1.65openrouter/deepseek/deepseek-v3.1-terminus— cache_read:missing→0.135openrouter/deepseek/deepseek-v3.2— cache_read:0.1345→0.13; input:0.269→0.26; output:0.4→0.38openrouter/deepseek/deepseek-v4-flash— cache_read:0.01652→0.01148; input:0.0826→0.0574; output:0.1652→0.1148openrouter/deepseek/deepseek-v4-pro— cache_read:0.022→0.043848; input:0.66→0.526176; output:1.98→1.052352openrouter/deepseek/deepseek-v4-pro-0813— cache_read:0.022→0.0374; input:0.66→1.122; output:1.98→3.366openrouter/minimax/minimax-m2.5— cache_read:0.05→0.027; input:0.22→0.27; output:0.9→1.08openrouter/minimax/minimax-m2.7— cache_read:0.06→0.048; input:0.3→0.24; output:1.2→0.96openrouter/mistralai/mistral-small-3.2-24b-instruct— input:0.09375→0.075; output:0.25→0.2openrouter/moonshotai/kimi-k2.5— cache_read:0.095→0.07; input:0.57→0.45; output:2.85→2.25openrouter/moonshotai/kimi-k2.7-code— cache_read:0.15→0.17; input:0.71→0.67; output:3.5→3.4An extended generated list is available in the workflow run summary.
Generated automatically by the weekly pricing refresh workflow.