chore(pricing): refresh models.dev snapshot - #535
Open
github-actions[bot] wants to merge 1 commit into
Open
Conversation
This was referenced Aug 18, 2026
github-actions
Bot
force-pushed
the
automation/models-dev-pricing
branch
from
August 18, 2026 04:36
005a37a to
e91d118
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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: 179 → 191. Models: 6047 → 6728.
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 (4)
google-vertex/gemini-3.7-flashgoogle/gemini-3.7-flashxai/grok-4.6xai/grok-imagine-image-2.0Other models added (1058)
abacus/claude-opus-5abacus/gemini-3-pro-imageabacus/gemini-3.1-flash-imageabacus/gemini-3.5-flash-liteabacus/gemini-3.6-flashabacus/gemini-3.7-flashabacus/grok-4.6abacus/moonshotai/Kimi-K2.7-Codeabacus/moonshotai/Kimi-K3abacus/muse-spark-1.2abacus/qwen3.7-maxabacus/qwen3.8-maxabacus/thinkingmachines/Inklingaiand/motif-technologies/motif-3aihubmix/claude-opus-5aihubmix/gemini-3.7-flashaihubmix/qwen3.8-maxalibaba-cn/qwen3.8-maxalibaba-token-plan-cn/deepseek-v4-flash-0731alibaba-token-plan-cn/deepseek-v4-pro-0813alibaba-token-plan-cn/qwen3.8-maxalibaba-token-plan/deepseek-v4-flash-0731alibaba-token-plan/deepseek-v4-pro-0813alibaba-token-plan/qwen3.8-maxalibaba/deepseek-v4-flash-0731alibaba/glm-5.2alibaba/qwen3.8-maxamazon-bedrock/global.openai.gpt-5.6-lunaamazon-bedrock/global.openai.gpt-5.6-solamazon-bedrock/global.openai.gpt-5.6-terraambient/deepseek/deepseek-v4-flash-0731amd/DeepSeek-V4-Flasharcee/deepseek/deepseek-v4-flash-latestarcee/deepseek/deepseek-v4-proarcee/deepseek/deepseek-v4-pro-0813arcee/moonshotai/kimi-k3arcee/thinkingmachines/inkling-smallarcee/trinity-large-thinkingarcee/zai-org/glm-5.2azure-cognitive-services/claude-fable-5azure-cognitive-services/claude-mythos-5azure-cognitive-services/claude-sonnet-4-6azure-cognitive-services/claude-sonnet-5azure/claude-mythos-5azure/kimi-k2.7-codebaseten/deepseek-ai/DeepSeek-V4-Pro-0813chutes/Qwen/Qwen3.8-27B-TEEcloudflare-ai-gateway/anthropic/claude-haiku-4.5cloudflare-ai-gateway/anthropic/claude-opus-4.5cloudflare-ai-gateway/anthropic/claude-opus-4.6cloudflare-ai-gateway/anthropic/claude-opus-4.7cloudflare-ai-gateway/anthropic/claude-opus-4.8cloudflare-ai-gateway/anthropic/claude-sonnet-4.5cloudflare-ai-gateway/anthropic/claude-sonnet-4.6cloudflare-ai-gateway/openai/gpt-4.1cloudflare-ai-gateway/openai/gpt-4.1-minicloudflare-ai-gateway/openai/gpt-4.1-nanocloudflare-ai-gateway/openai/gpt-5cloudflare-ai-gateway/openai/gpt-5-minicloudflare-ai-gateway/openai/gpt-5-nanocloudflare-ai-gateway/openai/gpt-5-procloudflare-ai-gateway/openai/gpt-5.2-chat-latestcloudflare-ai-gateway/openai/gpt-5.2-procloudflare-ai-gateway/openai/gpt-5.3-chat-latestcloudflare-ai-gateway/openai/gpt-5.3-codex-sparkcloudflare-ai-gateway/openai/gpt-5.4-minicloudflare-ai-gateway/openai/gpt-5.4-nanocloudflare-ai-gateway/openai/gpt-5.4-procloudflare-ai-gateway/openai/gpt-5.5-procloudflare-ai-gateway/openai/gpt-5.6cloudflare-ai-gateway/openai/o1-procloudflare-ai-gateway/workers-ai/@cf/google/gemma-4-26b-a4b-itcloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.7-codecloudflare-workers-ai/@cf/deepseek-ai/deepseek-v4-flash-0731cloudflare-workers-ai/@cf/deepseek-ai/deepseek-v4-pro-0813cloudflare-workers-ai/@cf/qwen/qwen3.8-27bcoralbricks/glm-5.2-fp4coralbricks/gpt-oss-120bcoralbricks/kimi-k3cortecs/apertus-70bcortecs/claude-opus-5cortecs/claude-sonnet-5cortecs/cosmos3-super-reasonercortecs/deepseek-v4-flash-0731cortecs/gemini-2.5-flashcortecs/gemini-3.1-flash-litecortecs/gemini-3.5-flashcortecs/gemini-3.5-flash-litecortecs/gemini-3.6-flashcortecs/gemini-3.7-flashcortecs/gemma-3-27b-itcortecs/gemma-4-26b-a4b-itcortecs/gemma-4-31b-itcortecs/gpt-4.1-minicortecs/gpt-4.1-nanocortecs/gpt-4ocortecs/gpt-4o-minicortecs/gpt-5cortecs/gpt-5-minicortecs/gpt-5-nanoPrimary-provider models removed (5)
anthropic/claude-opus-4-1anthropic/claude-opus-4-1-20250805google/gemini-2.0-flashgoogle/gemini-2.0-flash-litegoogle/gemini-3-pro-previewOther models removed (376)
cerebras/zai-glm-4.7cloudflare-ai-gateway/anthropic/claude-3-5-haikucloudflare-ai-gateway/anthropic/claude-3-haikucloudflare-ai-gateway/anthropic/claude-3-opuscloudflare-ai-gateway/anthropic/claude-3-sonnetcloudflare-ai-gateway/anthropic/claude-3.5-haikucloudflare-ai-gateway/anthropic/claude-3.5-sonnetcloudflare-ai-gateway/anthropic/claude-haiku-4-5cloudflare-ai-gateway/anthropic/claude-opus-4cloudflare-ai-gateway/anthropic/claude-opus-4-1cloudflare-ai-gateway/anthropic/claude-opus-4-5cloudflare-ai-gateway/anthropic/claude-opus-4-6cloudflare-ai-gateway/anthropic/claude-opus-4-7cloudflare-ai-gateway/anthropic/claude-opus-4-8cloudflare-ai-gateway/anthropic/claude-sonnet-4cloudflare-ai-gateway/anthropic/claude-sonnet-4-5cloudflare-ai-gateway/anthropic/claude-sonnet-4-6cloudflare-ai-gateway/moonshotai/kimi-k3cloudflare-ai-gateway/openai/gpt-5.1-codexcloudflare-ai-gateway/openai/gpt-5.2-codexcloudflare-ai-gateway/workers-ai/@cf/ai4bharat/indictrans2-en-indic-1Bcloudflare-ai-gateway/workers-ai/@cf/baai/bge-base-en-v1.5cloudflare-ai-gateway/workers-ai/@cf/baai/bge-large-en-v1.5cloudflare-ai-gateway/workers-ai/@cf/baai/bge-m3cloudflare-ai-gateway/workers-ai/@cf/baai/bge-reranker-basecloudflare-ai-gateway/workers-ai/@cf/baai/bge-small-en-v1.5cloudflare-ai-gateway/workers-ai/@cf/deepgram/aura-2-encloudflare-ai-gateway/workers-ai/@cf/deepgram/aura-2-escloudflare-ai-gateway/workers-ai/@cf/deepgram/nova-3cloudflare-ai-gateway/workers-ai/@cf/facebook/bart-large-cnncloudflare-ai-gateway/workers-ai/@cf/google/gemma-3-12b-itcloudflare-ai-gateway/workers-ai/@cf/huggingface/distilbert-sst-2-int8cloudflare-ai-gateway/workers-ai/@cf/meta/llama-2-7b-chat-fp16cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3-8b-instructcloudflare-ai-gateway/workers-ai/@cf/meta/llama-3-8b-instruct-awqcloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instructcloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-awqcloudflare-ai-gateway/workers-ai/@cf/meta/m2m100-1.2bcloudflare-ai-gateway/workers-ai/@cf/mistral/mistral-7b-instruct-v0.1cloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.5cloudflare-ai-gateway/workers-ai/@cf/myshell-ai/melottscloudflare-ai-gateway/workers-ai/@cf/pfnet/plamo-embedding-1bcloudflare-ai-gateway/workers-ai/@cf/pipecat-ai/smart-turn-v2cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-embedding-0.6bcortecs/deepseek-v3-0324cortecs/deepseek-v4-flashcortecs/glm-4.5cortecs/glm-4.5-aircortecs/hy3cortecs/intellect-3cortecs/kimi-k2-instructcortecs/kimi-k2-thinkingcortecs/llama-4-maverickcortecs/nemotron-3-super-120b-a12bcortecs/qwen-2.5-72b-instructcortecs/qwen3-coder-480b-a35b-instructcrossmodel/tencent/hy3-previewevroc/Qwen/Qwen3-VL-30B-A3B-Instructfriendli/Qwen/Qwen3-235B-A22B-Instruct-2507github-copilot/gemini-2.5-progithub-copilot/gemini-3-flash-previewgithub-models/ai21-labs/ai21-jamba-1.5-largegithub-models/ai21-labs/ai21-jamba-1.5-minigithub-models/cohere/cohere-command-agithub-models/cohere/cohere-command-rgithub-models/cohere/cohere-command-r-08-2024github-models/cohere/cohere-command-r-plusgithub-models/cohere/cohere-command-r-plus-08-2024github-models/core42/jais-30b-chatgithub-models/deepseek/deepseek-r1github-models/deepseek/deepseek-r1-0528github-models/deepseek/deepseek-v3-0324github-models/meta/llama-3.2-11b-vision-instructgithub-models/meta/llama-3.2-90b-vision-instructgithub-models/meta/llama-3.3-70b-instructgithub-models/meta/llama-4-maverick-17b-128e-instruct-fp8github-models/meta/llama-4-scout-17b-16e-instructgithub-models/meta/meta-llama-3-70b-instructgithub-models/meta/meta-llama-3-8b-instructgithub-models/meta/meta-llama-3.1-405b-instructgithub-models/meta/meta-llama-3.1-70b-instructgithub-models/meta/meta-llama-3.1-8b-instructgithub-models/microsoft/mai-ds-r1github-models/microsoft/phi-3-medium-128k-instructgithub-models/microsoft/phi-3-medium-4k-instructgithub-models/microsoft/phi-3-mini-128k-instructgithub-models/microsoft/phi-3-mini-4k-instructgithub-models/microsoft/phi-3-small-128k-instructgithub-models/microsoft/phi-3-small-8k-instructgithub-models/microsoft/phi-3.5-mini-instructgithub-models/microsoft/phi-3.5-moe-instructgithub-models/microsoft/phi-3.5-vision-instructgithub-models/microsoft/phi-4github-models/microsoft/phi-4-mini-instructgithub-models/microsoft/phi-4-mini-reasoninggithub-models/microsoft/phi-4-multimodal-instructgithub-models/microsoft/phi-4-reasoninggithub-models/mistral-ai/codestral-2501github-models/mistral-ai/ministral-3bgithub-models/mistral-ai/mistral-large-2411Primary-provider price fields changed (0)
None.
Other price fields changed (789)
aiand/qwen/qwen3.6-27b— input:0→0.32; output:0→3.2amazon-bedrock/openai.gpt-5.6-luna— context_over_200k:missing→{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55}; tiers:missing→[{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55,"tier":{"type":"context","size":272000}}]amazon-bedrock/openai.gpt-5.6-sol— cache_write:6.88→6.875; context_over_200k:missing→{"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75}; tiers:missing→[{"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75,"tier":{"type":"context","size":272000}}]amazon-bedrock/openai.gpt-5.6-terra— context_over_200k:missing→{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5}; tiers:missing→[{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}]ambient/moonshotai/kimi-k2.7-code— cache_read:0.15→0.14; input:0.73→0.69; output:3.5→3.49azure/gpt-5.6-luna— cache_read:0.1→0.02; cache_write:1.25→0.25; context_over_200k:{"input":2,"output":9,"cache_read":0.2,"cache_write":2.5}→{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}; input:1→0.2; output:6→1.2; tiers:[{"input":2,"output":9,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":272000}}]→[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}]azure/gpt-5.6-sol— cache_write:missing→6.25; context_over_200k:{"input":10,"output":45,"cache_read":1}→{"input":10,"output":45,"cache_read":1,"cache_write":12.5}; tiers:[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}]→[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}]azure/gpt-5.6-terra— cache_read:0.25→0.2; cache_write:3.125→2.5; context_over_200k:{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25}→{"input":4,"output":18,"cache_read":0.4,"cache_write":5}; input:2.5→2; output:15→12; tiers:[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25,"tier":{"type":"context","size":272000}}]→[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}]chutes/Nemotron-3-Nano-Omni-30B-TEE— cache_read:0.01225→0.0024499999999999995chutes/Qwen/Qwen3-235B-A22B-Thinking-2507-TEE— cache_read:0.14945→0.029889999999999993chutes/Qwen/Qwen3-32B-TEE— cache_read:0.052→0.010399999999999998chutes/Qwen/Qwen3.5-397B-A17B-TEE— cache_read:0.225→0.04499999999999999chutes/Qwen/Qwen3.6-27B-TEE— cache_read:0.15→0.029999999999999992chutes/deepseek-ai/DeepSeek-V3.2-TEE— cache_read:0.5→0.09999999999999998chutes/deepseek-ai/DeepSeek-V4-Flash-0731-TEE— cache_read:0.07→0.013999999999999999chutes/google/gemma-4-31B-turbo-TEE— cache_read:0.06→0.011999999999999997chutes/moonshotai/Kimi-K2.6-TEE— cache_read:0.33→0.05799999999999998; input:0.66→0.58; output:3.5→3.4chutes/moonshotai/Kimi-K3-TEE— cache_read:1.5→0.29999999999999993chutes/unsloth/Mistral-Nemo-Instruct-2407-TEE— cache_read:0.01225→0.0024499999999999995chutes/zai-org/GLM-5.1-TEE— cache_read:0.49→0.09799999999999998chutes/zai-org/GLM-5.2-TEE— cache_read:0.625→0.12499999999999997cloudflare-ai-gateway/openai/gpt-3.5-turbo— cache_read:1.25→0cloudflare-ai-gateway/openai/gpt-4o— cache_read:1.25→0.625; input:2.5→1.25; output:10→5cloudflare-ai-gateway/openai/gpt-4o-mini— cache_read:0.08→0.0375; input:0.15→0.075; output:0.6→0.3cloudflare-ai-gateway/openai/gpt-5.1— cache_read:0.13→0.125cloudflare-ai-gateway/openai/gpt-5.4— context_over_200k:missing→{"input":5,"output":22.5,"cache_read":0.5}; tiers:missing→[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}]cloudflare-ai-gateway/openai/gpt-5.6-luna— cache_read:0.1→0.02; cache_write:missing→0.25; context_over_200k:{"input":2,"output":9,"cache_read":0.2}→{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}; input:1→0.2; output:6→1.2; tiers:[{"input":2,"output":9,"cache_read":0.2,"tier":{"type":"context","size":272000}}]→[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}]cloudflare-ai-gateway/openai/gpt-5.6-sol— cache_write:missing→6.25; context_over_200k:{"input":10,"output":45,"cache_read":1}→{"input":10,"output":45,"cache_read":1,"cache_write":12.5}; tiers:[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}]→[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}]cloudflare-ai-gateway/openai/gpt-5.6-terra— cache_read:0.25→0.2; cache_write:missing→2.5; context_over_200k:{"input":5,"output":22.5,"cache_read":0.5}→{"input":4,"output":18,"cache_read":0.4,"cache_write":5}; input:2.5→2; output:15→12; tiers:[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}]→[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}]cloudflare-ai-gateway/openai/o4-mini— cache_read:0.28→0.275cloudflare-ai-gateway/workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it— input:0.35→0.351; output:0.56→0.555cloudflare-ai-gateway/workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b— input:0.5→0.497; output:4.88→4.881cloudflare-ai-gateway/workers-ai/@cf/ibm-granite/granite-4.0-h-micro— output:0.11→0.112cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8— input:0.15→0.152; output:0.29→0.287cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-11b-vision-instruct— input:0.049→0.0485; output:0.68→0.676cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-1b-instruct— output:0.2→0.201cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-3b-instruct— input:0.051→0.0509; output:0.34→0.335cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast— input:0.29→0.293; output:2.25→2.253cloudflare-ai-gateway/workers-ai/@cf/meta/llama-guard-3-8b— input:0.48→0.484cloudflare-ai-gateway/workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct— input:0.35→0.351; output:0.56→0.555cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-30b-a3b-fp8— input:0.051→0.0509; output:0.34→0.335cloudflare-ai-gateway/workers-ai/@cf/zai-org/glm-4.7-flash— input:0.06→0.0605cortecs/claude-4-5-sonnet— cache_read:missing→0.326; cache_write:missing→4.078; input:3.259→2.989; output:16.296→14.945cortecs/claude-4-6-sonnet— cache_read:missing→0.32; cache_write:missing→3.999; input:3.59→3.196; output:17.92→15.94cortecs/claude-haiku-4-5— cache_read:missing→0.099; cache_write:missing→1.186; input:1.09→0.996; output:5.43→4.982cortecs/claude-opus4-5— cache_read:missing→0.531; cache_write:missing→6.645; input:5.98→5.313; output:29.89→26.568cortecs/claude-opus4-6— cache_read:missing→0.531; cache_write:missing→6.645; input:5.98→5.313; output:29.89→26.561cortecs/claude-opus4-7— cache_read:0.56→0.544; cache_write:6.99→6.797; input:5.6→5.437; output:27.99→27.186cortecs/claude-opus4-8— cache_read:0.563→0.544; cache_write:7.049→6.797; input:5.64→5.437; output:28.198→27.186cortecs/claude-sonnet-4— cache_read:missing→0.29; cache_write:missing→3.624; input:3.307→2.898; output:16.536→14.493cortecs/codestral-2508— cache_read:0.03→0.033; input:0.3→0.334; output:0.9→1.003cortecs/deepseek-r1-0528— cache_read:missing→0.163; input:0.585→0.652; output:2.307→2.57cortecs/deepseek-v3.2— cache_read:missing→0.075; input:0.266→0.296; output:0.444→0.495cortecs/deepseek-v4-pro— cache_read:0.003625→0.432; input:1.553→1.73; output:3.106→3.46cortecs/devstral-2512— cache_read:missing→0.045; input:0→0.446; output:0→2.228cortecs/gemini-2.5-pro— cache_read:missing→0.242; cache_write:missing→0.434; input:1.654→1.495; output:11.024→9.964cortecs/glm-4.7— input:0.45→0.78; output:2.23→2.785cortecs/glm-4.7-flash— input:0.09→0.08; output:0.53→0.478cortecs/glm-5— cache_read:missing→0.247; input:1.08→0.988; output:3.44→3.164cortecs/glm-5-turbo— cache_read:0.308→0.296; input:1.235→1.186; output:4.118→3.955cortecs/glm-5.1— cache_read:0.24→0.346; input:1.31→1.384; output:4.1→4.348cortecs/glm-5.2— cache_read:0.39→0.26; input:1.44→1.2; output:4.53→4.2cortecs/glm-5v-turbo— cache_read:0.308→0.296; input:1.235→1.186; output:4.118→3.955cortecs/gpt-4.1— cache_read:missing→0.546; input:2.354→2.192; output:9.417→8.769cortecs/gpt-5.4— cache_read:0.25→0.242; input:3→2.898; output:16.13→15.453cortecs/gpt-oss-120b— cache_read:missing→0.01; input:0→0.089; output:0→0.446cortecs/hermes-4-70b— input:0.116→0.129; output:0.358→0.399cortecs/kimi-k2.5— cache_read:missing→0.124; input:0.55→0.495; output:2.76→2.768cortecs/kimi-k2.6— cache_read:0.2→0.193; input:0.81→0.773; output:3.54→3.38cortecs/kimi-k2.7-code— cache_read:0.32→0.201; input:1.28→0.75; output:4.63→3.5cortecs/kimi-k3— output:15→14.999cortecs/llama-3.1-405b-instruct— input:0→1.95; output:0→1.95cortecs/llama-3.3-70b-instruct— input:0.089→0.129; output:0.275→0.399cortecs/minimax-m2— input:0.39→0.349; output:1.57→1.405cortecs/minimax-m2.1— input:0.34→0.359; output:1.34→1.435cortecs/minimax-m2.5— cache_read:missing→0.03; input:0.32→0.296; output:1.18→1.087cortecs/minimax-m2.7— input:0.47→0.668; output:1.4→2.674cortecs/minimax-m3— cache_read:0.089→0.099; input:0.355→0.395; output:1.775→1.977cortecs/mistral-large-2512— cache_read:0.05→0.056; input:0.5→0.557; output:1.5→1.671cortecs/mixtral-8x7B-instruct-v0.1— input:0.438→0.488; output:0.68→0.758cortecs/nova-pro-v1— input:1.016→0.918; output:4.061→3.671cortecs/qwen3-235b-a22b-instruct-2507— cache_read:missing→0.018; input:0.062→0.069; output:0.408→0.455cortecs/qwen3-32b— output:0.33→0.299cortecs/qwen3-coder-30b-a3b-instruct— cache_read:missing→0.014; input:0.053→0.067; output:0.222→0.245cortecs/qwen3-coder-next— input:0.158→0.167; output:0.84→0.891cortecs/qwen3-next-80b-a3b-thinking— input:0.164→0.149; output:1.311→1.195cortecs/qwen3.5-122b-a10b— cache_read:missing→0.124; input:0.444→0.495; output:3.106→3.46cortecs/qwen3.5-397b-a17b— input:0.6→0.668; output:3.6→4.01crof/glm-5.2— cache_read:0.08→0.05; input:0.5→0.3; output:2.2→1.05crossmodel/deepseek/deepseek-v4-flash— cache_read:0.004→0.0135; cache_write:0.16→0.405; input:0.16→0.405; output:0.32→1.215crossmodel/deepseek/deepseek-v4-pro— cache_read:0.005→0.0405; cache_write:0.47→1.215; input:0.47→1.215; output:0.94→3.645crossmodel/x-ai/grok-4.5— cache_read:0.5→0.3; context_over_200k:{"input":4,"output":12,"cache_read":1,"cache_write":4}→{"input":4,"output":12,"cache_read":0.6,"cache_write":4}; tiers:[{"input":4,"output":12,"cache_read":1,"cache_write":4,"tier":{"type":"context","size":200000}}]→[{"input":4,"output":12,"cache_read":0.6,"cache_write":4,"tier":{"type":"context","size":200000}}]deepinfra/MiniMaxAI/MiniMax-M3— cache_read:0.06→0.056; input:0.3→0.28; output:1.2→1.1deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731— cache_read:0.018→0.016; input:0.09→0.08deepinfra/moonshotai/Kimi-K2.7-Code— cache_read:0.15→0.136; input:0.74→0.68; output:3.5→3.4deepinfra/moonshotai/Kimi-K3— cache_read:0.27→0.285; input:2.7→2.85; output:13.5→14.25digitalocean/anthropic-claude-4.5-sonnet— context_over_200k:{"input":6,"output":22.5,"cache_read":0.3,"cache_write":3.75}→{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}; tiers:[{"input":6,"output":22.5,"cache_read":0.3,"cache_write":3.75,"tier":{"type":"context","size":200000}}]→[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}]digitalocean/anthropic-claude-4.6-sonnet— context_over_200k:{"input":6,"output":22.5,"cache_read":0.3,"cache_write":3.75}→{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}; tiers:[{"input":6,"output":22.5,"cache_read":0.3,"cache_write":3.75,"tier":{"type":"context","size":200000}}]→[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}]digitalocean/anthropic-claude-fable-5— cache_read:missing→1; cache_write:missing→12.5; input:missing→10; output:missing→50digitalocean/anthropic-claude-haiku-4.5— cache_read:1→0.1An extended generated list is available in the workflow run summary.
Generated automatically by the weekly pricing refresh workflow.