Skip to content

Commit 2709e7e

Browse files
SebConejoSebConejo
authored
Merge pull request #29 from mnfst/feat/detailed-model-tables
Add detailed model tables for all providers
2 parents a0774e9 + 7ce016a commit 2709e7e

File tree

4 files changed

+1355
-22
lines changed

4 files changed

+1355
-22
lines changed

‎.github/workflows/generate-readme.yml‎

Lines changed: 26 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,26 @@
1+
name: Generate README
2+
3+
on:
4+
push:
5+
branches: [main]
6+
paths: ['data.json']
7+
8+
jobs:
9+
generate:
10+
runs-on: ubuntu-latest
11+
permissions:
12+
contents: write
13+
steps:
14+
- uses: actions/checkout@v4
15+
- uses: actions/setup-node@v4
16+
with:
17+
node-version: '20'
18+
- name: Generate README
19+
run: node scripts/generate-readme.js
20+
- name: Commit changes
21+
run: |
22+
git config user.name "github-actions[bot]"
23+
git config user.email "github-actions[bot]@users.noreply.github.com"
24+
git add README.md
25+
git diff --staged --quiet || git commit -m "docs: regenerate README from data.json"
26+
git push

‎README.md‎

Lines changed: 233 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -22,38 +22,249 @@
2222

2323
APIs run by the companies that train or fine-tune the models themselves.
2424

25-
- [Cohere](https://dashboard.cohere.com/api-keys) 🇺🇸 - Command A, Command R+, Aya Expanse 32B +9 more. 20 RPM, 1K/mo.
26-
- [Google Gemini](https://aistudio.google.com/app/apikey) 🇺🇸 - Gemini 2.5 Pro, Flash, Flash-Lite +4 more. 5-15 RPM, 100-1K RPD. [^1]
27-
- [Mistral AI](https://console.mistral.ai/api-keys) 🇪🇺 - Mistral Large 3, Small 3.1, Ministral 8B +3 more. 1 req/s, 1B tok/mo.
28-
- [Zhipu AI](https://open.bigmodel.cn/usercenter/apikeys) 🇨🇳 - GLM-4.7-Flash, GLM-4.5-Flash, GLM-4.6V-Flash. Limits undocumented.
25+
### [Cohere](https://dashboard.cohere.com/api-keys) 🇨🇦
26+
27+
Free "Trial" API key, no credit card. 1,000 API calls/month. Non-commercial use only.
28+
29+
| Model Name | Context | Max Output | Modality | Rate Limit |
30+
|---|---|---|---|---|
31+
| Command A (111B) | 256K | 4K | Text | 20 RPM |
32+
| Command R+ | 128K | 4K | Text | 20 RPM |
33+
| Command R | 128K | 4K | Text | 20 RPM |
34+
| Command R7B | 128K | 4K | Text | 20 RPM |
35+
| Embed 4 | — | — | Embeddings (Text + Image) | 2,000 inputs/min |
36+
| Rerank 3.5 | — | — | Reranking | 10 RPM |
37+
38+
### [Google Gemini](https://aistudio.google.com/app/apikey) 🇺🇸
39+
40+
Free tier unavailable in EU/UK/Switzerland. Free-tier prompts may be used by Google to improve products. [^1]
41+
42+
| Model Name | Context | Max Output | Modality | Rate Limit |
43+
|---|---|---|---|---|
44+
| Gemini 2.5 Flash | 1M | 65K | Text + Image + Audio + Video | 10 RPM, 250 RPD |
45+
| Gemini 2.5 Flash-Lite | 1M | 65K | Text + Image + Audio + Video | 15 RPM, 1,000 RPD |
46+
47+
### [Mistral AI](https://console.mistral.ai/api-keys) 🇫🇷
48+
49+
Free "Experiment" plan, no credit card. ~1B tokens/month.
50+
51+
| Model Name | Context | Max Output | Modality | Rate Limit |
52+
|---|---|---|---|---|
53+
| Mistral Small 4 | 256K | 256K | Text + Image + Code | ~1 RPS, 500K TPM |
54+
| Mistral Medium 3 | 128K | 128K | Text | ~1 RPS, 500K TPM |
55+
| Mistral Large 3 | 256K | 256K | Text | ~1 RPS, 500K TPM |
56+
| Mistral Nemo (12B) | 128K | 128K | Text | ~1 RPS, 500K TPM |
57+
| Codestral | 256K | 256K | Code | ~1 RPS, 500K TPM |
58+
| Pixtral Large | 128K | 128K | Text + Image | ~1 RPS, 500K TPM |
59+
60+
### [Z AI (Zhipu AI)](https://open.bigmodel.cn/usercenter/apikeys) 🇨🇳
61+
62+
Permanent free models, no credit card required.
63+
64+
| Model Name | Context | Max Output | Modality | Rate Limit |
65+
|---|---|---|---|---|
66+
| GLM-4.7-Flash | 200K | 128K | Text | 1 concurrent request |
67+
| GLM-4.5-Flash | 128K | ~8K | Text | 1 concurrent request |
68+
| GLM-4.6V-Flash | 128K | ~4K | Text + Image | 1 concurrent request |
2969

3070
## Inference providers
3171

3272
Third-party platforms that host open-weight models from various sources.
3373

34-
- [Cerebras](https://cloud.cerebras.ai/) 🇺🇸 - Llama 3.3 70B, Qwen3 235B, GPT-OSS-120B +3 more. 30 RPM, 14,400 RPD.
35-
- [Cloudflare Workers AI](https://dash.cloudflare.com/profile/api-tokens) 🇺🇸 - Llama 3.3 70B, Qwen QwQ 32B +47 more. 10K neurons/day.
36-
- [GitHub Models](https://github.com/marketplace/models) 🇺🇸 - GPT-4o, Llama 3.3 70B, DeepSeek-R1 +more. 10-15 RPM, 50-150 RPD.
37-
- [Groq](https://console.groq.com/keys) 🇺🇸 - Llama 3.3 70B, Llama 4 Scout, Kimi K2 +17 more. 30 RPM, 1K RPD (14,400 for Llama 3.1 8B). [^3]
38-
- [Hugging Face](https://huggingface.co/settings/tokens) 🇺🇸 - Llama 3.3 70B, Qwen2.5 72B, Mistral 7B +many more. $0.10/mo in free credits.
39-
- [Kluster AI](https://platform.kluster.ai/apikeys) 🇺🇸 - DeepSeek-R1, Llama 4 Maverick, Qwen3-235B +2 more. Limits undocumented.
40-
- [LLM7.io](https://token.llm7.io) 🇬🇧 - DeepSeek R1, Flash-Lite, Qwen2.5 Coder +27 more. 30 RPM (120 with token).
41-
- [NVIDIA NIM](https://build.nvidia.com/explore/discover) 🇺🇸 - Llama 3.3 70B, Mistral Large, Qwen3 235B +more. 40 RPM.
42-
- [Ollama Cloud](https://ollama.com/settings/keys) 🇺🇸 - DeepSeek-V3.2, Qwen3.5, Kimi-K2.5 +17 more. 1 concurrent model, light usage. [^2]
43-
- [OpenRouter](https://openrouter.ai/keys) 🇺🇸 - DeepSeek R1, Llama 3.3 70B, GPT-OSS-120B +29 more. 20 RPM, 50 RPD (1K with $10+ in purchased credits). [^4]
44-
- [SiliconFlow](https://cloud.siliconflow.cn/account/ak) 🇨🇳 - Qwen3-8B, DeepSeek-R1-Distill-Qwen-7B, GLM-4.1V-9B-Thinking +10 more. 1K RPM, 50K TPM.
74+
### [Cerebras](https://cloud.cerebras.ai/) 🇺🇸
75+
76+
Free tier, no credit card. Ultra-fast inference (~2,600 tok/s). 1M tokens/day cap.
77+
78+
| Model Name | Context | Max Output | Modality | Rate Limit |
79+
|---|---|---|---|---|
80+
| llama3.1-8b | 128K (8K on free) | 8K | Text | 30 RPM, 14,400 RPD, 1M TPD |
81+
| gpt-oss-120b | 128K (8K on free) | 8K | Text | 30 RPM, 14,400 RPD, 1M TPD |
82+
| qwen-3-235b-a22b-instruct-2507 | 131K (8K on free) | 8K | Text | 30 RPM, 14,400 RPD, 1M TPD |
83+
| zai-glm-4.7 | 128K (8K on free) | 8K | Text | 10 RPM, 100 RPD, 1M TPD |
84+
85+
### [Cloudflare Workers AI](https://dash.cloudflare.com/profile/api-tokens) 🇺🇸
86+
87+
10,000 Neurons/day free. 50+ models available on free tier.
88+
89+
| Model Name | Context | Max Output | Modality | Rate Limit |
90+
|---|---|---|---|---|
91+
| @cf/meta/llama-3.3-70b-instruct-fp8-fast | 131K | Shared w/ context | Text | 10K neurons/day (shared) |
92+
| @cf/meta/llama-3.1-8b-instruct-fp8-fast | 131K | Shared w/ context | Text | 10K neurons/day (shared) |
93+
| @cf/meta/llama-3.2-11b-vision-instruct | 131K | Shared w/ context | Text + Vision | 10K neurons/day (shared) |
94+
| @cf/meta/llama-4-scout-17b-16e-instruct | Up to 10M | Shared w/ context | Multimodal | 10K neurons/day (shared) |
95+
| @cf/mistralai/mistral-small-3.1-24b-instruct | 128K | Shared w/ context | Text | 10K neurons/day (shared) |
96+
| @cf/google/gemma-4-26b-a4b-it | 256K | Shared w/ context | Text | 10K neurons/day (shared) |
97+
| @cf/qwen/qwq-32b | 32K | Shared w/ context | Text | 10K neurons/day (shared) |
98+
| @cf/deepseek-ai/deepseek-r1-distill-qwen-32b | 32K | Shared w/ context | Text | 10K neurons/day (shared) |
99+
| + 42 more models | Varies | Varies | Text, Image, Audio, Embeddings | 10K neurons/day (shared) |
100+
101+
### [GitHub Models](https://github.com/marketplace/models) 🇺🇸
102+
103+
Free prototyping for all GitHub users. 45+ models. Per-request limits (8K in / 4K out).
104+
105+
| Model Name | Context | Max Output | Modality | Rate Limit |
106+
|---|---|---|---|---|
107+
| gpt-4.1 | 1M | 32K | Text | 10 RPM, 50 RPD |
108+
| gpt-4.1-mini | 1M | 32K | Text | 15 RPM, 150 RPD |
109+
| gpt-4o | 128K | 16K | Text + Vision | 10 RPM, 50 RPD |
110+
| o3-mini | 200K | 100K | Text (reasoning) | 10 RPM, 50 RPD |
111+
| o4-mini | 200K | 100K | Text (reasoning) | 10 RPM, 50 RPD |
112+
| Llama-4-Scout-17B-16E | 512K | ~4K | Text + Vision | 15 RPM, 150 RPD |
113+
| Llama-4-Maverick-17B-128E | 256K | ~4K | Text + Vision | 10 RPM, 50 RPD |
114+
| Meta-Llama-3.3-70B | 131K | ~4K | Text | 15 RPM, 150 RPD |
115+
| DeepSeek-R1 | 64K | 8K | Text (reasoning) | 15 RPM, 150 RPD |
116+
| Mistral-Small-3.1 | 128K | ~4K | Text + Vision | 15 RPM, 150 RPD |
117+
| + 35 more models | Varies | Varies | Text / Image | Varies by tier |
118+
119+
### [Groq](https://console.groq.com/keys) 🇺🇸
120+
121+
Free tier, no credit card. Ultra-fast LPU inference. [^2]
122+
123+
| Model Name | Context | Max Output | Modality | Rate Limit |
124+
|---|---|---|---|---|
125+
| llama-3.3-70b-versatile | 131K | 32K | Text | 30 RPM, 14,400 RPD |
126+
| llama-3.1-8b-instant | 131K | 131K | Text | 30 RPM, 14,400 RPD |
127+
| llama-4-scout-17b-16e-instruct | 131K | 8K | Text + Vision | 30 RPM, 14,400 RPD |
128+
| llama-4-maverick-17b-128e-instruct | 131K | 8K | Text + Vision | 15 RPM, 500 RPD |
129+
| qwen3-32b | 131K | 131K | Text | 30 RPM, 14,400 RPD |
130+
| gpt-oss-120b | 131K | 32K | Text | 30 RPM, 14,400 RPD |
131+
| kimi-k2-instruct | 262K | 262K | Text | 30 RPM, 14,400 RPD |
132+
| deepseek-r1-distill-70b | 131K | 8K | Text | 30 RPM, 14,400 RPD |
133+
| whisper-large-v3 | — | — | Audio → Text | 20 RPM, 2,000 RPD |
134+
| whisper-large-v3-turbo | — | — | Audio → Text | 20 RPM, 2,000 RPD |
135+
136+
### [Hugging Face](https://huggingface.co/settings/tokens) 🇺🇸
137+
138+
Free Serverless Inference API + ~$0.10/month free credits. Thousands of models.
139+
140+
| Model Name | Context | Max Output | Modality | Rate Limit |
141+
|---|---|---|---|---|
142+
| Meta-Llama-3.1-8B-Instruct | 128K | ~4K | Text | ~1,000 RPD |
143+
| Mistral-7B-Instruct-v0.3 | 32K | ~4K | Text | ~1,000 RPD |
144+
| Mixtral-8x7B-Instruct-v0.1 | 32K | ~4K | Text | ~1,000 RPD |
145+
| Phi-3.5-mini-instruct | 128K | ~4K | Text | ~1,000 RPD |
146+
| Qwen2.5-7B-Instruct | 131K | ~4K | Text | ~1,000 RPD |
147+
| + thousands of community models | Varies | Varies | Text, Image, Audio, Embeddings | ~$0.10/month free credits |
148+
149+
### [Kilo Code](https://kilo.ai) 🇺🇸
150+
151+
Free models with no credit card required. ~29 rotating free models. Base URL: `https://api.kilo.ai/api/gateway`. [^5]
152+
153+
| Model Name | Context | Max Output | Modality | Rate Limit |
154+
|---|---|---|---|---|
155+
| qwen/qwen3.6-plus-preview:free | 1M | 32K | Text + Image + Video | ~200 req/hr |
156+
| nvidia/nemotron-3-super-120b-a12b:free | 262K | 32K | Text | ~200 req/hr |
157+
| stepfun/step-3.5-flash:free | 256K | 65K | Text | ~200 req/hr |
158+
| corethink:free | ~78K | ~8K | Text | ~200 req/hr |
159+
| minimax/minimax-m2.5:free | 196K | 196K | Text | ~200 req/hr |
160+
| arcee-ai/trinity-large-preview:free | 128K | ~32K | Text | ~200 req/hr |
161+
| kwaipilot/kat-coder-pro:free | 262K | 128K | Text (code) | ~200 req/hr |
162+
| qwen/qwen3-coder:free | 262K | 262K | Text (code) | ~200 req/hr |
163+
| google/gemma-4-31b-it:free | 262K | — | Multimodal | ~200 req/hr |
164+
| deepseek/deepseek-r1-0528:free | — | — | Text (reasoning) | ~200 req/hr |
165+
| meta-llama/llama-3.3-70b-instruct:free | — | — | Text | ~200 req/hr |
166+
| + ~18 more rotating free models | Varies | Varies | Text / Image | ~200 req/hr |
167+
168+
### [LLM7.io](https://token.llm7.io) 🇬🇧
169+
170+
Zero-friction API gateway. No registration needed for basic access. 30+ models.
171+
172+
| Model Name | Context | Max Output | Modality | Rate Limit |
173+
|---|---|---|---|---|
174+
| deepseek-r1-0528 | — | — | Text (reasoning) | 30 RPM (120 with token) |
175+
| deepseek-v3-0324 | — | — | Text | 30 RPM (120 with token) |
176+
| gemini-2.5-flash-lite | — | — | Text + Vision | 30 RPM (120 with token) |
177+
| gpt-4o-mini | — | — | Text + Vision | 30 RPM (120 with token) |
178+
| mistral-small-3.1-24b | 32K | — | Text | 30 RPM (120 with token) |
179+
| qwen2.5-coder-32b | — | — | Text (code) | 30 RPM (120 with token) |
180+
| + ~24 more models | Varies | Varies | Text | 30 RPM (120 with token) |
181+
182+
### [NVIDIA NIM](https://build.nvidia.com/explore/discover) 🇺🇸
183+
184+
Free with NVIDIA Developer Program membership. 100+ models. No daily token cap.
185+
186+
| Model Name | Context | Max Output | Modality | Rate Limit |
187+
|---|---|---|---|---|
188+
| deepseek-ai/deepseek-r1 | 128K | ~163K | Text (reasoning) | ~40 RPM |
189+
| nvidia/llama-3.1-nemotron-ultra-253b-v1 | 128K | 4K | Text | ~40 RPM |
190+
| nvidia/nemotron-3-super-120b-a12b | 262K | 262K | Text | ~40 RPM |
191+
| nvidia/nemotron-3-nano-30b-a3b | 128K | 32K | Text | ~40 RPM |
192+
| meta/llama-3.1-405b-instruct | 128K | 4K | Text | ~40 RPM |
193+
| qwen/qwen2.5-72b-instruct | 128K | 8K | Text | ~40 RPM |
194+
| google/gemma-4-31b | 128K | 8K | Text | ~40 RPM |
195+
| mistralai/mistral-large-2-instruct | 128K | 4K | Text | ~40 RPM |
196+
| nvidia/nemotron-nano-2-vl | 128K | 8K | Vision + Text + Video | ~40 RPM |
197+
| minimax/minimax-m2.7 | 128K | 8K | Text | ~40 RPM |
198+
| + 90 more models | Varies | Varies | Text, Image, Video, Speech, Embeddings | ~40 RPM |
199+
200+
### [Ollama Cloud](https://ollama.com/settings/keys) 🇺🇸
201+
202+
Free tier with qualitative usage limits. 400+ models from Ollama library. Not OpenAI SDK-compatible; uses [Ollama API](https://docs.ollama.com/cloud). [^3]
203+
204+
| Model Name | Context | Max Output | Modality | Rate Limit |
205+
|---|---|---|---|---|
206+
| llama3.1:cloud | 128K | Model-dependent | Text | Session/weekly limits (unpublished) |
207+
| deepseek-r1:cloud | 128K | Model-dependent | Text (reasoning) | Session/weekly limits (unpublished) |
208+
| qwen2.5:cloud | 128K | Model-dependent | Text | Session/weekly limits (unpublished) |
209+
| gemma2:cloud | 8K | Model-dependent | Text | Session/weekly limits (unpublished) |
210+
| mistral:cloud | 32K | Model-dependent | Text | Session/weekly limits (unpublished) |
211+
| + 400 more models | Varies | Varies | Text | Session/weekly limits (unpublished) |
212+
213+
### [OpenRouter](https://openrouter.ai/keys) 🇺🇸
214+
215+
35+ free models (marked with `:free` suffix). OpenAI SDK-compatible. [^4]
216+
217+
| Model Name | Context | Max Output | Modality | Rate Limit |
218+
|---|---|---|---|---|
219+
| deepseek/deepseek-r1-0528:free | 163K | ~163K | Text (reasoning) | 20 RPM, 200 RPD |
220+
| deepseek/deepseek-chat-v3-0324:free | 163K | 163K | Text | 20 RPM, 200 RPD |
221+
| qwen/qwen3.6-plus:free | 1M | 65K | Text | 20 RPM, 200 RPD |
222+
| qwen/qwen3-coder-480b-a35b:free | 262K | ~32K | Text | 20 RPM, 200 RPD |
223+
| meta-llama/llama-4-scout:free | 10M | 16K | Multimodal | 20 RPM, 200 RPD |
224+
| meta-llama/llama-4-maverick:free | 1M | 16K | Multimodal | 20 RPM, 200 RPD |
225+
| meta-llama/llama-3.3-70b-instruct:free | 65K | ~16K | Text | 20 RPM, 200 RPD |
226+
| google/gemma-4-31b-it:free | 256K | ~8K | Multimodal | 20 RPM, 200 RPD |
227+
| nvidia/nemotron-3-super-120b-a12b:free | 1M | ~32K | Text | 20 RPM, 200 RPD |
228+
| openai/gpt-oss-120b:free | 131K | 131K | Text | 20 RPM, 200 RPD |
229+
| minimax/minimax-m2.5:free | 196K | 8K | Text | 20 RPM, 200 RPD |
230+
| mistralai/devstral-2512:free | 256K | ~32K | Text | 20 RPM, 200 RPD |
231+
| + ~23 more free models | Varies | Varies | Text / Image | 20 RPM, 200 RPD |
232+
233+
### [SiliconFlow](https://cloud.siliconflow.cn/account/ak) 🇨🇳
234+
235+
Free tier with 14 CNY signup credits. Permanently free models available.
236+
237+
| Model Name | Context | Max Output | Modality | Rate Limit |
238+
|---|---|---|---|---|
239+
| Qwen/Qwen3-8B | 131K | 131K | Text | 1,000 RPM, 50K TPM |
240+
| deepseek-ai/DeepSeek-R1-0528-Qwen3-8B | ~33K | 16K | Text (reasoning) | 1,000 RPM, 50K TPM |
241+
| deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | 131K | Configurable | Text (reasoning) | 1,000 RPM, 50K TPM |
242+
| THUDM/glm-4-9b-chat | 32K | 32K | Text | 1,000 RPM, 50K TPM |
243+
| THUDM/GLM-4.1V-9B-Thinking | 66K | 66K | Vision + Text | 1,000 RPM, 50K TPM |
244+
| deepseek-ai/DeepSeek-OCR | — | 8K | Vision (OCR) | 1,000 RPM, 50K TPM |
245+
| + embedding/speech models | Varies | Varies | Embeddings, Speech | 1,000 RPM, 50K TPM |
45246

46247
## Contributing
47248

48249
Know a free tier that's missing? [Open a PR](contributing.md). Include the provider, endpoint, rate limits (link to their docs), and a few notable models. Trial credits and time-limited promos don't count.
49250

50-
## Footnotes
251+
## Glossary
252+
253+
| Abbreviation | Meaning |
254+
|---|---|
255+
| **RPM** | Requests per minute |
256+
| **RPD** | Requests per day |
257+
| **TPM** | Tokens per minute |
258+
| **TPD** | Tokens per day |
259+
| **RPS** | Requests per second |
260+
261+
## Notes
51262

52-
- **RPM** -- requests per minute. **RPD** -- requests per day.
53-
- "Limits undocumented" means the provider doesn't publish their rate limits.
54263
- All endpoints are OpenAI SDK-compatible unless noted.
55264
- Each link points to the provider's API key page.
56-
- [^1]: Free tier not available in the EU, UK, or Switzerland ([available regions](https://ai.google.dev/gemini-api/docs/available-regions)).
57-
- [^2]: Ollama Cloud measures usage by GPU time, not tokens or requests. Free tier described as "light usage" with session limits resetting every 5 hours and weekly limits every 7 days. Pro (50x more) and Max (250x more) plans available. Not OpenAI SDK-compatible; uses [Ollama API](https://docs.ollama.com/cloud).
58-
- [^3]: 14,400 RPD only applies to Llama 3.1 8B Instant. Most other models (Llama 3.3 70B, Llama 4 Scout, Kimi K2, etc.) are limited to 1,000 RPD ([rate limits](https://console.groq.com/docs/rate-limits)).
59-
- [^4]: Free models default to 50 RPD. A one-time purchase of $10+ in credits unlocks 1,000 RPD for free models. OpenRouter also offers a [Free Models Router](https://openrouter.ai/docs/guides/routing/routers/free-models-router) (`openrouter/free`) and [model fallbacks](https://openrouter.ai/docs/guides/routing/model-fallbacks) for chaining models in priority order.
265+
266+
[^1]: Free tier not available in the EU, UK, or Switzerland ([available regions](https://ai.google.dev/gemini-api/docs/available-regions)).
267+
[^2]: Groq rate limits vary by model. Llama 4 Maverick is limited to 500 RPD. Most other models get 14,400 RPD ([rate limits](https://console.groq.com/docs/rate-limits)).
268+
[^3]: Ollama Cloud measures usage by GPU time, not tokens or requests. Free tier described as "light usage" with session limits resetting every 5 hours and weekly limits every 7 days. Pro (50x more) and Max (250x more) plans available. Not OpenAI SDK-compatible; uses [Ollama API](https://docs.ollama.com/cloud).
269+
[^4]: Free models default to 200 RPD. A one-time purchase of $10+ in credits unlocks 1,000 RPD for free models. OpenRouter also offers a [Free Models Router](https://openrouter.ai/docs/guides/routing/routers/free-models-router) (`openrouter/free`) and [model fallbacks](https://openrouter.ai/docs/guides/routing/model-fallbacks) for chaining models in priority order.
270+
[^5]: Kilo Code free model list is dynamic and rotates based on partnerships. Free models log prompts for improvement. Auto-router available: `kilo-auto/free`.

0 commit comments

Comments
 (0)