Repository navigation
chore: refresh models.dev snapshot (+151 -138 ~264) - #4573
Merged
Merged
Conversation
aheritier
approved these changes
Oct 13, 2026
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 free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Automated refresh of the models.dev catalog snapshot embedded in the
docker-agent binary (
pkg/modelsdev/snapshot.json).Added (151)
302ai/claude-haiku-5-5302ai/gpt-6.1-solaihubmix/coding-glm-5.3-flash-freeaihubmix/coding-glm-5.3-freeambient/qwen/qwen3-30b-a3b-instruct-2507ambient/qwen/qwen3.6-35b-a3bazure/deepseek-v4.1-flashcortecs/claude-haiku-5.5crossmodel/anthropic/claude-haiku-5-5deepinfra/Qwen/Qwen3-VL-30B-A3B-Instructdigitalocean/anthropic-claude-5.5-haikuedenai/amazon/qwen.qwen3-coder-nextedenai/cloudflare/?cf/meta/llama-3.2-1b-instructedenai/databricks/databricks-qwen3-next-80b-a3b-instructedenai/databricks/databricks-qwen3-next-80b-a3b-instruct?euedenai/deepinfra/Gryphe/MythoMax-L2-13bedenai/deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507edenai/deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instructedenai/deepinfra/Qwen/Qwen3-Maxedenai/deepinfra/Qwen/Qwen3-Next-80B-A3B-Instructedenai/deepinfra/Qwen/Qwen3-VL-235B-A22B-Instructedenai/deepinfra/Qwen/Qwen3-VL-30B-A3B-Instructedenai/deepinfra/deepseek-ai/DeepSeek-R1-0528edenai/deepinfra/microsoft/WizardLM-2-8x22Bedenai/deepinfra/moonshotai/Kimi-K2-Instructedenai/flexai/Muse-Glimmer-30Bedenai/google/gemini-nano-banana-2.1edenai/ionos/Qwen/Qwen3-Coder-Nextedenai/nebius/Qwen/Qwen3-235B-A22B-Instruct-2507edenai/qwen/qwen-mt-plusedenai/scaleway/qwen3-235b-a22b-instruct-2507edenai/scaleway/qwen3-coder-30b-a3b-instructedenai/tensorx/deepseek/deepseek-r1-0528edenai/vertex/gemini-nano-banana-2.1github-copilot/claude-haiku-5.5google-vertex/codestral-2google-vertex/gemini-3.1-flash-lite-imagegoogle-vertex/gemini-nano-banana-2.1google-vertex/google/gemma-4-26b-a4b-it-maasgoogle-vertex/meta/llama-4-scout-17b-16e-instruct-maasgoogle-vertex/mistral-medium-3google-vertex/mistral-small-2503google-vertex/xai/grok-4.7huggingface/MiniMaxAI/MiniMax-M1-80khuggingface/Qwen/Qwen3-VL-30B-A3B-Instructhuggingface/zai-org/AutoGLM-Phone-9B-Multilingualkilo/inclusionai/ling-3.0-flash-santekilo/stealth/glyph-clusterkilo/stepfun/step-5-previewkilo/stepfun/step-5-preview-freellmgateway/reka-edge-2603llmgateway-providers/reka-ai/deepseek-v4-flashllmgateway-providers/reka-ai/deepseek-v4-prollmgateway-providers/reka-ai/glm-5.3llmgateway-providers/reka-ai/glm-5.3-flashllmgateway-providers/reka-ai/qwen3.8-27bllmgateway-providers/reka-ai/reka-edge-2603lowrouter/auto/mistralai/codestral-2508lowrouter/auto/mistralai/ministral-14b-2512lowrouter/auto/mistralai/ministral-3b-2512lowrouter/auto/mistralai/ministral-8b-2512lowrouter/auto/mistralai/mistral-large-2512lowrouter/auto/mistralai/mistral-large-4lowrouter/auto/mistralai/mistral-medium-3.5lowrouter/auto/mistralai/mistral-small-2603merge-gateway/deepseek/deepseek-r1-0528merge-gateway/qwen/qwen3-vl-30b-a3b-instructmoark/DeepSeek-V4-Flashmoark/DeepSeek-V4-Promoark/GLM-5.3moark/Kimi-K2.6moark/MiniMax-M2.7moark/Qwen3.6-Flashmoark/deepseek-v4-flash-0731moark/kimi-k3nano-gpt/gemma-4-26b-a4b-it-chimeraxhereticnano-gpt/gemma-4-31b-it-scarletnearai/Qwen/Qwen3.8-27Bnearai/anthropic/claude-fable-5nearai/anthropic/claude-fable-5-1nearai/anthropic/claude-haiku-5-5nearai/anthropic/claude-opus-4-8nearai/anthropic/claude-opus-5nearai/anthropic/claude-opus-5-5nearai/anthropic/claude-sonnet-5nearai/anthropic/claude-sonnet-5-5nearai/deepseek/deepseek-v3.2nearai/deepseek/deepseek-v4.1-flashnearai/google/gemini-3.8-flashnearai/moonshotai/kimi-k2.6nearai/moonshotai/kimi-k3nearai/openai/gpt-5.6-lunanearai/openai/gpt-5.6-solnearai/openai/gpt-6-astranearai/openai/gpt-6-lunanearai/openai/gpt-6-solnearai/openai/gpt-6.1-solnearai/qwen/qwen3.5-397b-a17bnearai/qwen/qwen3.7-maxnearai/x-ai/grok-4.6nearai/x-ai/grok-4.7nearai/z-ai/glm-5.3-flashneuralwatt/mimo-v2.6-proneuralwatt/mimo-v2.6-pro-flexnovita-ai/apodex/apodex-1.1-mininovita-ai/baai/bge-m3novita-ai/baai/bge-reranker-v2-m3novita-ai/baidu/cobuddynovita-ai/deepseek/deepseek-v4-flash-0731novita-ai/deepseek/deepseek-v4-pro-0813novita-ai/deepseek/deepseek-v4.1-flashnovita-ai/deepseek/deepseek_v3novita-ai/inclusionai/ling-3.0-flashnovita-ai/inclusionai/ling-3.0-flash-finnovita-ai/inclusionai/ling-3.0-flash-santenovita-ai/inclusionai/ling-3.0-flash-vlnovita-ai/inclusionai/ling-3.1-flashnovita-ai/meta-llama/llama-3.2-1b-instructnovita-ai/mindai/macaron-v1-tallnovita-ai/mindai/macaron-v1-ventinovita-ai/minimax/minimax-m3novita-ai/nvidia/nemotron-3-nano-30b-a3bnovita-ai/qwen/qwen3-embedding-8bnovita-ai/qwen/qwen3-reranker-8bnovita-ai/qwen/qwen3.6-27bnovita-ai/qwen/qwen3.6-35b-a3bnovita-ai/qwen/qwen3.8-2.4t-a95bnovita-ai/qwen/qwen3.8-27bnovita-ai/qwen/qwen3.8-flashnovita-ai/qwen/qwen3.8-maxnovita-ai/stepfun/step-3.7-flashnovita-ai/tencent/hy3novita-ai/tencent/hy4-previewnovita-ai/xiaomimimo/mimo-v2.5novita-ai/xiaomimimo/mimo-v2.6-flashnovita-ai/xiaomimimo/mimo-v2.6-pronovita-ai/zai-org/glm-5.3novita-ai/zai-org/glm-5.3-flashofox/anthropic/claude-haiku-5.5opencode/step-5-preview-freeopencode-go/step-5-preview-freeopenrouter/inclusionai/ling-3.0-flash-santeopenrouter/stepfun/step-5-previewrequesty/claude-haiku-5-5requesty/claude-haiku-5-5?eurequesty/kimi-k2.5?euvenice/claude-haiku-5-5venice/openai-gpt-61-sol-ultrafastvercel/callstack/apexvercel/heygen/heygen-video-1vivgrid/claude-haiku-5-5Removed (138)
edenai/qwen/qwen-vl-maxedenai/qwen/qwen-vl-plusedenai/qwen/qwen3-235b-a22b-instruct-2507edenai/qwen/qwen3-coder-30b-a3b-instructedenai/qwen/qwen3-coder-480b-a35b-instructedenai/qwen/qwen3-coder-nextedenai/qwen/qwen3-coder-next?euedenai/qwen/qwen3-coder-plusedenai/qwen/qwen3-maxedenai/qwen/qwen3-max?euedenai/qwen/qwen3-next-80b-a3b-instructedenai/qwen/qwen3-next-80b-a3b-thinkingedenai/qwen/qwen3-vl-235b-a22b-instructedenai/qwen/qwen3-vl-235b-a22b-thinkingedenai/qwen/qwq-plusedenai/tencent/step-5-previewempiriolabs/deepseek-v3-2empiriolabs/deepseek-v4-flashempiriolabs/qwen3-6-max-previewempiriolabs/qwen3-maxgoogle-vertex/gemini-3.1-flash-lite-previewgoogle-vertex/gemini-flash-latestgoogle-vertex/gemini-flash-lite-latesthyper/deepseek-v4-flashhyper/deepseek-v4-prokilo/baidu/ernie-4.5-vl-424b-a47bkilo/inclusionai/ling-3.0-flash-sante:freekilo/qwen/qwen-plus-2025-07-28kilo/qwen/qwen3-235b-a22bkilo/qwen/qwen3-30b-a3b-thinking-2507kilo/qwen/qwen3-8bkilo/qwen/qwen3-coder-pluskilo/qwen/qwen3-maxkilo/qwen/qwen3-max-thinkingkilo/qwen/qwen3-vl-235b-a22b-thinkingkilo/qwen/qwen3-vl-32b-instructkilo/qwen/qwen3-vl-8b-thinkingkilo/qwen/qwen3.6-max-previewkilo/stepfun/step-3.7-flash:freellmgateway/qwen-coder-plusllmgateway/qwen-omni-turbollmgateway/qwen3-coder-plusllmgateway/qwen3-vl-flashllmgateway/qwen3.6-max-previewllmgateway-providers/alibaba/qwen-coder-plusllmgateway-providers/alibaba/qwen-omni-turbollmgateway-providers/alibaba/qwen3-coder-plusllmgateway-providers/alibaba/qwen3-maxllmgateway-providers/alibaba/qwen3-vl-flashllmgateway-providers/alibaba/qwen3.6-max-previewllmgateway-providers/deepinfra/hy3llmgateway-providers/deepinfra/qwen3.8-2.4t-a95bnearai/zai-org/GLM-5.1-FP8novita-ai/baidu/ernie-4.5-21B-a3b-thinkingnovita-ai/baidu/ernie-4.5-300b-a47b-paddlenovita-ai/baidu/ernie-4.5-vl-28b-a3bnovita-ai/baidu/ernie-4.5-vl-28b-a3b-thinkingnovita-ai/baidu/ernie-4.5-vl-424b-a47bnovita-ai/deepseek/deepseek-ocrnovita-ai/deepseek/deepseek-prover-v2-671bnovita-ai/deepseek/deepseek-r1-distill-llama-70bnovita-ai/deepseek/deepseek-r1-distill-qwen-14bnovita-ai/deepseek/deepseek-r1-distill-qwen-32bnovita-ai/deepseek/deepseek-v3-0324novita-ai/deepseek/deepseek-v3-turbonovita-ai/deepseek/deepseek-v3.1novita-ai/deepseek/deepseek-v3.1-terminusnovita-ai/deepseek/deepseek-v3.2novita-ai/deepseek/deepseek-v3.2-expnovita-ai/deepseek/deepseek-v4-flashnovita-ai/inclusionai/ling-2.6-1tnovita-ai/inclusionai/ling-2.6-flashnovita-ai/inclusionai/ring-2.6-1tnovita-ai/kwaipilot/kat-coder-pronovita-ai/meta-llama/llama-3-70b-instructnovita-ai/meta-llama/llama-3-8b-instructnovita-ai/meta-llama/llama-3.2-3b-instructnovita-ai/minimax/minimax-m2novita-ai/minimax/minimax-m2.1novita-ai/minimax/minimax-m2.5-highspeednovita-ai/mistralai/mistral-nemonovita-ai/openai/gpt-oss-20bnovita-ai/qwen/qwen-2.5-72b-instructnovita-ai/qwen/qwen2.5-7b-instructnovita-ai/qwen/qwen2.5-vl-72b-instructnovita-ai/qwen/qwen3-235b-a22b-fp8novita-ai/qwen/qwen3-235b-a22b-instruct-2507novita-ai/qwen/qwen3-235b-a22b-thinking-2507novita-ai/qwen/qwen3-30b-a3b-fp8novita-ai/qwen/qwen3-32b-fp8novita-ai/qwen/qwen3-4b-fp8novita-ai/qwen/qwen3-8b-fp8novita-ai/qwen/qwen3-coder-30b-a3b-instructnovita-ai/qwen/qwen3-coder-480b-a35b-instructnovita-ai/qwen/qwen3-coder-nextnovita-ai/qwen/qwen3-maxnovita-ai/qwen/qwen3-next-80b-a3b-instructnovita-ai/qwen/qwen3-next-80b-a3b-thinkingnovita-ai/qwen/qwen3-omni-30b-a3b-instructnovita-ai/qwen/qwen3-vl-235b-a22b-instructnovita-ai/qwen/qwen3-vl-235b-a22b-thinkingnovita-ai/qwen/qwen3-vl-30b-a3b-thinkingnovita-ai/qwen/qwen3-vl-8b-instructnovita-ai/sao10K/L3-8B-stheno-v3.2novita-ai/sao10K/l3-70b-euryale-v2.1novita-ai/sao10K/l3-8b-lunarisnovita-ai/sao10K/l31-70b-euryale-v2.2novita-ai/xiaomimimo/mimo-v2-flashnovita-ai/xiaomimimo/mimo-v2-pronovita-ai/zai-org/glm-4.5openrouter/baidu/ernie-4.5-vl-424b-a47bopenrouter/inclusionai/ling-3.0-flash-sante:freeopenrouter/qwen/qwen-plus-2025-07-28openrouter/qwen/qwen3-235b-a22bopenrouter/qwen/qwen3-30b-a3b-thinking-2507openrouter/qwen/qwen3-8bopenrouter/qwen/qwen3-coder-plusopenrouter/qwen/qwen3-maxopenrouter/qwen/qwen3-max-thinkingopenrouter/qwen/qwen3-vl-235b-a22b-thinkingopenrouter/qwen/qwen3-vl-32b-instructopenrouter/qwen/qwen3-vl-8b-thinkingopenrouter/qwen/qwen3.6-max-previewovhcloud/qwen3-coder-30b-a3b-instructtinfoil/glm-5-3-flashv0/v0-1.0-mdv0/v0-1.5-lgv0/v0-1.5-mdvercel/alibaba/qwen-3.6-max-previewvercel/alibaba/qwen3-235b-a22b-thinkingvercel/alibaba/qwen3-coder-plusvercel/alibaba/qwen3-maxvercel/alibaba/qwen3-max-previewvercel/alibaba/qwen3-vl-235b-a22b-instructvercel/alibaba/qwen3-vl-thinkingvercel/deepseek/deepseek-v4.1-flash-fastvercel/moonshotai/kimi-k2-thinkingvercel/stepfun/step-3.5-flashChanged (264)
amazon-bedrock/anthropic.claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}amazon-bedrock/eu.anthropic.claude-sonnet-5-5{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75}→{"input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75}amazon-bedrock/global.anthropic.claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}amazon-bedrock/us.anthropic.claude-sonnet-5-5{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75}→{"input":2.2,"output":11,"cache_read":0.11,"cache_write":2.75}ambient/qwen/qwen3.6-27b{"input":["text","image"],"output":["text"]}→{"input":["text"],"output":["text"]}true→nullanthropic/claude-sonnet-4-5{"context":1000000,"output":64000}→{"context":200000,"output":64000}anthropic/claude-sonnet-4-5-20250929{"context":1000000,"output":64000}→{"context":200000,"output":64000}anthropic/claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast"deepseek-ai/DeepSeek-V4.1-Flash-Fast"→"DeepSeek V4.1 Flash Fast"cloudflare-workers-ai/?cf/mistralai/mistral-small-3.1-24b-instruct{"input":["text"],"output":["text"]}→{"input":["text","image"],"output":["text"]}null→truecoralbricks/deepseek-v4.1-flash-fast{"input":0.3,"output":1.2,"cache_write":0.09}→{"input":0.01,"output":1.2,"cache_write":0.09}coralbricks/deepseek-v4.1-flash-fast-fp4{"input":0.3,"output":1.2,"cache_write":0.09}→{"input":0.01,"output":1.2,"cache_write":0.09}cortecs/qwen3-coder-30b-a3b-instruct{"input":0.067,"output":0.245,"cache_read":0.014}→{"input":0.179,"output":0.697,"cache_read":0.014}crossmodel/anthropic/claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}digitalocean/minimax-m2.5{"input":["text","image"],"output":["text"]}→{"input":["text"],"output":["text"]}true→nulledenai/amazon/mistral.voxtral-mini-3b-2507{"context":128000,"output":32768}→{"context":32768,"output":32768}edenai/amazon/mistral.voxtral-mini-3b-2507?us{"context":128000,"output":32768}→{"context":32768,"output":32768}edenai/amazon/mistral.voxtral-small-24b-2507{"context":128000,"output":32768}→{"context":32768,"output":32768}edenai/amazon/mistral.voxtral-small-24b-2507?us{"context":128000,"output":32768}→{"context":32768,"output":32768}edenai/flexai/DeepSeek-V4-Flash-0731{"input":0.06,"output":0.18,"cache_read":0.009}→{"input":0.0192,"output":0.27,"cache_read":0.0029}edenai/flexai/DeepSeek-V4.1-Flash{"input":0.14,"output":0.42,"cache_read":0.021}→{"input":0.09,"output":0.18,"cache_read":0.0135}edenai/infomaniak/mistralai/Ministral-3-14B-Instruct-2512{"input":0.33531,"output":0.44708}→{"input":0.33618,"output":0.44824}edenai/ionos/meta-llama/Llama-3.3-70B-Instruct{"input":0.726505,"output":0.726505}→{"input":0.72839,"output":0.72839}edenai/ionos/openai/gpt-oss-120b{"input":0.167655,"output":0.726505}→{"input":0.16809,"output":0.72839}edenai/scaleway/deepseek-v4-flash-0731{"input":0.44708,"output":0.89416,"cache_read":0.089416}→{"input":0.44824,"output":0.89648,"cache_read":0.089648}edenai/scaleway/gpt-oss-120b{"input":0.167655,"output":0.67062}→{"input":0.16809,"output":0.67236}edenai/scaleway/llama-3.3-70b-instruct{"input":1.005931,"output":1.005931}→{"input":1.00854,"output":1.00854}google-vertex/claude-opus-4-6?default{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,→{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}google-vertex/claude-opus-4-7?default{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,→{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}google-vertex/claude-opus-4-8?default{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,→{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}google-vertex/claude-sonnet-4-6?default{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"→{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75}google-vertex/claude-sonnet-5-5?default{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}google-vertex/deepseek-ai/deepseek-v3.1-maas{"input":["text","pdf"],"output":["text"]}→{"input":["text"],"output":["text"]}google-vertex/deepseek-ai/deepseek-v3.2-maas{"input":["text","pdf"],"output":["text"]}→{"input":["text"],"output":["text"]}google-vertex/gemini-2.5-flash-image{"input":["text","image"],"output":["text","image"]}→{"input":["text","image","pdf"],"output":["text","image"]}google-vertex/gemini-2.5-flash-lite{"context":1048576,"output":65535}→{"context":1048576,"output":65536}google-vertex/gemini-3-pro-image{"input":["text","image"],"output":["text","image"]}→{"input":["text","image","pdf"],"output":["text","image"]}google-vertex/qwen/qwen3-235b-a22b-instruct-2507-maastrue→nullgoogle-vertex/zai-org/glm-4.7-maas{"input":["text","pdf"],"output":["text"]}→{"input":["text"],"output":["text"]}kilo/anthropic/claude-haiku-5.5true→nullkilo/anthropic/claude-opus-4.8true→nullkilo/anthropic/claude-opus-5true→nullkilo/anthropic/claude-opus-5.5true→nullkilo/anthropic/claude-sonnet-5.5true→nullkilo/bytedance-seed/seed-1.6"ByteDance Seed: Seed 1.6"→"ByteDance Seed: Seed 1.6 (retires Nov 11)"kilo/bytedance-seed/seed-1.6-flash"ByteDance Seed: Seed 1.6 Flash"→"ByteDance Seed: Seed 1.6 Flash (retires Nov 11)"kilo/deepseek/deepseek-chat{"input":0.2574,"output":1.0287}→{"input":0.32,"output":0.89}{"context":128000,"output":16000}→{"context":163840,"output":16384}kilo/deepseek/deepseek-r1-0528"DeepSeek: R1 0528"→"DeepSeek R1 0528""deepseek"→"deepseek-thinking"null→truekilo/deepseek/deepseek-v3.2{"input":0.259,"output":0.42,"cache_read":0.135}→{"input":0.259,"output":0.8,"cache_read":0.14}kilo/deepseek/deepseek-v4-flash{"input":0.14,"output":0.28,"cache_read":0.028}→{"input":0.0173,"output":1.28,"cache_read":0.0173}kilo/deepseek/deepseek-v4-flash-vision-exp{"input":0.44,"output":1.32,"cache_read":0.028}→{"input":0.2156,"output":0.6468,"cache_read":0.00686}kilo/google/gemini-nano-banana-2.1"Google: Nano Banana 2.1"→"Nano Banana 2.1""nano-banana"→"gemini-flash"{"input":["image","text","pdf"],"output":["image","text"]}→{"input":["image","text","pdf"],"output":["text","image"]}kilo/google/gemma-4-26b-a4b-it{"context":262144,"output":235929}→{"context":131072,"output":32768}kilo/inclusionai/ling-3.1-flash"inclusionAI: Ling 3.1 Flash (new)"→"inclusionAI: Ling 3.1 Flash"kilo/meta-llama/llama-3.2-1b-instruct"Meta: Llama 3.2 1B Instruct"→"Llama 3.2 1B Instruct"null→truekilo/meta/muse-glimmer-30b{"input":0.3,"output":1.1,"cache_read":0.04}→{"input":0.3,"output":1.2,"cache_read":0.04}kilo/mistralai/mistral-large-4-0"Mistral: Mistral Large 4"→"Mistral: Mistral Large 4 (50% off)"{"input":1.36,"output":4.18,"cache_read":0.14}→{"input":0.68,"output":2.09,"cache_read":0.07}{"context":524288,"output":262144}→{"context":1048576,"output":262144}kilo/moonshotai/kimi-k2-0905"MoonshotAI: Kimi K2 0905"→"Kimi K2 Instruct 0905""2025-09-04"→"2025-09-05"null→truekilo/moonshotai/kimi-k2-thinking{"input":0.6,"output":2.5}→{"input":0.6,"output":2.5,"cache_read":0.15}{"context":262144,"output":235929}→{"context":262144,"output":98304}kilo/moonshotai/kimi-k2.6{"input":0.465,"output":2.45,"cache_read":0.0975}→{"input":0.65,"output":3.41,"cache_read":0.15}kilo/nvidia/nemotron-3-nano-30b-a3b{"context":262144,"output":32768}→{"context":262144,"output":235929}kilo/nvidia/nemotron-3-ultra-550b-a55b{"context":262144,"output":16384}→{"context":202800,"output":182520}kilo/nvidia/nemotron-3.5-lightning{"input":0.039,"output":0.18,"cache_read":0.0195}→{"input":0.025,"output":0.12,"cache_read":0.0125}{"context":262144,"output":131072}→{"context":262144,"output":235929}kilo/openai/gpt-oss-120b{"input":0.03,"output":0.17,"cache_read":0.03}→{"input":0.03,"output":0.15,"cache_read":0.03}kilo/qwen/qwen3-14b{"input":0.2275,"output":0.91}→{"input":0.12,"output":0.24}kilo/qwen/qwen3-235b-a22b-2507{"input":0.1495,"output":0.598}→{"input":0.09,"output":0.55}kilo/qwen/qwen3-235b-a22b-thinking-2507"Qwen: Qwen3 235B A22B Thinking 2507 (retires Oct 9)"→"Qwen: Qwen3 235B A22B Thinking 2507"{"input":0.23,"output":2.3}→{"input":0.45,"output":3.5}{"context":131072,"output":117964}→{"context":128000,"output":16384}kilo/qwen/qwen3-30b-a3b{"input":0.13,"output":0.52}→{"input":0.12,"output":0.5}kilo/qwen/qwen3-30b-a3b-instruct-2507{"input":0.13,"output":0.52}→{"input":0.1,"output":0.3}{"context":128000,"output":32000}→{"context":262144,"output":235929}kilo/qwen/qwen3-coder{"input":0.975,"output":4.875}→{"input":0.3,"output":1,"cache_read":0.1}kilo/qwen/qwen3-coder-30b-a3b-instruct{"input":0.2925,"output":1.4625}→{"input":0.07,"output":0.28}kilo/qwen/qwen3-coder-next{"input":0.3,"output":1.5}→{"input":0.12,"output":0.8,"cache_read":0.07}kilo/qwen/qwen3-next-80b-a3b-instruct{"input":0.0975,"output":0.78}→{"input":0.1,"output":1.1,"cache_read":0.07}kilo/qwen/qwen3-next-80b-a3b-thinking{"context":131072,"output":32768}→{"context":262144,"output":235929}kilo/qwen/qwen3-vl-235b-a22b-instruct{"input":0.26,"output":1.04}→{"input":0.21,"output":1.9,"cache_read":0.1}kilo/qwen/qwen3-vl-30b-a3b-instruct"Qwen: Qwen3 VL 30B A3B Instruct"→"Qwen3 VL 30B A3B Instruct"{"input":0.13,"output":0.52}→{"input":0.15,"output":0.6}"2025-10-06"→"2025-10-04"null→truekilo/qwen/qwen3-vl-30b-a3b-thinking"Qwen: Qwen3 VL 30B A3B Thinking (retires Oct 9)"→"Qwen: Qwen3 VL 30B A3B Thinking"{"input":0.2,"output":2.4}→{"input":0.29,"output":1}{"context":131072,"output":32768}→{"context":262144,"output":235929}kilo/qwen/qwen3-vl-8b-instruct"Qwen: Qwen3 VL 8B Instruct (retires Oct 9)"→"Qwen: Qwen3 VL 8B Instruct"{"input":0.117,"output":0.455}→{"input":0.25,"output":0.75,"cache_read":0.12}{"context":131072,"output":32768}→{"context":262144,"output":235929}kilo/qwen/qwen3.5-27b{"context":262144,"output":65536}→{"context":262144,"output":81920}kilo/qwen/qwen3.5-35b-a3b{"context":262144,"output":235929}→{"context":262144,"output":32768}kilo/qwen/qwen3.5-397b-a17b{"context":262144,"output":81920}→{"context":262144,"output":235929}kilo/qwen/qwen3.6-27b{"context":262144,"output":65536}→{"context":262144,"output":81920}kilo/qwen/qwen3.6-35b-a3b{"input":0.15,"output":1,"cache_read":0.05}→{"input":0.1,"output":0.95,"cache_read":0.1}{"context":262144,"output":235929}→{"context":262144,"output":65536}kilo/qwen/qwen3.8-27b{"context":1000000,"output":131072}→{"context":262144,"output":235929}kilo/sao10k/l3.1-euryale-70btrue→nullkilo/tencent/hy3{"input":0.0825,"output":0.33,"cache_read":0.020625}→{"input":0.132,"output":0.528,"cache_read":0.033}kilo/tencent/hy4-preview{"input":0.7506,"output":2.2509,"cache_read":0.0378}→{"input":0.834,"output":2.501,"cache_read":0.042}kilo/z-ai/glm-4.6{"input":0.43,"output":1.75,"cache_read":0.08}→{"input":0.5,"output":2,"cache_read":0.1}{"context":198000,"output":16384}→{"context":202752,"output":131072}kilo/z-ai/glm-5.2{"context":1048576,"output":131072}→{"context":1048576,"output":943718}kilo/?anthropic/claude-haiku-latesttrue→nullkilo/?anthropic/claude-opus-latesttrue→nullkilo/?anthropic/claude-sonnet-latesttrue→nullkilo/?deepseek/deepseek-flash-latest{"input":0.0248,"output":1.2,"cache_read":0.02}→{"input":0.0336,"output":1.188,"cache_read":0.0336}kilo/?deepseek/deepseek-pro-latest{"input":0.2862,"output":4.2,"cache_read":0.2}→{"input":0.25,"output":5,"cache_read":0.2}{"context":1048576,"output":393216}→{"context":1048576,"output":943718}kilo/?deepseek/deepseek-v4-flash-latest{"input":0.018,"output":1.28,"cache_read":0.018}→{"input":0.0128,"output":0.768,"cache_read":0.0128}kilo/?moonshotai/kimi-latest{"input":0.49,"output":13,"cache_read":0.45}→{"input":0.45,"output":18,"cache_read":0.3}kilo/?z-ai/glm-flash-latest{"input":0.04,"output":0.5,"cache_read":0.025}→{"input":0.032,"output":1.2,"cache_read":0.032}{"context":1048576,"output":131072}→{"context":1048576,"output":943718}kilo/?z-ai/glm-latest{"input":0.062,"output":3.39,"cache_read":0.06}→{"input":0.079,"output":4.8,"cache_read":0.059}llmgateway/claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}llmgateway/mimo-v2.5{"input":0.14,"output":0.28,"cache_read":0.0028,"tiers":[{"input":0.8,"output":4→{"input":0.168,"output":0.336,"cache_read":0.0034,"tiers":[{"input":0.8,"output"llmgateway-providers/anthropic/claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}llmgateway-providers/aws-bedrock/claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}llmgateway-providers/azure-anthropic/claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}llmgateway-providers/deepinfra/qwen3.5-9b{"input":["text"],"output":["text"]}→{"input":["text","image","video"],"output":["text"]}null→truellmgateway-providers/vertex-anthropic/claude-haiku-4-5{"input":1,"output":5,"cache_read":0.1}→{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25}llmgateway-providers/vertex-anthropic/claude-opus-4-5-20251101{"input":5,"output":25,"cache_read":0.5}→{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}llmgateway-providers/vertex-anthropic/claude-opus-4-6{"input":5,"output":25,"cache_read":0.5}→{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}llmgateway-providers/vertex-anthropic/claude-opus-4-7{"input":5,"output":25,"cache_read":0.5}→{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25}llmgateway-providers/vertex-anthropic/claude-sonnet-4-5{"input":3,"output":15,"cache_read":0.3}→{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75}llmgateway-providers/vertex-anthropic/claude-sonnet-4-6{"input":3,"output":15,"cache_read":0.3}→{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75}merge-gateway/anthropic/claude-haiku-5-5{"input":["text"],"output":["text"]}→{"input":["text","image","pdf"],"output":["text"]}null→truenull→truemerge-gateway/anthropic/claude-sonnet-5-5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}merge-gateway/openai/gpt-5.6-sol{"input":4,"output":20,"cache_read":0.4,"cache_write":5}→{"input":5,"output":30,"cache_read":0.5,"cache_write":5}mistral/mistral-large-4{"context":524288,"output":262144}→{"context":1048576,"output":262144}moark/GLM-4.7{"input":3.5,"output":14}→{"input":0.42,"output":2.2}moark/MiniMax-M2.1{"input":2.1,"output":8.4,"cache_read":2.1,"cache_write":8.4}→{"input":0.29,"output":1.2}nano-gpt/Gryphe/MythoMax-L2-13b"llama"→null"2025-08-08"→"2023-08-10"null→truenano-gpt/anthropic/claude-haiku-latest{"input":1,"output":5,"cache_read":0.1}→{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125}{"context":200000,"output":64000}→{"context":1000000,"output":128000}nano-gpt/anthropic/claude-sonnet-5.5{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}nano-gpt/anthropic/claude-sonnet-5.5:thinking{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}nano-gpt/anthropic/claude-sonnet-latest{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5}→{"input":2,"output":10,"cache_read":0.1,"cache_write":2.5}nano-gpt/claw-high{"input":1,"output":3.2,"cache_read":0.2}→{"input":0.6,"output":1.1,"cache_read":0.2}nano-gpt/claw-low{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0.08333}→{"input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0.08333}nano-gpt/claw-medium{"input":1,"output":3.2,"cache_read":0.2}→{"input":0.6,"output":1.1,"cache_read":0.2}nano-gpt/deepseek/deepseek-v4-flash-0731{"context":1000000,"output":131072}→{"context":1048576,"output":131072}nano-gpt/deepseek/deepseek-v4-flash-0731:thinking{"context":1000000,"output":131072}→{"context":1048576,"output":131072}nano-gpt/hermes-high{"input":1,"output":3.2,"cache_read":0.2}→{"input":0.6,"output":1.1,"cache_read":0.2}nano-gpt/hermes-low{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0.08333}→{"input":0.6,"output":1.1,"cache_read":0.2,"cache_write":0.08333}nano-gpt/hermes-medium{"input":1,"output":3.2,"cache_read":0.2}→{"input":0.6,"output":1.1,"cache_read":0.2}nano-gpt/inclusionai/ling-3.0-flashnull→truenull→truenano-gpt/inclusionai/ling-3.0-flash-vl"2026-09-09"→"2026-09-10"null→truenano-gpt/inclusionai/ling-3.0-flash:thinkingnull→truenull→truenano-gpt/microsoft/wizardlm-2-8x22b"gpt"→null"2025-04-15"→"2024-04-15"null→truenano-gpt/moonshotai/kimi-k2-instruct"2024-01-01"→"2025-07-11"null→truenano-gpt/moonshotai/kimi-k2.5{"context":256000,"output":65536}→{"context":262144,"output":65536}nano-gpt/moonshotai/kimi-k2.5:thinking{"context":256000,"output":65536}→{"context":262144,"output":65536}nano-gpt/moonshotai/kimi-k2.6{"context":256000,"output":65536}→{"context":262144,"output":65536}nano-gpt/moonshotai/kimi-k2.6:thinking{"context":256000,"output":65536}→{"context":262144,"output":65536}nano-gpt/openai/gpt-oss-20b{"context":128000,"output":16384}→{"context":131072,"output":16384}nano-gpt/qwen/qwen3-coder-next{"input":0.2,"output":1.5,"cache_read":0.1}→{"input":0.250251,"output":0.80293,"cache_read":0.079764}nano-gpt/qwen/qwen3.5-122b-a10b{"context":131072,"output":32768}→{"context":262144,"output":32768}nano-gpt/qwen/qwen3.5-122b-a10b:thinking{"context":131072,"output":32768}→{"context":262144,"output":32768}nano-gpt/qwen/qwen3.5-397b-a17b{"context":258048,"output":65536}→{"context":262144,"output":65536}nano-gpt/qwen/qwen3.5-397b-a17b:thinking{"context":258048,"output":65536}→{"context":262144,"output":65536}nano-gpt/qwen/qwen3.5-9b{"context":256000,"output":65536}→{"context":262144,"output":65536}nano-gpt/qwen/qwen3.6-27b{"context":260096,"output":65536}→{"context":262144,"output":65536}nano-gpt/qwen/qwen3.6-27b:thinking{"context":260096,"output":65536}→{"context":262144,"output":65536}nano-gpt/qwen/qwen3.8-27b{"context":262144,"output":32768}→{"context":1001536,"output":32768}nano-gpt/qwen/qwen3.8-27b-uncensored{"input":0.15,"output":1.2,"cache_read":0.125}→{"input":0.75,"output":2.5,"cache_read":0.125}{"context":524288,"output":32768}→{"context":1010000,"output":32768}nano-gpt/qwen/qwen3.8-27b-uncensored:thinking{"input":0.15,"output":1.2,"cache_read":0.125}→{"input":0.75,"output":2.5,"cache_read":0.125}{"context":524288,"output":32768}→{"context":1010000,"output":32768}nano-gpt/qwen/qwen3.8-27b:thinking{"context":262144,"output":32768}→{"context":1001536,"output":32768}nano-gpt/z-ai/glm-5.3{"input":1,"output":3.2,"cache_read":0.2}→{"input":0.6,"output":1.1,"cache_read":0.2}nano-gpt/z-ai/glm-5.3:thinking{"input":1,"output":3.2,"cache_read":0.2}→{"input":0.6,"output":1.1,"cache_read":0.2}nano-gpt/z-ai/glm-latest{"input":1,"output":3.2,"cache_read":0.2}→{"input":0.6,"output":1.1,"cache_read":0.2}nearai/Qwen/Qwen3-VL-30B-A3B-Instruct{"input":0.15,"output":0.55}→{"input":0.15,"output":0.55,"cache_read":0.03}novita-ai/baichuan/baichuan-m2-32b"baichuan-m2-32b"→"Baichuan M2 32B"null→truenovita-ai/deepseek/deepseek-ocr-2"deepseek/deepseek-ocr-2"→"DeepSeek OCR 2"novita-ai/deepseek/deepseek-r1-0528-qwen3-8bnull→"deepseek-thinking"novita-ai/deepseek/deepseek-r1-turbo"DeepSeek R1 (Turbo)\t"→"DeepSeek R1 (Turbo)""2025-03-05"→"2025-01-20"null→"deepseek-thinking"novita-ai/google/gemma-3-12b-it"Gemma 3 12B"→"Gemma 3 12B IT""2025-03-13"→"2025-03-12"null→truenovita-ai/google/gemma-3-27b-it"Gemma 3 27B"→"Gemma 3 27B IT""2025-03-25"→"2025-03-12"null→truenovita-ai/google/gemma-4-26b-a4b-it"Gemma 4 26B A4B"→"Gemma 4 26B A4B IT"novita-ai/google/gemma-4-31b-it"Gemma 4 31B"→"Gemma 4 31B IT"novita-ai/gryphe/mythomax-l2-13b"Mythomax L2 13B"→"MythoMax L2 13B""2024-04-25"→"2023-08-10"novita-ai/meta-llama/llama-3.1-8b-instruct"Llama 3.1 8B Instruct"→"Llama-3.1-8B-Instruct""2024-07-24"→"2024-07-23"null→truenovita-ai/meta-llama/llama-3.3-70b-instruct"Llama 3.3 70B Instruct"→"Llama-3.3-70B-Instruct"{"context":131072,"output":120000}→{"context":12288,"output":12288}"2024-12-07"→"2024-12-06"novita-ai/meta-llama/llama-4-maverick-17b-128e-instruct-fp8"Llama 4 Maverick Instruct"→"Llama 4 Maverick 17B Instruct""2025-04-06"→"2025-04-05"null→"llama"null→truenovita-ai/meta-llama/llama-4-scout-17b-16e-instruct"Llama 4 Scout Instruct"→"Llama 4 Scout 17B Instruct""2025-04-06"→"2025-04-05"null→"llama"null→truenovita-ai/microsoft/wizardlm-2-8x22b"Wizardlm 2 8x22B"→"WizardLM 2 8x22B""2024-04-24"→"2024-04-15"novita-ai/minimax/minimax-m2.5"MiniMax M2.5"→"MiniMax-M2.5"{"context":204800,"output":131072}→{"context":204800,"output":131100}null→truenovita-ai/minimax/minimax-m2.7"MiniMax M2.7"→"MiniMax-M2.7""minimax-m2.7"(delta truncated at 60 kB)
Generated by
task update-models.