From d22d6e30550347d8ea29abf47f4771d5278bd73b Mon Sep 17 00:00:00 2001 From: Fabio Suizu Date: Sat, 28 Feb 2026 09:58:44 -0300 Subject: [PATCH 1/3] feat: add Brainiall as AI model provider --- packages/core/script/generate-venice.ts | 33 +++++++++++++++++-- .../models/gpt-5.3-codex.toml | 23 ------------- providers/azure/models/gpt-5.3-codex.toml | 23 ------------- providers/brainiall/logo.svg | 8 +++++ .../brainiall/models/claude-3-haiku.toml | 24 ++++++++++++++ .../brainiall/models/claude-3.5-haiku.toml | 25 ++++++++++++++ .../brainiall/models/claude-haiku-4-5.toml | 25 ++++++++++++++ .../brainiall/models/claude-opus-4-5.toml | 25 ++++++++++++++ .../models/claude-opus-4-6.toml} | 11 ++++--- .../models/claude-sonnet-4-6.toml} | 9 ++--- .../models/command-r-plus.toml} | 20 +++++------ providers/brainiall/models/deepseek-r1.toml | 23 +++++++++++++ providers/brainiall/models/deepseek-v3.toml | 23 +++++++++++++ providers/brainiall/models/devstral-2.toml | 23 +++++++++++++ providers/brainiall/models/gemma-3-27b.toml | 22 +++++++++++++ .../models/glm-4.7.toml} | 22 ++++++------- .../models/gpt-oss-120b.toml} | 18 +++++----- providers/brainiall/models/kimi-k2.5.toml | 22 +++++++++++++ .../models/llama-3.1-8b.toml} | 17 +++++----- providers/brainiall/models/llama-3.2-1b.toml | 22 +++++++++++++ providers/brainiall/models/llama-3.2-3b.toml | 22 +++++++++++++ providers/brainiall/models/llama-3.3-70b.toml | 23 +++++++++++++ providers/brainiall/models/llama-4-scout.toml | 23 +++++++++++++ .../models/minimax-m2.toml} | 17 ++++------ .../brainiall/models/mistral-large-3.toml | 23 +++++++++++++ providers/brainiall/models/mistral-small.toml | 23 +++++++++++++ providers/brainiall/models/nemotron-30b.toml | 23 +++++++++++++ providers/brainiall/models/nova-lite.toml | 24 ++++++++++++++ providers/brainiall/models/nova-micro.toml | 24 ++++++++++++++ providers/brainiall/models/nova-premier.toml | 23 +++++++++++++ providers/brainiall/models/nova-pro.toml | 24 ++++++++++++++ providers/brainiall/models/palmyra-x5.toml | 22 +++++++++++++ providers/brainiall/models/qwen3-32b.toml | 23 +++++++++++++ providers/brainiall/models/qwen3-80b.toml | 22 +++++++++++++ providers/brainiall/provider.toml | 5 +++ .../models/openai/gpt-5.2-codex.toml | 28 ---------------- .../models/openai/gpt-5.3-codex.toml | 28 ---------------- providers/opencode-go/logo.svg | 3 -- providers/opencode-go/models/kimi-k2.5.toml | 26 --------------- .../opencode-go/models/minimax-m2.5.toml | 26 --------------- providers/opencode-go/provider.toml | 5 --- providers/opencode/logo.svg | 1 + providers/opencode/models/glm-5-free.toml | 1 - providers/opencode/models/gpt-5.3-codex.toml | 28 ---------------- .../gemini-3.1-pro-preview-customtools.toml | 32 ------------------ .../models/gemini-2.5-flash-lite.toml | 24 -------------- .../sap-ai-core/models/gpt-4.1-mini.toml | 24 -------------- providers/sap-ai-core/models/gpt-4.1.toml | 24 -------------- providers/sap-ai-core/models/sonar-pro.toml | 22 ------------- providers/venice/README.md | 3 +- .../venice/models/gemini-3-1-pro-preview.toml | 4 +-- .../venice/models/openai-gpt-53-codex.toml | 23 ------------- .../vercel/models/alibaba/qwen3.5-flash.toml | 23 ------------- .../models/google/gemini-3.1-pro-preview.toml | 22 ------------- .../vercel/models/openai/gpt-5.3-codex.toml | 22 ------------- 55 files changed, 638 insertions(+), 470 deletions(-) delete mode 100644 providers/azure-cognitive-services/models/gpt-5.3-codex.toml delete mode 100644 providers/azure/models/gpt-5.3-codex.toml create mode 100644 providers/brainiall/logo.svg create mode 100644 providers/brainiall/models/claude-3-haiku.toml create mode 100644 providers/brainiall/models/claude-3.5-haiku.toml create mode 100644 providers/brainiall/models/claude-haiku-4-5.toml create mode 100644 providers/brainiall/models/claude-opus-4-5.toml rename providers/{sap-ai-core/models/anthropic--claude-4.6-opus.toml => brainiall/models/claude-opus-4-6.toml} (87%) rename providers/{sap-ai-core/models/anthropic--claude-4.6-sonnet.toml => brainiall/models/claude-sonnet-4-6.toml} (89%) rename providers/{venice/models/qwen3-coder-480b-a35b-instruct-turbo.toml => brainiall/models/command-r-plus.toml} (50%) create mode 100644 providers/brainiall/models/deepseek-r1.toml create mode 100644 providers/brainiall/models/deepseek-v3.toml create mode 100644 providers/brainiall/models/devstral-2.toml create mode 100644 providers/brainiall/models/gemma-3-27b.toml rename providers/{opencode-go/models/glm-5.toml => brainiall/models/glm-4.7.toml} (55%) rename providers/{sap-ai-core/models/sonar.toml => brainiall/models/gpt-oss-120b.toml} (51%) create mode 100644 providers/brainiall/models/kimi-k2.5.toml rename providers/{venice/models/nvidia-nemotron-3-nano-30b-a3b.toml => brainiall/models/llama-3.1-8b.toml} (55%) create mode 100644 providers/brainiall/models/llama-3.2-1b.toml create mode 100644 providers/brainiall/models/llama-3.2-3b.toml create mode 100644 providers/brainiall/models/llama-3.3-70b.toml create mode 100644 providers/brainiall/models/llama-4-scout.toml rename providers/{baseten/models/MiniMaxAI/MiniMax-M2.5.toml => brainiall/models/minimax-m2.toml} (53%) create mode 100644 providers/brainiall/models/mistral-large-3.toml create mode 100644 providers/brainiall/models/mistral-small.toml create mode 100644 providers/brainiall/models/nemotron-30b.toml create mode 100644 providers/brainiall/models/nova-lite.toml create mode 100644 providers/brainiall/models/nova-micro.toml create mode 100644 providers/brainiall/models/nova-premier.toml create mode 100644 providers/brainiall/models/nova-pro.toml create mode 100644 providers/brainiall/models/palmyra-x5.toml create mode 100644 providers/brainiall/models/qwen3-32b.toml create mode 100644 providers/brainiall/models/qwen3-80b.toml create mode 100644 providers/brainiall/provider.toml delete mode 100644 providers/cloudflare-ai-gateway/models/openai/gpt-5.2-codex.toml delete mode 100644 providers/cloudflare-ai-gateway/models/openai/gpt-5.3-codex.toml delete mode 100644 providers/opencode-go/logo.svg delete mode 100644 providers/opencode-go/models/kimi-k2.5.toml delete mode 100644 providers/opencode-go/models/minimax-m2.5.toml delete mode 100644 providers/opencode-go/provider.toml delete mode 100644 providers/opencode/models/gpt-5.3-codex.toml delete mode 100644 providers/openrouter/models/google/gemini-3.1-pro-preview-customtools.toml delete mode 100644 providers/sap-ai-core/models/gemini-2.5-flash-lite.toml delete mode 100644 providers/sap-ai-core/models/gpt-4.1-mini.toml delete mode 100644 providers/sap-ai-core/models/gpt-4.1.toml delete mode 100644 providers/sap-ai-core/models/sonar-pro.toml delete mode 100644 providers/venice/models/openai-gpt-53-codex.toml delete mode 100644 providers/vercel/models/alibaba/qwen3.5-flash.toml delete mode 100644 providers/vercel/models/google/gemini-3.1-pro-preview.toml delete mode 100644 providers/vercel/models/openai/gpt-5.3-codex.toml diff --git a/packages/core/script/generate-venice.ts b/packages/core/script/generate-venice.ts index 77a78aadb..346e5529b 100644 --- a/packages/core/script/generate-venice.ts +++ b/packages/core/script/generate-venice.ts @@ -3,11 +3,30 @@ import { z } from "zod"; import path from "node:path"; import { readdir } from "node:fs/promises"; +import * as readline from "node:readline"; import { ModelFamilyValues } from "../src/family.js"; // Venice API endpoint const API_ENDPOINT = "https://api.venice.ai/api/v1/models?type=text"; +async function promptForApiKey(): Promise { + const rl = readline.createInterface({ + input: process.stdin, + output: process.stdout, + }); + + return new Promise((resolve) => { + rl.question( + "Enter Venice API key to include alpha models (or press Enter to skip): ", + (answer) => { + rl.close(); + const trimmed = answer.trim(); + resolve(trimmed.length > 0 ? trimmed : null); + }, + ); + }); +} + // Zod schemas for API response validation const Capabilities = z .object({ @@ -50,7 +69,6 @@ const ModelSpec = z .object({ pricing: Pricing.optional(), availableContextTokens: z.number(), - maxCompletionTokens: z.number().optional(), capabilities: Capabilities, constraints: z.any().optional(), name: z.string(), @@ -239,7 +257,11 @@ function mergeModel( const caps = spec.capabilities; const contextTokens = spec.availableContextTokens; - const outputTokens = spec.maxCompletionTokens ?? Math.floor(contextTokens / 4); + const proposedOutputTokens = Math.floor(contextTokens / 4); + const outputTokens = + existing?.limit?.output !== undefined && existing.limit.output < proposedOutputTokens + ? existing.limit.output + : proposedOutputTokens const openWeights = spec.modelSource ? spec.modelSource.toLowerCase().includes("huggingface") @@ -465,7 +487,7 @@ async function main() { "models", ); - // Check for API key from CLI argument or environment variable + // Check for API key from CLI argument, environment, or prompt let apiKey: string | null = null; // Check CLI args for --api-key=xxx or --api-key xxx @@ -484,6 +506,11 @@ async function main() { apiKey = process.env.VENICE_API_KEY ?? null; } + // Prompt if still no key + if (!apiKey) { + apiKey = await promptForApiKey(); + } + const includeAlpha = apiKey !== null; if (dryRun) { diff --git a/providers/azure-cognitive-services/models/gpt-5.3-codex.toml b/providers/azure-cognitive-services/models/gpt-5.3-codex.toml deleted file mode 100644 index 57fc28803..000000000 --- a/providers/azure-cognitive-services/models/gpt-5.3-codex.toml +++ /dev/null @@ -1,23 +0,0 @@ -name = "GPT-5.3 Codex" -family = "gpt-codex" -release_date = "2026-02-24" -last_updated = "2026-02-24" -attachment = false -reasoning = true -temperature = false -knowledge = "2025-08-31" -tool_call = true -open_weights = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/azure/models/gpt-5.3-codex.toml b/providers/azure/models/gpt-5.3-codex.toml deleted file mode 100644 index 57fc28803..000000000 --- a/providers/azure/models/gpt-5.3-codex.toml +++ /dev/null @@ -1,23 +0,0 @@ -name = "GPT-5.3 Codex" -family = "gpt-codex" -release_date = "2026-02-24" -last_updated = "2026-02-24" -attachment = false -reasoning = true -temperature = false -knowledge = "2025-08-31" -tool_call = true -open_weights = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/brainiall/logo.svg b/providers/brainiall/logo.svg new file mode 100644 index 000000000..1693f086e --- /dev/null +++ b/providers/brainiall/logo.svg @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/providers/brainiall/models/claude-3-haiku.toml b/providers/brainiall/models/claude-3-haiku.toml new file mode 100644 index 000000000..0b0220863 --- /dev/null +++ b/providers/brainiall/models/claude-3-haiku.toml @@ -0,0 +1,24 @@ +name = "Claude 3 Haiku" +release_date = "2024-03-13" +last_updated = "2024-03-13" +family = "claude-haiku" +attachment = true +reasoning = false +tool_call = true +open_weights = false +temperature = true +knowledge = "2023-08-31" + +[cost] +input = 0.25 +output = 1.25 +cache_read = 0.03 +cache_write = 0.30 + +[limit] +context = 200_000 +output = 4_096 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] diff --git a/providers/brainiall/models/claude-3.5-haiku.toml b/providers/brainiall/models/claude-3.5-haiku.toml new file mode 100644 index 000000000..f706ba6da --- /dev/null +++ b/providers/brainiall/models/claude-3.5-haiku.toml @@ -0,0 +1,25 @@ +name = "Claude 3.5 Haiku" +release_date = "2024-10-22" +last_updated = "2024-10-22" +family = "claude-haiku" +attachment = true +reasoning = false +tool_call = true +open_weights = false +structured_output = true +temperature = true +knowledge = "2024-07-31" + +[cost] +input = 0.80 +output = 4.00 +cache_read = 0.08 +cache_write = 1.00 + +[limit] +context = 200_000 +output = 8_192 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] diff --git a/providers/brainiall/models/claude-haiku-4-5.toml b/providers/brainiall/models/claude-haiku-4-5.toml new file mode 100644 index 000000000..1a852d731 --- /dev/null +++ b/providers/brainiall/models/claude-haiku-4-5.toml @@ -0,0 +1,25 @@ +name = "Claude Haiku 4.5" +release_date = "2025-10-15" +last_updated = "2025-10-15" +family = "claude-haiku" +attachment = true +reasoning = true +tool_call = true +open_weights = false +structured_output = true +temperature = true +knowledge = "2025-02-28" + +[cost] +input = 1.00 +output = 5.00 +cache_read = 0.10 +cache_write = 1.25 + +[limit] +context = 200_000 +output = 8_192 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] diff --git a/providers/brainiall/models/claude-opus-4-5.toml b/providers/brainiall/models/claude-opus-4-5.toml new file mode 100644 index 000000000..313065731 --- /dev/null +++ b/providers/brainiall/models/claude-opus-4-5.toml @@ -0,0 +1,25 @@ +name = "Claude Opus 4.5" +release_date = "2025-11-24" +last_updated = "2025-11-24" +family = "claude-opus" +attachment = true +reasoning = true +tool_call = true +open_weights = false +structured_output = true +temperature = true +knowledge = "2025-03-31" + +[cost] +input = 5.00 +output = 25.00 +cache_read = 0.50 +cache_write = 6.25 + +[limit] +context = 200_000 +output = 64_000 + +[modalities] +input = ["text", "image", "pdf"] +output = ["text"] diff --git a/providers/sap-ai-core/models/anthropic--claude-4.6-opus.toml b/providers/brainiall/models/claude-opus-4-6.toml similarity index 87% rename from providers/sap-ai-core/models/anthropic--claude-4.6-opus.toml rename to providers/brainiall/models/claude-opus-4-6.toml index 20e4d5863..3ac6eba0f 100644 --- a/providers/sap-ai-core/models/anthropic--claude-4.6-opus.toml +++ b/providers/brainiall/models/claude-opus-4-6.toml @@ -1,13 +1,14 @@ -name = "anthropic--claude-4.6-opus" -family = "claude-opus" +name = "Claude Opus 4.6" release_date = "2026-02-05" last_updated = "2026-02-05" +family = "claude-opus" attachment = true reasoning = true -temperature = true tool_call = true -knowledge = "2025-05" open_weights = false +structured_output = true +temperature = true +knowledge = "2025-05" [cost] input = 5.00 @@ -23,7 +24,7 @@ cache_write = 12.50 [limit] context = 200_000 -output = 128_000 +output = 32_000 [modalities] input = ["text", "image", "pdf"] diff --git a/providers/sap-ai-core/models/anthropic--claude-4.6-sonnet.toml b/providers/brainiall/models/claude-sonnet-4-6.toml similarity index 89% rename from providers/sap-ai-core/models/anthropic--claude-4.6-sonnet.toml rename to providers/brainiall/models/claude-sonnet-4-6.toml index 1a04ce359..99ccf2e06 100644 --- a/providers/sap-ai-core/models/anthropic--claude-4.6-sonnet.toml +++ b/providers/brainiall/models/claude-sonnet-4-6.toml @@ -1,13 +1,14 @@ -name = "anthropic--claude-4.6-sonnet" -family = "claude-sonnet" +name = "Claude Sonnet 4.6" release_date = "2026-02-17" last_updated = "2026-02-17" +family = "claude-sonnet" attachment = true reasoning = true -temperature = true tool_call = true -knowledge = "2025-08" open_weights = false +structured_output = true +temperature = true +knowledge = "2025-08" [cost] input = 3.00 diff --git a/providers/venice/models/qwen3-coder-480b-a35b-instruct-turbo.toml b/providers/brainiall/models/command-r-plus.toml similarity index 50% rename from providers/venice/models/qwen3-coder-480b-a35b-instruct-turbo.toml rename to providers/brainiall/models/command-r-plus.toml index 3bea35197..be484290b 100644 --- a/providers/venice/models/qwen3-coder-480b-a35b-instruct-turbo.toml +++ b/providers/brainiall/models/command-r-plus.toml @@ -1,22 +1,22 @@ -name = "Qwen 3 Coder 480B Turbo" -family = "qwen" +name = "Command R+" +release_date = "2024-04-04" +last_updated = "2024-04-04" +family = "command-r" attachment = false reasoning = false tool_call = true +open_weights = true structured_output = true temperature = true -release_date = "2026-01-27" -last_updated = "2026-02-26" -open_weights = true +knowledge = "2024-04" [cost] -input = 0.35 -output = 1.5 -cache_read = 0.04 +input = 3.00 +output = 15.00 [limit] -context = 256_000 -output = 65_536 +context = 128_000 +output = 4_096 [modalities] input = ["text"] diff --git a/providers/brainiall/models/deepseek-r1.toml b/providers/brainiall/models/deepseek-r1.toml new file mode 100644 index 000000000..3d6e66343 --- /dev/null +++ b/providers/brainiall/models/deepseek-r1.toml @@ -0,0 +1,23 @@ +name = "DeepSeek R1" +release_date = "2025-01-20" +last_updated = "2025-05-29" +family = "deepseek-thinking" +attachment = false +reasoning = true +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2024-07" + +[cost] +input = 1.35 +output = 5.40 + +[limit] +context = 128_000 +output = 64_000 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/deepseek-v3.toml b/providers/brainiall/models/deepseek-v3.toml new file mode 100644 index 000000000..e615c4e9b --- /dev/null +++ b/providers/brainiall/models/deepseek-v3.toml @@ -0,0 +1,23 @@ +name = "DeepSeek V3" +release_date = "2026-02-15" +last_updated = "2026-02-15" +family = "deepseek" +attachment = false +reasoning = true +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2024-07" + +[cost] +input = 0.27 +output = 1.10 + +[limit] +context = 128_000 +output = 8_192 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/devstral-2.toml b/providers/brainiall/models/devstral-2.toml new file mode 100644 index 000000000..68893596b --- /dev/null +++ b/providers/brainiall/models/devstral-2.toml @@ -0,0 +1,23 @@ +name = "Devstral 2 123B" +release_date = "2025-12-09" +last_updated = "2025-12-09" +family = "devstral" +attachment = false +reasoning = false +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2025-12" + +[cost] +input = 0.40 +output = 2.00 + +[limit] +context = 262_144 +output = 262_144 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/gemma-3-27b.toml b/providers/brainiall/models/gemma-3-27b.toml new file mode 100644 index 000000000..65b01ceaf --- /dev/null +++ b/providers/brainiall/models/gemma-3-27b.toml @@ -0,0 +1,22 @@ +name = "Gemma 3 27B" +release_date = "2025-07-27" +last_updated = "2025-07-27" +family = "gemma" +attachment = true +reasoning = false +tool_call = true +open_weights = true +temperature = true +knowledge = "2025-07" + +[cost] +input = 0.12 +output = 0.20 + +[limit] +context = 202_752 +output = 8_192 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/opencode-go/models/glm-5.toml b/providers/brainiall/models/glm-4.7.toml similarity index 55% rename from providers/opencode-go/models/glm-5.toml rename to providers/brainiall/models/glm-4.7.toml index 7fd605088..6f0a8ae22 100644 --- a/providers/opencode-go/models/glm-5.toml +++ b/providers/brainiall/models/glm-4.7.toml @@ -1,26 +1,26 @@ -name = "GLM-5" +name = "GLM 4.7" +release_date = "2025-12-22" +last_updated = "2025-12-22" family = "glm" -release_date = "2026-02-11" -last_updated = "2026-02-11" attachment = false reasoning = true -temperature = true tool_call = true -knowledge = "2025-04" open_weights = true +structured_output = true +temperature = true +knowledge = "2025-04" [interleaved] field = "reasoning_content" [cost] -input = 1.0 -output = 3.2 -cache_read = 0.2 +input = 0.60 +output = 2.20 [limit] -context = 204800 -output = 131072 +context = 204_800 +output = 131_072 [modalities] input = ["text"] -output = ["text"] \ No newline at end of file +output = ["text"] diff --git a/providers/sap-ai-core/models/sonar.toml b/providers/brainiall/models/gpt-oss-120b.toml similarity index 51% rename from providers/sap-ai-core/models/sonar.toml rename to providers/brainiall/models/gpt-oss-120b.toml index 310f6822d..07af7df5e 100644 --- a/providers/sap-ai-core/models/sonar.toml +++ b/providers/brainiall/models/gpt-oss-120b.toml @@ -1,17 +1,17 @@ -name = "sonar" -family = "sonar" -release_date = "2024-01-01" -last_updated = "2025-09-01" +name = "GPT OSS 120B" +release_date = "2024-12-01" +last_updated = "2024-12-01" +family = "gpt-oss" attachment = false reasoning = false -temperature = true -tool_call = false -knowledge = "2025-09-01" +tool_call = true open_weights = false +structured_output = true +temperature = true [cost] -input = 1.00 -output = 1.00 +input = 0.15 +output = 0.60 [limit] context = 128_000 diff --git a/providers/brainiall/models/kimi-k2.5.toml b/providers/brainiall/models/kimi-k2.5.toml new file mode 100644 index 000000000..d58bb26d8 --- /dev/null +++ b/providers/brainiall/models/kimi-k2.5.toml @@ -0,0 +1,22 @@ +name = "Kimi K2.5" +release_date = "2026-02-06" +last_updated = "2026-02-06" +family = "kimi" +attachment = false +reasoning = true +tool_call = true +open_weights = true +structured_output = true +temperature = true + +[cost] +input = 0.60 +output = 3.00 + +[limit] +context = 256_000 +output = 256_000 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/nvidia-nemotron-3-nano-30b-a3b.toml b/providers/brainiall/models/llama-3.1-8b.toml similarity index 55% rename from providers/venice/models/nvidia-nemotron-3-nano-30b-a3b.toml rename to providers/brainiall/models/llama-3.1-8b.toml index af8ec866d..6957d5dc1 100644 --- a/providers/venice/models/nvidia-nemotron-3-nano-30b-a3b.toml +++ b/providers/brainiall/models/llama-3.1-8b.toml @@ -1,21 +1,22 @@ -name = "NVIDIA Nemotron 3 Nano 30B" -family = "nemotron" +name = "Llama 3.1 8B" +release_date = "2024-07-23" +last_updated = "2024-07-23" +family = "llama" attachment = false reasoning = false tool_call = true +open_weights = true structured_output = true temperature = true -release_date = "2026-01-27" -last_updated = "2026-02-26" -open_weights = true +knowledge = "2023-12" [cost] -input = 0.075 -output = 0.3 +input = 0.22 +output = 0.22 [limit] context = 128_000 -output = 12_288 +output = 4_096 [modalities] input = ["text"] diff --git a/providers/brainiall/models/llama-3.2-1b.toml b/providers/brainiall/models/llama-3.2-1b.toml new file mode 100644 index 000000000..bc478e4d2 --- /dev/null +++ b/providers/brainiall/models/llama-3.2-1b.toml @@ -0,0 +1,22 @@ +name = "Llama 3.2 1B" +release_date = "2024-09-25" +last_updated = "2024-09-25" +family = "llama" +attachment = false +reasoning = false +tool_call = true +open_weights = true +temperature = true +knowledge = "2023-12" + +[cost] +input = 0.10 +output = 0.10 + +[limit] +context = 128_000 +output = 4_096 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/llama-3.2-3b.toml b/providers/brainiall/models/llama-3.2-3b.toml new file mode 100644 index 000000000..e0d656f29 --- /dev/null +++ b/providers/brainiall/models/llama-3.2-3b.toml @@ -0,0 +1,22 @@ +name = "Llama 3.2 3B" +release_date = "2024-09-25" +last_updated = "2024-09-25" +family = "llama" +attachment = false +reasoning = false +tool_call = true +open_weights = true +temperature = true +knowledge = "2023-12" + +[cost] +input = 0.15 +output = 0.15 + +[limit] +context = 128_000 +output = 4_096 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/llama-3.3-70b.toml b/providers/brainiall/models/llama-3.3-70b.toml new file mode 100644 index 000000000..a2838c733 --- /dev/null +++ b/providers/brainiall/models/llama-3.3-70b.toml @@ -0,0 +1,23 @@ +name = "Llama 3.3 70B" +release_date = "2024-12-06" +last_updated = "2024-12-06" +family = "llama" +attachment = false +reasoning = false +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2023-12" + +[cost] +input = 0.72 +output = 0.72 + +[limit] +context = 128_000 +output = 4_096 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/llama-4-scout.toml b/providers/brainiall/models/llama-4-scout.toml new file mode 100644 index 000000000..f24ffbcc5 --- /dev/null +++ b/providers/brainiall/models/llama-4-scout.toml @@ -0,0 +1,23 @@ +name = "Llama 4 Scout 17B" +release_date = "2025-04-05" +last_updated = "2025-04-05" +family = "llama" +attachment = true +reasoning = false +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2024-08" + +[cost] +input = 0.17 +output = 0.66 + +[limit] +context = 3_500_000 +output = 16_384 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/baseten/models/MiniMaxAI/MiniMax-M2.5.toml b/providers/brainiall/models/minimax-m2.toml similarity index 53% rename from providers/baseten/models/MiniMaxAI/MiniMax-M2.5.toml rename to providers/brainiall/models/minimax-m2.toml index 481a10f45..c0e1e571c 100644 --- a/providers/baseten/models/MiniMaxAI/MiniMax-M2.5.toml +++ b/providers/brainiall/models/minimax-m2.toml @@ -1,24 +1,21 @@ -name = "MiniMax-M2.5" +name = "MiniMax M2" +release_date = "2025-10-27" +last_updated = "2025-10-27" family = "minimax" -release_date = "2026-02-12" -last_updated = "2026-02-12" attachment = false reasoning = true -temperature = true tool_call = true -knowledge = "2026-01" open_weights = true - -[interleaved] -field = "reasoning_content" +structured_output = false +temperature = true [cost] input = 0.30 output = 1.20 [limit] -context = 204000 -output = 204000 +context = 204_608 +output = 128_000 [modalities] input = ["text"] diff --git a/providers/brainiall/models/mistral-large-3.toml b/providers/brainiall/models/mistral-large-3.toml new file mode 100644 index 000000000..b1839c430 --- /dev/null +++ b/providers/brainiall/models/mistral-large-3.toml @@ -0,0 +1,23 @@ +name = "Mistral Large 3 675B" +release_date = "2024-11-01" +last_updated = "2025-12-02" +family = "mistral-large" +attachment = true +reasoning = false +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2024-11" + +[cost] +input = 2.00 +output = 6.00 + +[limit] +context = 262_144 +output = 262_144 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/brainiall/models/mistral-small.toml b/providers/brainiall/models/mistral-small.toml new file mode 100644 index 000000000..a58c055db --- /dev/null +++ b/providers/brainiall/models/mistral-small.toml @@ -0,0 +1,23 @@ +name = "Mistral Small 24B" +release_date = "2024-09-01" +last_updated = "2024-09-04" +family = "mistral-small" +attachment = false +reasoning = false +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2025-03" + +[cost] +input = 0.10 +output = 0.30 + +[limit] +context = 128_000 +output = 16_384 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/brainiall/models/nemotron-30b.toml b/providers/brainiall/models/nemotron-30b.toml new file mode 100644 index 000000000..556835942 --- /dev/null +++ b/providers/brainiall/models/nemotron-30b.toml @@ -0,0 +1,23 @@ +name = "Nemotron Nano 30B" +release_date = "2024-12-01" +last_updated = "2024-12-01" +family = "nemotron" +attachment = false +reasoning = true +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2024-09" + +[cost] +input = 0.06 +output = 0.24 + +[limit] +context = 128_000 +output = 8_192 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/nova-lite.toml b/providers/brainiall/models/nova-lite.toml new file mode 100644 index 000000000..9907469de --- /dev/null +++ b/providers/brainiall/models/nova-lite.toml @@ -0,0 +1,24 @@ +name = "Amazon Nova Lite" +release_date = "2024-12-03" +last_updated = "2024-12-03" +family = "nova-lite" +attachment = true +reasoning = false +tool_call = true +open_weights = false +structured_output = true +temperature = true +knowledge = "2024-10" + +[cost] +input = 0.06 +output = 0.24 +cache_read = 0.015 + +[limit] +context = 300_000 +output = 5_120 + +[modalities] +input = ["text", "image", "video"] +output = ["text"] diff --git a/providers/brainiall/models/nova-micro.toml b/providers/brainiall/models/nova-micro.toml new file mode 100644 index 000000000..6678a50b6 --- /dev/null +++ b/providers/brainiall/models/nova-micro.toml @@ -0,0 +1,24 @@ +name = "Amazon Nova Micro" +release_date = "2024-12-03" +last_updated = "2024-12-03" +family = "nova-micro" +attachment = false +reasoning = false +tool_call = true +open_weights = false +structured_output = true +temperature = true +knowledge = "2024-10" + +[cost] +input = 0.035 +output = 0.14 +cache_read = 0.00875 + +[limit] +context = 128_000 +output = 5_120 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/nova-premier.toml b/providers/brainiall/models/nova-premier.toml new file mode 100644 index 000000000..6dc7943b2 --- /dev/null +++ b/providers/brainiall/models/nova-premier.toml @@ -0,0 +1,23 @@ +name = "Amazon Nova Premier" +release_date = "2024-12-03" +last_updated = "2024-12-03" +family = "nova" +attachment = true +reasoning = true +tool_call = true +open_weights = false +structured_output = true +temperature = true +knowledge = "2024-10" + +[cost] +input = 2.50 +output = 12.50 + +[limit] +context = 1_000_000 +output = 16_384 + +[modalities] +input = ["text", "image", "video"] +output = ["text"] diff --git a/providers/brainiall/models/nova-pro.toml b/providers/brainiall/models/nova-pro.toml new file mode 100644 index 000000000..bcc58ea86 --- /dev/null +++ b/providers/brainiall/models/nova-pro.toml @@ -0,0 +1,24 @@ +name = "Amazon Nova Pro" +release_date = "2024-12-03" +last_updated = "2024-12-03" +family = "nova-pro" +attachment = true +reasoning = false +tool_call = true +open_weights = false +structured_output = true +temperature = true +knowledge = "2024-10" + +[cost] +input = 0.80 +output = 3.20 +cache_read = 0.20 + +[limit] +context = 300_000 +output = 5_120 + +[modalities] +input = ["text", "image", "video"] +output = ["text"] diff --git a/providers/brainiall/models/palmyra-x5.toml b/providers/brainiall/models/palmyra-x5.toml new file mode 100644 index 000000000..1547c2d3c --- /dev/null +++ b/providers/brainiall/models/palmyra-x5.toml @@ -0,0 +1,22 @@ +name = "Palmyra X5" +release_date = "2025-04-28" +last_updated = "2025-04-28" +family = "palmyra" +attachment = false +reasoning = true +tool_call = true +open_weights = false +structured_output = true +temperature = true + +[cost] +input = 0.60 +output = 6.00 + +[limit] +context = 1_040_000 +output = 8_192 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/qwen3-32b.toml b/providers/brainiall/models/qwen3-32b.toml new file mode 100644 index 000000000..86d1f0cfe --- /dev/null +++ b/providers/brainiall/models/qwen3-32b.toml @@ -0,0 +1,23 @@ +name = "Qwen3 32B" +release_date = "2025-09-18" +last_updated = "2025-09-18" +family = "qwen" +attachment = false +reasoning = true +tool_call = true +open_weights = true +structured_output = true +temperature = true +knowledge = "2024-04" + +[cost] +input = 0.15 +output = 0.60 + +[limit] +context = 16_384 +output = 16_384 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/models/qwen3-80b.toml b/providers/brainiall/models/qwen3-80b.toml new file mode 100644 index 000000000..531e439be --- /dev/null +++ b/providers/brainiall/models/qwen3-80b.toml @@ -0,0 +1,22 @@ +name = "Qwen3 80B (MoE)" +release_date = "2025-09-18" +last_updated = "2025-11-25" +family = "qwen" +attachment = false +reasoning = false +tool_call = true +open_weights = false +structured_output = true +temperature = true + +[cost] +input = 0.14 +output = 1.40 + +[limit] +context = 262_000 +output = 262_000 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/brainiall/provider.toml b/providers/brainiall/provider.toml new file mode 100644 index 000000000..24f476b0c --- /dev/null +++ b/providers/brainiall/provider.toml @@ -0,0 +1,5 @@ +name = "Brainiall" +env = ["BRAINIALL_API_KEY"] +npm = "@ai-sdk/openai-compatible" +api = "https://apim-ai-apis.azure-api.net/v1" +doc = "https://app.brainiall.com" diff --git a/providers/cloudflare-ai-gateway/models/openai/gpt-5.2-codex.toml b/providers/cloudflare-ai-gateway/models/openai/gpt-5.2-codex.toml deleted file mode 100644 index 96d9680ae..000000000 --- a/providers/cloudflare-ai-gateway/models/openai/gpt-5.2-codex.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "GPT-5.2 Codex" -family = "gpt-codex" -release_date = "2025-12-11" -last_updated = "2025-12-11" -attachment = true -reasoning = true -temperature = false -knowledge = "2025-08-31" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400_000 -input = 272_000 -output = 128_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] - -[provider] -npm = "ai-gateway-provider" diff --git a/providers/cloudflare-ai-gateway/models/openai/gpt-5.3-codex.toml b/providers/cloudflare-ai-gateway/models/openai/gpt-5.3-codex.toml deleted file mode 100644 index 36299a222..000000000 --- a/providers/cloudflare-ai-gateway/models/openai/gpt-5.3-codex.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "GPT-5.3 Codex" -family = "gpt-codex" -release_date = "2026-02-05" -last_updated = "2026-02-05" -attachment = true -reasoning = true -temperature = false -knowledge = "2025-08-31" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400_000 -input = 272_000 -output = 128_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] - -[provider] -npm = "ai-gateway-provider" diff --git a/providers/opencode-go/logo.svg b/providers/opencode-go/logo.svg deleted file mode 100644 index e0833b923..000000000 --- a/providers/opencode-go/logo.svg +++ /dev/null @@ -1,3 +0,0 @@ - - - diff --git a/providers/opencode-go/models/kimi-k2.5.toml b/providers/opencode-go/models/kimi-k2.5.toml deleted file mode 100644 index bc89f9168..000000000 --- a/providers/opencode-go/models/kimi-k2.5.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "Kimi K2.5" -family = "kimi" -release_date = "2026-01-27" -last_updated = "2026-01-27" -attachment = true -reasoning = true -temperature = true -tool_call = true -knowledge = "2024-10" -open_weights = true - -[interleaved] -field = "reasoning_content" - -[cost] -input = 0.6 -output = 3.0 -cache_read = 0.1 - -[limit] -context = 262_144 -output = 65_536 - -[modalities] -input = ["text", "image", "video"] -output = ["text"] diff --git a/providers/opencode-go/models/minimax-m2.5.toml b/providers/opencode-go/models/minimax-m2.5.toml deleted file mode 100644 index 503469cd8..000000000 --- a/providers/opencode-go/models/minimax-m2.5.toml +++ /dev/null @@ -1,26 +0,0 @@ -name = "MiniMax M2.5" -family = "minimax" -release_date = "2026-02-12" -last_updated = "2026-02-12" -attachment = false -reasoning = true -temperature = true -tool_call = true -knowledge = "2025-01" -open_weights = true - -[cost] -input = 0.3 -output = 1.2 -cache_read = 0.03 - -[limit] -context = 204_800 -output = 131_072 - -[modalities] -input = ["text"] -output = ["text"] - -[provider] -npm = "@ai-sdk/anthropic" \ No newline at end of file diff --git a/providers/opencode-go/provider.toml b/providers/opencode-go/provider.toml deleted file mode 100644 index 4c1547c53..000000000 --- a/providers/opencode-go/provider.toml +++ /dev/null @@ -1,5 +0,0 @@ -name = "OpenCode Go" -env = ["OPENCODE_API_KEY"] -npm = "@ai-sdk/openai-compatible" -api = "https://opencode.ai/zen/go/v1" -doc = "https://opencode.ai/docs/zen" diff --git a/providers/opencode/logo.svg b/providers/opencode/logo.svg index 950846582..9e336ef2d 100644 --- a/providers/opencode/logo.svg +++ b/providers/opencode/logo.svg @@ -1,3 +1,4 @@ + diff --git a/providers/opencode/models/glm-5-free.toml b/providers/opencode/models/glm-5-free.toml index 86e24ba38..f67521403 100644 --- a/providers/opencode/models/glm-5-free.toml +++ b/providers/opencode/models/glm-5-free.toml @@ -8,7 +8,6 @@ temperature = true tool_call = true knowledge = "2025-04" open_weights = true -status = "deprecated" [interleaved] field = "reasoning_content" diff --git a/providers/opencode/models/gpt-5.3-codex.toml b/providers/opencode/models/gpt-5.3-codex.toml deleted file mode 100644 index 6b6cf2f6f..000000000 --- a/providers/opencode/models/gpt-5.3-codex.toml +++ /dev/null @@ -1,28 +0,0 @@ -name = "GPT-5.3 Codex" -family = "gpt-codex" -release_date = "2026-02-24" -last_updated = "2026-02-24" -attachment = true -reasoning = true -temperature = false -knowledge = "2025-08-31" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 1.75 -output = 14.00 -cache_read = 0.175 - -[limit] -context = 400_000 -input = 272_000 -output = 128_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] - -[provider] -npm = "@ai-sdk/openai" diff --git a/providers/openrouter/models/google/gemini-3.1-pro-preview-customtools.toml b/providers/openrouter/models/google/gemini-3.1-pro-preview-customtools.toml deleted file mode 100644 index cb6f20d67..000000000 --- a/providers/openrouter/models/google/gemini-3.1-pro-preview-customtools.toml +++ /dev/null @@ -1,32 +0,0 @@ -name = "Gemini 3.1 Pro Preview Custom Tools" -family = "gemini-pro" -release_date = "2026-02-19" -last_updated = "2026-02-19" -attachment = true -reasoning = true -temperature = true -knowledge = "2025-01" -tool_call = true -structured_output = true -open_weights = false - -[interleaved] -field = "reasoning_details" - -[cost] -input = 2.00 -output = 12.00 -reasoning = 12.00 - -[cost.context_over_200k] -input = 4.00 -output = 18.00 -cache_read = 0.40 - -[limit] -context = 1_048_576 -output = 65_536 - -[modalities] -input = ["text", "image", "audio", "video", "pdf"] -output = ["text"] diff --git a/providers/sap-ai-core/models/gemini-2.5-flash-lite.toml b/providers/sap-ai-core/models/gemini-2.5-flash-lite.toml deleted file mode 100644 index d2cdc3cde..000000000 --- a/providers/sap-ai-core/models/gemini-2.5-flash-lite.toml +++ /dev/null @@ -1,24 +0,0 @@ -name = "gemini-2.5-flash-lite" -family = "gemini-flash-lite" -release_date = "2025-06-17" -last_updated = "2025-06-17" -attachment = true -reasoning = true -temperature = true -knowledge = "2025-01" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 0.10 -output = 0.40 -cache_read = 0.025 - -[limit] -context = 1_048_576 -output = 65_536 - -[modalities] -input = ["text", "image", "audio", "video", "pdf"] -output = ["text"] diff --git a/providers/sap-ai-core/models/gpt-4.1-mini.toml b/providers/sap-ai-core/models/gpt-4.1-mini.toml deleted file mode 100644 index cd4d13e7a..000000000 --- a/providers/sap-ai-core/models/gpt-4.1-mini.toml +++ /dev/null @@ -1,24 +0,0 @@ -name = "gpt-4.1-mini" -family = "gpt-mini" -release_date = "2025-04-14" -last_updated = "2025-04-14" -attachment = true -reasoning = false -temperature = true -knowledge = "2024-04" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 0.40 -output = 1.60 -cache_read = 0.10 - -[limit] -context = 1_047_576 -output = 32_768 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/sap-ai-core/models/gpt-4.1.toml b/providers/sap-ai-core/models/gpt-4.1.toml deleted file mode 100644 index 52b02390b..000000000 --- a/providers/sap-ai-core/models/gpt-4.1.toml +++ /dev/null @@ -1,24 +0,0 @@ -name = "gpt-4.1" -family = "gpt" -release_date = "2025-04-14" -last_updated = "2025-04-14" -attachment = true -reasoning = false -temperature = true -knowledge = "2024-04" -tool_call = true -structured_output = true -open_weights = false - -[cost] -input = 2.00 -output = 8.00 -cache_read = 0.50 - -[limit] -context = 1_047_576 -output = 32_768 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/sap-ai-core/models/sonar-pro.toml b/providers/sap-ai-core/models/sonar-pro.toml deleted file mode 100644 index b8c6302dc..000000000 --- a/providers/sap-ai-core/models/sonar-pro.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "sonar-pro" -family = "sonar-pro" -release_date = "2024-01-01" -last_updated = "2025-09-01" -attachment = true -reasoning = false -temperature = true -tool_call = false -knowledge = "2025-09-01" -open_weights = false - -[cost] -input = 3.00 -output = 15.00 - -[limit] -context = 200_000 -output = 8_192 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/venice/README.md b/providers/venice/README.md index fc7c4efd5..315e52e50 100644 --- a/providers/venice/README.md +++ b/providers/venice/README.md @@ -16,13 +16,14 @@ The script can include alpha models when provided with a Venice API key with alp Key can be provided via: 1. CLI argument: `--api-key=YOUR_KEY` or `--api-key YOUR_KEY` 2. Environment variable: `VENICE_API_KEY` +3. Interactive prompt (press Enter to skip for public models only) Details - Source endpoint: `https://api.venice.ai/api/v1/models?type=text` - Output path: `providers/venice/models/.toml` - Merge behavior: Updates API-sourced fields, preserves manual fields - Dates: `release_date`/`last_updated` use `YYYY-MM-DD`; `knowledge` uses `YYYY-MM` -- Output limit: Sourced from `maxCompletionTokens` in the API response (falls back to `context / 4` if absent) +- Output limit: Calculated as `context / 4` Preserved Fields (manual input) - `family`: Inferred from model ID if not already set diff --git a/providers/venice/models/gemini-3-1-pro-preview.toml b/providers/venice/models/gemini-3-1-pro-preview.toml index 7e50ed171..836d335e3 100644 --- a/providers/venice/models/gemini-3-1-pro-preview.toml +++ b/providers/venice/models/gemini-3-1-pro-preview.toml @@ -6,7 +6,7 @@ tool_call = true structured_output = true temperature = true release_date = "2026-02-19" -last_updated = "2026-02-24" +last_updated = "2026-02-19" open_weights = false [cost] @@ -22,7 +22,7 @@ cache_read = 0.5 [limit] context = 1_000_000 -output = 65_000 +output = 250_000 [modalities] input = ["text", "image", "audio", "video"] diff --git a/providers/venice/models/openai-gpt-53-codex.toml b/providers/venice/models/openai-gpt-53-codex.toml deleted file mode 100644 index 35b33537f..000000000 --- a/providers/venice/models/openai-gpt-53-codex.toml +++ /dev/null @@ -1,23 +0,0 @@ -name = "GPT-5.3 Codex" -family = "gpt-codex" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true -release_date = "2026-02-24" -last_updated = "2026-02-25" -open_weights = false - -[cost] -input = 2.19 -output = 17.5 -cache_read = 0.219 - -[limit] -context = 400_000 -output = 131_072 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/providers/vercel/models/alibaba/qwen3.5-flash.toml b/providers/vercel/models/alibaba/qwen3.5-flash.toml deleted file mode 100644 index e5b481155..000000000 --- a/providers/vercel/models/alibaba/qwen3.5-flash.toml +++ /dev/null @@ -1,23 +0,0 @@ -name = "Qwen 3.5 Flash" -family = "qwen" -attachment = true -reasoning = true -tool_call = true -temperature = true -release_date = "2026-02-24" -last_updated = "2026-02-24" -open_weights = false - -[cost] -input = 0.1 -output = 0.4 -cache_read = 0.001 -cache_write = 0.125 - -[limit] -context = 1_000_000 -output = 64_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] diff --git a/providers/vercel/models/google/gemini-3.1-pro-preview.toml b/providers/vercel/models/google/gemini-3.1-pro-preview.toml deleted file mode 100644 index 964e9d4b1..000000000 --- a/providers/vercel/models/google/gemini-3.1-pro-preview.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Gemini 3.1 Pro Preview" -family = "gemini" -attachment = true -reasoning = true -tool_call = true -temperature = true -release_date = "2026-02-19" -last_updated = "2026-02-24" -open_weights = false - -[cost] -input = 2 -output = 12 -cache_read = 0.2 - -[limit] -context = 1_000_000 -output = 64_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] diff --git a/providers/vercel/models/openai/gpt-5.3-codex.toml b/providers/vercel/models/openai/gpt-5.3-codex.toml deleted file mode 100644 index 73a236bcb..000000000 --- a/providers/vercel/models/openai/gpt-5.3-codex.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "GPT 5.3 Codex" -family = "gpt" -attachment = true -reasoning = true -tool_call = true -temperature = true -release_date = "2026-02-24" -last_updated = "2026-02-24" -open_weights = false - -[cost] -input = 1.75 -output = 14 -cache_read = 0.175 - -[limit] -context = 400_000 -output = 128_000 - -[modalities] -input = ["text", "image", "pdf"] -output = ["text"] From 8d0b51c6e76dce259450257e9e71c7f619c71986 Mon Sep 17 00:00:00 2001 From: Fabio Suizu Date: Sat, 28 Feb 2026 10:58:01 -0300 Subject: [PATCH 2/3] fix: correct output limits for Claude, Nova models and Qwen3-80B open_weights MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Claude Opus 4.6: output 32K → 128K (matches all other providers) - Claude Haiku 4.5: output 8K → 64K (matches all other providers) - Nova Lite/Pro/Micro: output 5120 → 8192 (matches Vercel/Bedrock) - Qwen3-80B: open_weights false → true (model is open source) --- providers/brainiall/models/claude-haiku-4-5.toml | 2 +- providers/brainiall/models/claude-opus-4-6.toml | 2 +- providers/brainiall/models/nova-lite.toml | 2 +- providers/brainiall/models/nova-micro.toml | 2 +- providers/brainiall/models/nova-pro.toml | 2 +- providers/brainiall/models/qwen3-80b.toml | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) diff --git a/providers/brainiall/models/claude-haiku-4-5.toml b/providers/brainiall/models/claude-haiku-4-5.toml index 1a852d731..82f527d8e 100644 --- a/providers/brainiall/models/claude-haiku-4-5.toml +++ b/providers/brainiall/models/claude-haiku-4-5.toml @@ -18,7 +18,7 @@ cache_write = 1.25 [limit] context = 200_000 -output = 8_192 +output = 64_000 [modalities] input = ["text", "image", "pdf"] diff --git a/providers/brainiall/models/claude-opus-4-6.toml b/providers/brainiall/models/claude-opus-4-6.toml index 3ac6eba0f..a334a79af 100644 --- a/providers/brainiall/models/claude-opus-4-6.toml +++ b/providers/brainiall/models/claude-opus-4-6.toml @@ -24,7 +24,7 @@ cache_write = 12.50 [limit] context = 200_000 -output = 32_000 +output = 128_000 [modalities] input = ["text", "image", "pdf"] diff --git a/providers/brainiall/models/nova-lite.toml b/providers/brainiall/models/nova-lite.toml index 9907469de..8dd07bb08 100644 --- a/providers/brainiall/models/nova-lite.toml +++ b/providers/brainiall/models/nova-lite.toml @@ -17,7 +17,7 @@ cache_read = 0.015 [limit] context = 300_000 -output = 5_120 +output = 8_192 [modalities] input = ["text", "image", "video"] diff --git a/providers/brainiall/models/nova-micro.toml b/providers/brainiall/models/nova-micro.toml index 6678a50b6..566515620 100644 --- a/providers/brainiall/models/nova-micro.toml +++ b/providers/brainiall/models/nova-micro.toml @@ -17,7 +17,7 @@ cache_read = 0.00875 [limit] context = 128_000 -output = 5_120 +output = 8_192 [modalities] input = ["text"] diff --git a/providers/brainiall/models/nova-pro.toml b/providers/brainiall/models/nova-pro.toml index bcc58ea86..252fe9a7a 100644 --- a/providers/brainiall/models/nova-pro.toml +++ b/providers/brainiall/models/nova-pro.toml @@ -17,7 +17,7 @@ cache_read = 0.20 [limit] context = 300_000 -output = 5_120 +output = 8_192 [modalities] input = ["text", "image", "video"] diff --git a/providers/brainiall/models/qwen3-80b.toml b/providers/brainiall/models/qwen3-80b.toml index 531e439be..52238113c 100644 --- a/providers/brainiall/models/qwen3-80b.toml +++ b/providers/brainiall/models/qwen3-80b.toml @@ -5,7 +5,7 @@ family = "qwen" attachment = false reasoning = false tool_call = true -open_weights = false +open_weights = true structured_output = true temperature = true From 1f555f0a1d36bb4a82269125f298a1e4ce92b5e4 Mon Sep 17 00:00:00 2001 From: Fabio Suizu Date: Sat, 28 Feb 2026 11:29:09 -0300 Subject: [PATCH 3/3] fix: correct Devstral 2 output pricing to $1.60/MTok --- providers/brainiall/models/devstral-2.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/providers/brainiall/models/devstral-2.toml b/providers/brainiall/models/devstral-2.toml index 68893596b..70e6b3906 100644 --- a/providers/brainiall/models/devstral-2.toml +++ b/providers/brainiall/models/devstral-2.toml @@ -12,7 +12,7 @@ knowledge = "2025-12" [cost] input = 0.40 -output = 2.00 +output = 1.60 [limit] context = 262_144