diff --git a/README.md b/README.md
index e07d864..64ce9f8 100644
--- a/README.md
+++ b/README.md
@@ -96,7 +96,6 @@ Models share a common quota.
- [moonshotai/kimi-dev-72b:free](https://openrouter.ai/moonshotai/kimi-dev-72b:free)
- [moonshotai/kimi-k2:free](https://openrouter.ai/moonshotai/kimi-k2:free)
- [qwen/qwen3-14b:free](https://openrouter.ai/qwen/qwen3-14b:free)
-- [qwen/qwen3-235b-a22b-2507:free](https://openrouter.ai/qwen/qwen3-235b-a22b-2507:free)
- [qwen/qwen3-235b-a22b:free](https://openrouter.ai/qwen/qwen3-235b-a22b:free)
- [qwen/qwen3-30b-a3b:free](https://openrouter.ai/qwen/qwen3-30b-a3b:free)
- [qwen/qwen3-4b:free](https://openrouter.ai/qwen/qwen3-4b:free)
@@ -200,7 +199,6 @@ Free tier restricted to 8K context.
| Llama 3.3 70B | 1,000 requests/day
12,000 tokens/minute |
| Llama 4 Maverick 17B 128E Instruct | 1,000 requests/day
6,000 tokens/minute |
| Llama 4 Scout Instruct | 1,000 requests/day
30,000 tokens/minute |
-| Mistral Saba 24B | 1,000 requests/day
6,000 tokens/minute |
| Whisper Large v3 | 7,200 audio-seconds/minute
2,000 requests/day |
| Whisper Large v3 Turbo | 7,200 audio-seconds/minute
2,000 requests/day |
| meta-llama/llama-guard-4-12b | 14,400 requests/day
15,000 tokens/minute |
@@ -308,12 +306,12 @@ Data is sent to individual hosts.
- DeepHermes 3 Llama 3 8B Preview
- openbmb/minicpm4-8b
- qwen/qwen3-14b
-- qwen/qwen3-235b-a22b-instruct-2507
- qwen/qwen3-4b
- qwen/qwen3-8b
- tencent/hunyuan-a13b-instruct
- thudm/glm-4-32b-0414
- zai-org/glm-4.5-air
+- zai-org/glm-4.5-fp8
### [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai)
@@ -491,7 +489,6 @@ Very stringent payment verification for Google Cloud.
- Llama-4-Maverick-17B-128E-Instruct
- Qwen/Qwen3-32B
- Whisper-Large-v3
-- deepseek-ai/DeepSeek-R1
- deepseek-ai/DeepSeek-R1-0528
- deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- deepseek-ai/DeepSeek-V3-0324