Repository navigation
v2026.9.15
·
23 commits
to main
since this release
What changed
New providers (5)
- Ollama Cloud (
ollama-cloud) - Infer by Flow7 (
infer) - Melious (
melious) - Wallaby (
wallaby) - Vispark (
vispark)
New models (103)
- NanoGPT — Qwen3.7 Max (
qwen/qwen3.7-max) - NanoGPT — Qwen3 Next 80B A3B (Instruct) (
qwen/qwen3-next-80b-a3b-instruct) - NanoGPT — Qwen3.5 122B A10B Thinking (
qwen/qwen3.5-122b-a10b:thinking) - NanoGPT — Qwen 2.5 Max (
qwen/qwen-max) - NanoGPT — Qwen 3.6 Plus (
qwen/qwen3.6-plus) - NanoGPT — Qwen3.5 27B (
qwen/qwen3.5-27b) - NanoGPT — Qwen3.8 27B (
qwen/qwen3.8-27b) - NanoGPT — Qwen3.5 35B A3B (
qwen/qwen3.5-35b-a3b) - NanoGPT — Qwen Turbo (
qwen/qwen-turbo) - NanoGPT — Qwen3.7 Flash Thinking (
qwen/qwen3.7-flash:thinking) - NanoGPT — Qwen3.6 27B Thinking (
qwen/qwen3.6-27b:thinking) - NanoGPT — Qwen3.5 Flash Thinking (
qwen/qwen3.5-flash:thinking) - NanoGPT — Qwen3.5 Flash (
qwen/qwen3.5-flash) - NanoGPT — Qwen3 Coder 30B A3B Instruct (
qwen/qwen3-coder-30b-a3b-instruct) - NanoGPT — Qwen3.8 Max Thinking (
qwen/qwen3.8-max:thinking) - NanoGPT — Qwen3.7 Max Thinking (
qwen/qwen3.7-max:thinking) - NanoGPT — Qwen3.6 27B (
qwen/qwen3.6-27b) - NanoGPT — Qwen3.5 27B Thinking (
qwen/qwen3.5-27b:thinking) - NanoGPT — Qwen3.5 0.8B (
qwen/qwen3.5-0.8b) - NanoGPT — Qwen3.7 Flash (
qwen/qwen3.7-flash) - NanoGPT — Qwen3.6 35B A3B (
qwen/qwen3.6-35b-a3b) - NanoGPT — Qwen3.5 35B A3B Thinking (
qwen/qwen3.5-35b-a3b:thinking) - NanoGPT — Qwen3.8 Max 0902 (
qwen/qwen3.8-max-0902) - NanoGPT — Qwen3.5 Plus Thinking (
qwen/qwen3.5-plus:thinking) - NanoGPT — Qwen3.8 27B Thinking (
qwen/qwen3.8-27b:thinking) - NanoGPT — Qwen Plus (
qwen/qwen-plus) - NanoGPT — Qwen3.5 122B A10B (
qwen/qwen3.5-122b-a10b) - NanoGPT — Qwen3 30B A3B Instruct 2507 (
qwen/qwen3-30b-a3b-instruct-2507) - NanoGPT — Qwen3.7 Plus Thinking (
qwen/qwen3.7-plus:thinking) - NanoGPT — Qwen3.5 4B (
qwen/qwen3.5-4b) - NanoGPT — Qwen3.6 Flash (
qwen/qwen3.6-flash) - NanoGPT — Qwen3.8 Flash (
qwen/qwen3.8-flash) - NanoGPT — Qwen3.6 Max Preview (
qwen/qwen3.6-max-preview) - NanoGPT — Qwen3.8 Max (
qwen/qwen3.8-max) - NanoGPT — Qwen 3 8B (
qwen/qwen3-8b) - NanoGPT — Qwen3.5 397B A17B Thinking (
qwen/qwen3.5-397b-a17b:thinking) - NanoGPT — Qwen3 VL 235B A22B Thinking (
qwen/qwen3-vl-235b-a22b-thinking) - NanoGPT — Qwen3 VL 235B A22B Instruct (
qwen/qwen3-vl-235b-a22b-instruct) - NanoGPT — Qwen3.7 Plus (
qwen/qwen3.7-plus) - NanoGPT — Qwen 3 235b A22B 2507 (
qwen/qwen3-235b-a22b-instruct-2507) - NanoGPT — Qwen3.5 2B (
qwen/qwen3.5-2b) - NanoGPT — Qwen3.6 35B A3B Thinking (
qwen/qwen3.6-35b-a3b:thinking) - NanoGPT — Qwen Long 10M (
qwen/qwen-long) - NanoGPT — Qwen3 Max 2026-01-23 (
qwen/qwen3-max-2026-01-23) - NanoGPT — Qwen 2.5 Coder 32b (
qwen/qwen2.5-coder-32b-instruct) - NanoGPT — Mistral Small 3.2 24B (2506) (
mistralai/mistral-small-3.2-24b-instruct) - NanoGPT — Mistral Devstral Small 2505 (
mistralai/devstral-small-2505) - NanoGPT — Mistral Nemo (
mistralai/mistral-nemo-instruct-2407) - NanoGPT — Mistral Small 3.1 24B (2503) (
mistralai/mistral-small-3.1-24b-instruct) - NanoGPT — Mistral Medium 3.5 Thinking (
mistralai/mistral-medium-3.5:thinking) - NanoGPT — Mistral Medium 3.5 (
mistralai/mistral-medium-3.5) - NanoGPT — MiniMax M2 (
minimax/minimax-m2) - NanoGPT — Claude 4.1 Opus Thinking (8K) (
anthropic/claude-opus-4.1:thinking:8192) - NanoGPT — Claude 4 Opus Thinking (8K) (
anthropic/claude-opus-4:thinking:8192) - NanoGPT — Claude 4.1 Opus Thinking (32K) (
anthropic/claude-opus-4.1:thinking:32768) - NanoGPT — Claude 4 Sonnet Thinking (8K) (
anthropic/claude-sonnet-4:thinking:8192) - NanoGPT — Claude 4 Sonnet Thinking (1K) (
anthropic/claude-sonnet-4:thinking:1024) - NanoGPT — Claude 4 Opus Thinking (1K) (
anthropic/claude-opus-4:thinking:1024) - NanoGPT — Claude 4.1 Opus Thinking (1K) (
anthropic/claude-opus-4.1:thinking:1024) - NanoGPT — Claude 4.1 Opus (
anthropic/claude-opus-4.1) - NanoGPT — Claude Haiku 4.5 Thinking (
anthropic/claude-haiku-4.5:thinking) - NanoGPT — Claude 4 Opus Thinking (
anthropic/claude-opus-4:thinking) - NanoGPT — Claude 4.1 Opus Thinking (
anthropic/claude-opus-4.1:thinking) - NanoGPT — Claude Haiku 4.5 (
anthropic/claude-haiku-4.5) - NanoGPT — Claude 4 Sonnet Thinking (
anthropic/claude-sonnet-4:thinking) - NanoGPT — Claude 4 Sonnet Thinking (32K) (
anthropic/claude-sonnet-4:thinking:32768) - NanoGPT — Claude 4 Opus (
anthropic/claude-opus-4) - NanoGPT — Claude 4 Opus Thinking (32K) (
anthropic/claude-opus-4:thinking:32768) - NanoGPT — Claude Sonnet 4.5 (
anthropic/claude-sonnet-4.5) - NanoGPT — Claude 4 Sonnet Thinking (64K) (
anthropic/claude-sonnet-4:thinking:64000) - NanoGPT — Claude 4.5 Opus (
anthropic/claude-opus-4.5) - NanoGPT — Claude 4.5 Opus Thinking (
anthropic/claude-opus-4.5:thinking) - NanoGPT — Claude Sonnet 4.5 Thinking (
anthropic/claude-sonnet-4.5:thinking) - NanoGPT — Claude 4 Sonnet (
anthropic/claude-sonnet-4) - NanoGPT — DeepSeek V4.1 Flash TEE (
TEE/deepseek-v4.1-flash) - NanoGPT — Schematron V2 Small (
inference-net/schematron-v2-small) - NanoGPT — Schematron V2 Turbo (
inference-net/schematron-v2-turbo) - DigitalOcean — DeepSeek V4.1 Flash (
deepseek-v4.1-flash) - LLM Gateway — Atria Dawn Preview (Atria) (
atria/atria-dawn-preview) - LLM Gateway — DeepSeek V4.1 Flash (Alibaba Cloud) (
alibaba/deepseek-v4.1-flash) - CoralBricks — GLM 5.3 Flash FP4 (
glm-5.3-flash-fp4) - AKI.IO — GLM-5.3 (
glm5.3-754b) - Vercel AI Gateway — Seed 2.1 Turbo (
bytedance/seed-2.1-turbo) - Vercel AI Gateway — Fugu Max (
sakana/fugu-max) - Vercel AI Gateway — Fugu Ultra v2 (
sakana/fugu-ultra-v2) - Vercel AI Gateway — Ling 3.0 Flash VL (Free) (
inclusionai/ling-3.0-flash-vl-free) - Vercel AI Gateway — Ling 3.0 Flash VL (
inclusionai/ling-3.0-flash-vl) - Friendli — GLM-5.3-Flash (
zai-org/GLM-5.3-Flash) - DevPass (LLM Gateway) — Atria Dawn Preview (
atria-dawn-preview) - EmpirioLabs AI — DeepSeek V4.1 Flash (
deepseek-v4-1-flash) - Deep Infra — Qwen3.8 Flash (
Qwen/Qwen3.8-Flash) - Kilo Gateway — DeepSeek: DeepSeek Pro Latest (
~deepseek/deepseek-pro-latest) - Kilo Gateway — DeepSeek: DeepSeek Flash Latest (
~deepseek/deepseek-flash-latest) - OpenRouter — DeepSeek Pro Latest (
~deepseek/deepseek-pro-latest) - OpenRouter — DeepSeek Flash Latest (
~deepseek/deepseek-flash-latest) - AMD — Qwen3.8 27B (
Qwen3.8-27B) - AMD — MiniCPM5-2B (
MiniCPM5-2B) - AMD — DeepSeek V4.1 Flash (
DeepSeek-V4.1-Flash) - 302.AI — DeepSeek V4.1 Flash (
deepseek-flash) - Vancine — DeepSeek V4.1 Flash (
deepseek-flash) - Cortecs — DeepSeek V4.1 Flash (
deepseek-v4.1-flash) - Alibaba Token Plan (China) — DeepSeek V4.1 Flash (
deepseek-v4.1-flash) - Tinfoil — DeepSeek V4.1 Flash (
deepseek-v4-1-flash)
Removed models (105)
- NanoGPT — Claude 4 Opus Thinking (8K) (
claude-opus-4-thinking:8192) - NanoGPT — Qwen3.7 Max (
qwen3.7-max) - NanoGPT — Exa (Answer) (
exa-answer) - NanoGPT — MiniMax M2 (
MiniMax-M2) - NanoGPT — Claude 4 Sonnet Thinking (32K) (
claude-sonnet-4-thinking:32768) - NanoGPT — Qwen3.5 122B A10B Thinking (
qwen3.5-122b-a10b:thinking) - NanoGPT — Qwen 2.5 Max (
qwen-max) - NanoGPT — Qwen3.5 27B (
qwen3.5-27b) - NanoGPT — Claude 4.1 Opus Thinking (1K) (
claude-opus-4-1-thinking:1024) - NanoGPT — Qwen3.8 27B (
qwen3.8-27b) - NanoGPT — Qwen3.5 35B A3B (
qwen3.5-35b-a3b) - NanoGPT — Claude Haiku 4.5 Thinking (
claude-haiku-4-5-20251001-thinking) - NanoGPT — Qwen 3.6 Plus (
qwen-3.6-plus) - NanoGPT — Claude 4 Sonnet Thinking (8K) (
claude-sonnet-4-thinking:8192) - NanoGPT — Qwen Turbo (
qwen-turbo) - NanoGPT — Qwen3.7 Flash Thinking (
qwen3.7-flash:thinking) - NanoGPT — Qwen3.5 Omni Plus (
qwen3.5-omni-plus) - NanoGPT — Claude Sonnet 4.5 Thinking (
claude-sonnet-4-5-20250929-thinking) - NanoGPT — Claude 4.1 Opus (
claude-opus-4-1-20250805) - NanoGPT — Qwen25 VL 72b (
qwen25-vl-72b-instruct) - NanoGPT — Qwen3.5 Flash Thinking (
qwen3.5-flash:thinking) - NanoGPT — Claude 4 Opus Thinking (32K) (
claude-opus-4-thinking:32768) - NanoGPT — Qwen3.5 Flash (
qwen3.5-flash) - NanoGPT — Claude 4 Opus Thinking (
claude-opus-4-thinking) - NanoGPT — Brave (Research) (
brave-research) - NanoGPT — Qwen3 Coder 30B A3B Instruct (
qwen3-coder-30b-a3b-instruct) - NanoGPT — Qwen3.8 Max Thinking (
qwen3.8-max:thinking) - NanoGPT — Claude 4 Opus (
claude-opus-4-20250514) - NanoGPT — Perplexity Academic Researcher (
perplexity-academic-researcher) - NanoGPT — Claude 4 Sonnet Thinking (64K) (
claude-sonnet-4-thinking:64000) - NanoGPT — Qwen3.7 Max Thinking (
qwen3.7-max:thinking) - NanoGPT — Claude 4.5 Opus Thinking (
claude-opus-4-5-20251101:thinking) - NanoGPT — Qwen3.5 27B Thinking (
qwen3.5-27b:thinking) - NanoGPT — Qwen3.5 0.8B (
qwen3.5-0.8b) - NanoGPT — Claude Sonnet 4.5 (
claude-sonnet-4-5-20250929) - NanoGPT — Qwen3.7 Flash (
qwen3.7-flash) - NanoGPT — Qwen3.5 Omni Flash (
qwen3.5-omni-flash) - NanoGPT — Qwen3.5 35B A3B Thinking (
qwen3.5-35b-a3b:thinking) - NanoGPT — Claude 4 Sonnet Thinking (1K) (
claude-sonnet-4-thinking:1024) - NanoGPT — Claude Haiku 4.5 (
claude-haiku-4-5-20251001) - NanoGPT — Qwen3.8 27B Thinking (
qwen3.8-27b:thinking) - NanoGPT — Qwen Plus (
qwen-plus) - NanoGPT — Qwen3.5 122B A10B (
qwen3.5-122b-a10b) - NanoGPT — Perplexity Simple (
sonar) - NanoGPT — Claude 4 Sonnet Thinking (
claude-sonnet-4-thinking) - NanoGPT — Perplexity Reasoning Pro (
sonar-reasoning-pro) - NanoGPT — Qwen3 30B A3B Instruct 2507 (
qwen3-30b-a3b-instruct-2507) - NanoGPT — Qwen3.7 Plus Thinking (
qwen3.7-plus:thinking) - NanoGPT — Claude 4.1 Opus Thinking (
claude-opus-4-1-thinking) - NanoGPT — Qwen3.5 4B (
qwen3.5-4b) - NanoGPT — Claude 4.1 Opus Thinking (32K) (
claude-opus-4-1-thinking:32768) - NanoGPT — Mistral Small 31 24b Instruct (
mistral-small-31-24b-instruct) - NanoGPT — Qwen3.6 Max Preview (
qwen3.6-max-preview) - NanoGPT — Claude 4 Opus Thinking (1K) (
claude-opus-4-thinking:1024) - NanoGPT — Qwen3.8 Max (
qwen3.8-max) - NanoGPT — Qwen3 VL 235B A22B Thinking (
qwen3-vl-235b-a22b-thinking) - NanoGPT — Qwen3.7 Plus (
qwen3.7-plus) - NanoGPT — Brave (Pro) (
brave-pro) - NanoGPT — Perplexity Pro (
sonar-pro) - NanoGPT — Qwen3.5 2B (
qwen3.5-2b) - NanoGPT — Perplexity Deep Research (
sonar-deep-research) - NanoGPT — Claude 4 Sonnet (
claude-sonnet-4-20250514) - NanoGPT — Qwen Long 10M (
qwen-long) - NanoGPT — Qwen3 Max 2026-01-23 (
qwen3-max-2026-01-23) - NanoGPT — Brave (Answers) (
brave) - NanoGPT — Claude 4.1 Opus Thinking (8K) (
claude-opus-4-1-thinking:8192) - NanoGPT — Claude 4.5 Opus (
claude-opus-4-5-20251101) - NanoGPT — Qwen3.5 397B A17B Thinking (
qwen/qwen3.5-397b-a17b-thinking) - NanoGPT — Qwen 3 8B (
qwen/Qwen3-8B) - NanoGPT — Qwen3.5 Plus Thinking (
qwen/qwen3.5-plus-thinking) - NanoGPT — Qwen 3 235b A22B 2507 (
qwen/Qwen3-235B-A22B-Instruct-2507) - NanoGPT — Qwen3 VL 235B A22B Instruct (
qwen/Qwen3-VL-235B-A22B-Instruct) - NanoGPT — Qwen3 Next 80B A3B (Instruct) (
qwen/Qwen3-Next-80B-A3B-Instruct) - NanoGPT — Qwen3.8 2.4T A95B (Max) (
qwen/qwen3.8-2.4t-a95b) - NanoGPT — Qwen 3 235b A22B 2507 Thinking (
qwen/Qwen3-235B-A22B-Thinking-2507) - NanoGPT — Qwen3.6 35B A3B (
qwen/Qwen3.6-35B-A3B) - NanoGPT — Qwen3.6 35B A3B Thinking (
qwen/Qwen3.6-35B-A3B:thinking) - NanoGPT — Qwen 2.5 Coder 32b (
qwen/Qwen2.5-Coder-32B-Instruct) - NanoGPT — Mistral Small 3.2 24b Instruct (
chutesai/Mistral-Small-3.2-24B-Instruct-2506) - NanoGPT — Mistral Devstral Small 2505 (
mistralai/Devstral-Small-2505) - NanoGPT — Mistral Nemo (
mistralai/Mistral-Nemo-Instruct-2407) - NanoGPT — MiMo V2.5 Pro (Crof) (
xiaomi/mimo-v2.5-pro-crof) - NanoGPT — MiMo V2.5 Pro Thinking (Crof) (
xiaomi/mimo-v2.5-pro-crof:thinking) - NanoGPT — Qwen3.6 27B Thinking (
alibaba/qwen3.6-27b:thinking) - NanoGPT — Qwen3.6 27B (
alibaba/qwen3.6-27b) - NanoGPT — Qwen3.8 Max 0902 (
alibaba/qwen3.8-max-0902) - NanoGPT — Qwen3.6 Flash (
alibaba/qwen3.6-flash) - NanoGPT — Qwen3.8 Flash (
alibaba/qwen3.8-flash) - NanoGPT — Greg 2 Super (
crofai/greg-2-super) - NanoGPT — Greg 2 Ultra (
crofai/greg-2-ultra) - NanoGPT — Qwen3 8B TEE (
TEE/qwen3-8b) - NanoGPT — Mistral Medium 3.5 Thinking (
mistral/mistral-medium-3.5:thinking) - NanoGPT — Mistral Medium 3.5 (
mistral/mistral-medium-3.5) - LLM Gateway — GPT OSS 20B (Together AI) (
together-ai/gpt-oss-20b) - LLM Gateway — Gemma 4 31B IT (Together AI) (
together-ai/gemma-4-31b-it) - AKI.IO — Kimi K2.7 Code (
kimi-k2.7-code-1100b) - Vercel AI Gateway — Qwen 3.8 Flash Next (
alibaba/qwen3.8-flash-next) - Kilo Gateway — Google: Gemini 2.5 Pro Preview 05-06 (
google/gemini-2.5-pro-preview-05-06) - Kilo Gateway — OpenAI: GPT-4 Turbo Preview ($$$$) (
openai/gpt-4-turbo-preview) - OpenRouter — Gemini 2.5 Pro Preview 05-06 (
google/gemini-2.5-pro-preview-05-06) - OpenRouter — GPT-4 Turbo Preview (
openai/gpt-4-turbo-preview) - AMD — MiniCPM5-1B (
MiniCPM5-1B) - Vancine — DeepSeek V4 Flash Vision Exp (
deepseek-v4-flash-vision-exp) - Vancine — DeepSeek V4 Flash (
deepseek-v4-flash) - Vancine — DeepSeek V4 Pro (
deepseek-v4-pro)
Price changes (58)
- NanoGPT — DeepSeek V4 Flash Vision Exp: input $0.22 → $0.44, output $0.66 → $1.32
- NanoGPT — DeepSeek V4.1 Flash: input $0.15 → $0.1, output $0.6 → $0.4
- NanoGPT — DeepSeek V4.1 Flash Thinking: input $0.15 → $0.1, output $0.6 → $0.4
- NanoGPT — GLM 5.3 Flash Uncensored: input $0.35 → $0.2, output $1.4 → $0.8
- LLM Gateway — GLM-5.2 (SCX.ai): input $0.8 → $0.88
- LLM Gateway — DeepSeek V4.1 Flash (Consensus Protocol): output $1 → $0.6
- Charm Hyper — Gemma 4 26B A4B IT: input $0.102 → $0.1, output $0.356 → $0.374
- Charm Hyper — MiniMax-M2.7: input $0.396 → $0.462, output $1.464 → $1.728
- Charm Hyper — DeepSeek V4.1 Flash: input $0.3 → $0.3266, output $1.2 → $1.307
- Charm Hyper — GLM-5: input $0.86 → $0.94, output $2.752 → $3.008
- Charm Hyper — Kimi K2.5: input $0.5584 → $0.5344, output $2.935 → $2.815
- Charm Hyper — GLM-5.1: output $4.308 → $4.268
- Charm Hyper — GPT OSS 120B: input $0.168 → $0.178, output $0.66 → $0.68
- Vercel AI Gateway — Qwen 3.8 Flash: input $0.16 → $0.15
- Vercel AI Gateway — Qwen 3.5 Plus: output $2.4 → $2.5
- Vercel AI Gateway — Nemotron 3 Nano 30B A3B: output $0.24 → $0.2
- Vercel AI Gateway — DeepSeek V4.1 Flash: input $0.3 → $0.15, output $1.2 → $0.6
- Vercel AI Gateway — Ling 3.0 Flash: input $0.06 → $0.021, output $0.18 → $0.063
- Weights & Biases — Nemotron 3 Ultra: input $0.75 → $0.5, output $2.75 → $2.15
- Weights & Biases — Nemotron 3.5 Lightning: input $0.1 → $0.07, output $0.25 → $0.2
- Friendli — GLM-5.3: input $1.4 → $1.26, output $4.4 → $3.96
- Deep Infra — Qwen3.8 27B: input $0.4 → $0.2, output $3 → $2.5
- Kilo Gateway — DeepSeek: DeepSeek V4 Flash Latest: input $0.0352 → $0.04, output $0.1056 → $0.1
- Kilo Gateway — MoonshotAI: Kimi Latest: input $2.1 → $1.875, output $10.95 → $10.5
- Kilo Gateway — Meta: Llama 4 Maverick: input $0.2 → $0.1875, output $0.696 → $0.6525
- Kilo Gateway — Z.ai: GLM Latest: input $0.92 → $0.8775, output $3.137 → $2.97
- Merge Gateway — DeepSeek V4 Pro 0813: input $0.66 → $1.74, output $1.98 → $3.48
- Merge Gateway — DeepSeek V4 Pro: input $0.66 → $1.74, output $1.98 → $3.48
- OpenRouter — Qwen3.5 35B-A3B: input $0.3125 → $0.1625, output $1.25 → $1.3
- OpenRouter — DeepSeek V4 Flash Latest: input $0.0352 → $0.04, output $0.1056 → $0.1
- OpenRouter — Nemotron 3 Super 120B A12B: input $0.085 → $0.08, output $0.4 → $0.45
- OpenRouter — Kimi Latest: input $2.1 → $1.875, output $10.95 → $10.5
- OpenRouter — DeepSeek V4 Flash 0731: input $0.06 → $0.055, output $0.12 → $0.11
- OpenRouter — Llama 4 Maverick: input $0.2 → $0.1875, output $0.696 → $0.6525
- OpenRouter — GLM Latest: input $0.92 → $0.8775, output $3.137 → $2.97
- OpenRouter — GLM-5.2: input $0.6832 → $1.4, output $2.147 → $4.4
- Vancine — GLM-5.3-Flash: input $0.06 → $0.12, output $0.2 → $0.4
- Cortecs — ministral-14b-2512: input $0.223 → $0.24, output $0.223 → $0.24
- Cortecs — Codestral 2508: input $0.334 → $0.368, output $1.003 → $1.103
- Cortecs — Mistral Large 3: input $0.557 → $0.613, output $1.671 → $1.838
- Cortecs — ministral-3b-2512: input $0.111 → $0.123, output $0.111 → $0.123
- Cortecs — Mistral Small 4: input $0.143 → $0.156, output $0.568 → $0.625
- Cortecs — ministral-8b-2512: input $0.167 → $0.179, output $0.167 → $0.179
- Cortecs — mistral-medium-3.5: input $1.393 → $1.532, output $7.13 → $7.843
- Cortecs — voxtral-small-2507: input $0.111 → $0.123, output $0.334 → $0.368
- Eden AI — DeepSeek V4 Pro 0813 (Alibaba): input $1.122 → $0.66, output $3.366 → $1.98
- Eden AI — DeepSeek V4 Flash 0731 (Alibaba): input $0.352 → $0.22, output $1.056 → $0.66
- Eden AI — DeepSeek V4.1 Flash (Alibaba): input $0.3 → $0.15, output $1.2 → $0.6
- Eden AI — DeepSeek V4 Flash 0731 (Scaleway): input $0.4637 → $0.462, output $0.9274 → $0.9241
- Eden AI — GPT OSS 120B (Scaleway): input $0.1739 → $0.1733, output $0.6955 → $0.6931
- Eden AI — Llama-3.3-70B-Instruct (Scaleway): input $1.043 → $1.04, output $1.043 → $1.04
- Eden AI — Ministral 3 14B (Infomaniak): input $0.3478 → $0.3465, output $0.4637 → $0.462
- Eden AI — DeepSeek V4 Flash Vision Exp: input $0.22 → $0.15, output $0.66 → $0.6
- Eden AI — DeepSeek V4 Flash: input $0.44 → $0.15, output $1.32 → $0.6
- Eden AI — DeepSeek Chat: input $0.28 → $0.15, output $0.42 → $0.6
- Eden AI — DeepSeek V4 Pro: input $1.32 → $0.66, output $3.96 → $1.98
- Eden AI — Llama-3.3-70B-Instruct (IONOS): input $0.7535 → $0.7508, output $0.7535 → $0.7508
- Eden AI — GPT OSS 120B (IONOS): input $0.1739 → $0.1733, output $0.7535 → $0.7508