@blockrun/clawrouter 0.12.257 → 0.12.259
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +34 -30
- package/dist/cli.js +538 -142
- package/dist/index.js +538 -142
- package/dist/router/index.js +43 -30
- package/docs/9-free-ai-models-zero-cost-blockrun.md +79 -86
- package/docs/anthropic-cost-savings.md +4 -4
- package/docs/anthropic-third-party-harness-changes.md +4 -4
- package/docs/clawrouter-cuts-llm-api-costs-500x.md +1 -1
- package/docs/clawrouter-vs-openrouter-llm-routing-comparison.md +4 -4
- package/docs/features.md +9 -8
- package/docs/routing-profiles.md +27 -23
- package/docs/subscription-failover.md +1 -1
- package/package.json +3 -3
- package/scripts/benchmark.py +2 -2
- package/scripts/reinstall.sh +7 -5
- package/skills/clawrouter/SKILL.md +4 -4
- package/src/top-models.json +11 -4
package/docs/routing-profiles.md
CHANGED
|
@@ -21,7 +21,7 @@ Use `blockrun/auto` (or `/model auto`) for the best quality/price balance.
|
|
|
21
21
|
|
|
22
22
|
| Tier | Primary Model | Input | Output | Fallback chain (in order) |
|
|
23
23
|
| --------- | -------------------------- | ----- | ------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
|
24
|
-
| SIMPLE | google/gemini-2.5-flash | $0.30 | $2.50 | gemini-3-flash-preview → gemini-3.5-flash-lite → deepseek-chat → gemini-3.1-flash-lite → gpt-5.6-luna → gpt-5.4-nano → gemini-2.5-flash-lite →
|
|
24
|
+
| SIMPLE | google/gemini-2.5-flash | $0.30 | $2.50 | gemini-3-flash-preview → gemini-3.5-flash-lite → deepseek-chat → gemini-3.1-flash-lite → gpt-5.6-luna → gpt-5.4-nano → gemini-2.5-flash-lite → nemotron-3.5-lightning (free) |
|
|
25
25
|
| MEDIUM | google/gemini-3.5-flash | $1.50 | $9.00 | gemini-3.6-flash → glm-5.3-flash → gpt-5.6-terra → gemini-3-flash-preview → deepseek-chat → gemini-2.5-flash → minimax-m3 → gemini-3.1-flash-lite → gpt-5.6-luna → gemini-2.5-flash-lite |
|
|
26
26
|
| COMPLEX | google/gemini-3.1-pro | $2.00 | $12.00 | gemini-3.6-flash → gemini-3.5-flash → claude-sonnet-5 → grok-4.5 → gemini-2.5-pro → claude-sonnet-4.6 → gpt-5.6-terra → gpt-5.5 → gpt-5.4 → glm-5.3 → kimi-k3 → deepseek-v4-pro → deepseek-chat → gemini-2.5-flash |
|
|
27
27
|
| REASONING | deepseek/deepseek-reasoner | $0.14 | $0.28 | deepseek-v4-pro → grok-4.3 → qwen3.7-plus → gemini-3.5-flash → o4-mini → o3 |
|
|
@@ -32,14 +32,14 @@ Use `blockrun/auto` (or `/model auto`) for the best quality/price balance.
|
|
|
32
32
|
|
|
33
33
|
Use `blockrun/eco` for maximum cost savings. The first stop is the free tier, so simple requests can cost $0.00.
|
|
34
34
|
|
|
35
|
-
| Tier | Primary Model
|
|
36
|
-
| --------- |
|
|
37
|
-
| SIMPLE | free/
|
|
38
|
-
| MEDIUM | zai/glm-5.3-flash
|
|
39
|
-
| COMPLEX | zai/glm-5.3-flash
|
|
40
|
-
| REASONING | deepseek/deepseek-reasoner
|
|
35
|
+
| Tier | Primary Model | Input | Output | Fallback chain (in order) |
|
|
36
|
+
| --------- | --------------------------- | ----- | ------ | ------------------------------------------------------------------------------------------------------------------------ |
|
|
37
|
+
| SIMPLE | free/nemotron-3.5-lightning | $0.00 | $0.00 | nemotron-3-nano-30b (free) → gemini-2.5-flash-lite → glm-5.3-flash → gpt-5.6-luna → gpt-5.4-nano → gemini-3.1-flash-lite |
|
|
38
|
+
| MEDIUM | zai/glm-5.3-flash | $0.15 | $0.50 | deepseek-chat → gemini-3.1-flash-lite → gpt-5.6-luna → gpt-5.4-nano → gemini-2.5-flash-lite → gemini-2.5-flash |
|
|
39
|
+
| COMPLEX | zai/glm-5.3-flash | $0.15 | $0.50 | deepseek-chat → minimax-m3 → deepseek-v4-pro → gemini-3.1-flash-lite → gemini-2.5-flash |
|
|
40
|
+
| REASONING | deepseek/deepseek-reasoner | $0.14 | $0.28 | deepseek-v4-pro → qwen3.7-plus → minimax-m3 → glm-5.3-flash |
|
|
41
41
|
|
|
42
|
-
The two free rungs at the head of ECO SIMPLE follow NVIDIA's free hosting, which retires models without notice (deepseek-v4-flash 410'd 2026-08-12, seed-oss-36b 2026-08-03, gpt-oss-120b hung 2026-08-16). Each retirement retargets the free rungs to the current free tier; the paid rungs never move. `src/router/free-model-liveness.test.ts` fails the build if a chain names a free model the picker no longer lists.
|
|
42
|
+
The two free rungs at the head of ECO SIMPLE follow NVIDIA's free hosting, which retires models without notice (deepseek-v4-flash 410'd 2026-08-12, seed-oss-36b 2026-08-03, gpt-oss-120b hung 2026-08-16, and on 2026-08-30 NVIDIA retired FOUR of the five visible free models at once). Each retirement retargets the free rungs to the current free tier; the paid rungs never move. `src/router/free-model-liveness.test.ts` fails the build if a chain names a free model the picker no longer lists.
|
|
43
43
|
|
|
44
44
|
---
|
|
45
45
|
|
|
@@ -47,12 +47,12 @@ The two free rungs at the head of ECO SIMPLE follow NVIDIA's free hosting, which
|
|
|
47
47
|
|
|
48
48
|
Use `blockrun/premium` for maximum quality. Codex for complex coding, Gemini 3.5 Flash for simple work, Sonnet 5 for reasoning/instructions, Fable/Opus for architecture, audits and PM-grade work.
|
|
49
49
|
|
|
50
|
-
| Tier | Primary Model | Input | Output | Fallback chain (in order)
|
|
51
|
-
| --------- | ------------------------- | ------ | ------ |
|
|
52
|
-
| SIMPLE | google/gemini-3.5-flash | $1.50 | $9.00 | gemini-3.6-flash → claude-haiku-4.5 → glm-5.3 → gemini-2.5-flash → gemini-3.5-flash-lite → deepseek-chat
|
|
53
|
-
| MEDIUM | openai/gpt-5.3-codex | $1.75 | $14.00 | claude-sonnet-5 → kimi-k3 → glm-5.3 → gemini-3.6-flash → gemini-3.5-flash → gemini-2.5-pro → grok-4.5 → claude-sonnet-4.6 → gpt-5.6-terra
|
|
54
|
-
| COMPLEX | anthropic/claude-fable-5 | $10.00 | $50.00 | claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → claude-sonnet-5 → claude-sonnet-4.6 → grok-4.5 → kimi-k3 → gpt-5.6-terra → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → glm-5.3 → deepseek-v4-pro → deepseek-chat →
|
|
55
|
-
| REASONING | anthropic/claude-sonnet-5 | $3.00 | $15.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → deepseek-v4-pro → grok-4.3 → o4-mini → o3
|
|
50
|
+
| Tier | Primary Model | Input | Output | Fallback chain (in order) |
|
|
51
|
+
| --------- | ------------------------- | ------ | ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
52
|
+
| SIMPLE | google/gemini-3.5-flash | $1.50 | $9.00 | gemini-3.6-flash → claude-haiku-4.5 → glm-5.3 → gemini-2.5-flash → gemini-3.5-flash-lite → deepseek-chat |
|
|
53
|
+
| MEDIUM | openai/gpt-5.3-codex | $1.75 | $14.00 | claude-sonnet-5 → kimi-k3 → glm-5.3 → gemini-3.6-flash → gemini-3.5-flash → gemini-2.5-pro → grok-4.5 → claude-sonnet-4.6 → gpt-5.6-terra |
|
|
54
|
+
| COMPLEX | anthropic/claude-fable-5 | $10.00 | $50.00 | claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → claude-sonnet-5 → claude-sonnet-4.6 → grok-4.5 → kimi-k3 → gpt-5.6-terra → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → glm-5.3 → deepseek-v4-pro → deepseek-chat → nemotron-3.5-lightning (free) |
|
|
55
|
+
| REASONING | anthropic/claude-sonnet-5 | $3.00 | $15.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → deepseek-v4-pro → grok-4.3 → o4-mini → o3 |
|
|
56
56
|
|
|
57
57
|
The premium COMPLEX chain is deliberately de-Gemini'd: Google's "high demand" 503s correlate with Anthropic outages (everyone falls back to Google at the same time), so the chain prefers the in-family Opus hot swaps, then xAI, Moonshot, OpenAI and Z.AI — providers on independent infrastructure.
|
|
58
58
|
|
|
@@ -62,12 +62,12 @@ The premium COMPLEX chain is deliberately de-Gemini'd: Google's "high demand" 50
|
|
|
62
62
|
|
|
63
63
|
Not a profile you pick — router-core switches to these tiers when the turn actually needs its attached tools (`inferToolRequirement`: `tool_choice: "none"` is authoritative, and host tool _descriptions_ alone do not trigger it). Primaries favour models that keep going instead of stopping to ask.
|
|
64
64
|
|
|
65
|
-
| Tier | Primary Model | Input | Output | Fallback chain (in order)
|
|
66
|
-
| --------- | ------------------------- | ----- | ------ |
|
|
67
|
-
| SIMPLE | openai/gpt-4o-mini | $0.15 | $0.60 | gpt-5.6-luna → glm-5.3-flash → claude-haiku-4.5 → gemini-2.5-flash
|
|
68
|
-
| MEDIUM | openai/gpt-5-mini | $0.25 | $2.00 | gemini-3.5-flash → glm-5.3-flash → gpt-5.6-terra → gpt-4o-mini → claude-haiku-4.5 → deepseek-chat → kimi-k3
|
|
69
|
-
| COMPLEX | anthropic/claude-sonnet-5 | $3.00 | $15.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → kimi-k3 → gpt-5.6-terra → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → glm-5.3 → deepseek-v4-pro → deepseek-chat →
|
|
70
|
-
| REASONING | anthropic/claude-sonnet-5 | $3.00 | $15.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → deepseek-v4-pro → deepseek-reasoner
|
|
65
|
+
| Tier | Primary Model | Input | Output | Fallback chain (in order) |
|
|
66
|
+
| --------- | ------------------------- | ----- | ------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
|
67
|
+
| SIMPLE | openai/gpt-4o-mini | $0.15 | $0.60 | gpt-5.6-luna → glm-5.3-flash → claude-haiku-4.5 → gemini-2.5-flash |
|
|
68
|
+
| MEDIUM | openai/gpt-5-mini | $0.25 | $2.00 | gemini-3.5-flash → glm-5.3-flash → gpt-5.6-terra → gpt-4o-mini → claude-haiku-4.5 → deepseek-chat → kimi-k3 |
|
|
69
|
+
| COMPLEX | anthropic/claude-sonnet-5 | $3.00 | $15.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → kimi-k3 → gpt-5.6-terra → gpt-5.5 → gpt-5.4 → gpt-5.3-codex → glm-5.3 → deepseek-v4-pro → deepseek-chat → nemotron-3.5-lightning (free) |
|
|
70
|
+
| REASONING | anthropic/claude-sonnet-5 | $3.00 | $15.00 | claude-sonnet-4.6 → claude-opus-5 → claude-opus-4.8 → claude-opus-4.7 → grok-4.5 → deepseek-v4-pro → deepseek-reasoner |
|
|
71
71
|
|
|
72
72
|
Set `routing.overrides.agenticMode: false` to disable the agentic tier set, or `true` to force it.
|
|
73
73
|
|
|
@@ -75,9 +75,13 @@ Set `routing.overrides.agenticMode: false` to disable the agentic tier set, or `
|
|
|
75
75
|
|
|
76
76
|
## FREE (`/model free`)
|
|
77
77
|
|
|
78
|
-
`free` is an alias, not a routed profile: it pins the free-tier default, currently **`free/
|
|
78
|
+
`free` is an alias, not a routed profile: it pins the free-tier default, currently **`free/nemotron-3.5-lightning`** — the same model that opens ECO SIMPLE. If that model is excluded (`/exclude add lightning`) or the budget cap forces a free fallback, the proxy walks the free cascade in this order: nemotron-3.5-lightning → nemotron-3-nano-30b → laguna-xs-2.1 → north-mini-code → nemotron-3-nano-omni-30b-a3b-reasoning → nemotron-3-ultra-550b → llama-3.2-11b-vision. All seven are $0.00 and need no USDC, and all seven are treated as **text-only** — see the vision note below.
|
|
79
79
|
|
|
80
|
-
|
|
80
|
+
The order is not arbitrary. The head is whatever the gateway itself redirects the previous head to, so the proxy and the gateway never name different models. After it comes the fastest rung, then the two sub-second coders — adjacent on purpose, because they sit on _different_ capacity pools (our own NVIDIA key vs OpenRouter's $0 pool), so one pool's outage cannot take both. The vision model sits mid-chain, and the two slowest rungs go last. The tier stopped being NVIDIA-only on 2026-08-30: two of the seven come from Cohere and Poolside.
|
|
81
|
+
|
|
82
|
+
Pin any of them directly with `/model lightning`, `/model nano-30b`, `/model laguna`, `/model north-mini`, `/model nemotron-omni`, `/model ultra-550b` or `/model llama-vision`.
|
|
83
|
+
|
|
84
|
+
**No free model carries the `vision` flag,** even the two the upstream catalogs advertise as vision-capable. A 64×64 solid-colour probe on 2026-08-31 got the right answer 1 time in 4 from `nemotron-3-nano-omni` on Base, and "white" for red on Solana — where the response's own `model` field showed a silent fallback to a text model. `llama-3.2-11b-vision`, despite the name, said "I'm unable to see the image" on 3 of 3 while a plain-text control passed. Every one of those is an HTTP 200, so the caller gets a confident wrong answer with nothing to branch on. Since `vision` is what `filterByVision()` uses to _aim_ image turns at a model, flagging them would route real traffic into that. Requests carrying an `image_url` go to a paid vision model.
|
|
81
85
|
|
|
82
86
|
---
|
|
83
87
|
|
|
@@ -109,7 +113,7 @@ Combined input + output rate per 1M tokens, primaries only:
|
|
|
109
113
|
| COMPLEX | $1.75 | $14.00 | **88%** |
|
|
110
114
|
| REASONING | $0.70 | $0.70 | 0% |
|
|
111
115
|
|
|
112
|
-
The published savings claim (**
|
|
116
|
+
The published savings claim (**84%** on `auto`, **98%** on `eco`, against pinning Claude Opus 5) is blended across a stated workload mix and priced on the live catalog — see [`savings-mix.json`](https://github.com/BlockRunAI/blockrun/blob/main/src/brand/savings-mix.json). Per-tier numbers above are illustrative; the blended figure is the one to quote.
|
|
113
117
|
|
|
114
118
|
---
|
|
115
119
|
|
|
@@ -139,7 +139,7 @@ To verify failover works:
|
|
|
139
139
|
```bash
|
|
140
140
|
openclaw models fallbacks add blockrun/google/gemini-2.5-flash # Fast & cheap
|
|
141
141
|
openclaw models fallbacks add blockrun/deepseek/deepseek-chat # Even cheaper
|
|
142
|
-
openclaw models fallbacks add blockrun/
|
|
142
|
+
openclaw models fallbacks add blockrun/free/nemotron-3.5-lightning # Free tier
|
|
143
143
|
```
|
|
144
144
|
|
|
145
145
|
#### Per-Agent Configuration
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@blockrun/clawrouter",
|
|
3
|
-
"version": "0.12.
|
|
4
|
-
"description": "Smart LLM router — save
|
|
3
|
+
"version": "0.12.259",
|
|
4
|
+
"description": "Smart LLM router — save 84% on inference costs. 76 models (7 free), one wallet, x402 micropayments.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|
|
7
7
|
"types": "dist/index.d.ts",
|
|
@@ -111,7 +111,7 @@
|
|
|
111
111
|
}
|
|
112
112
|
},
|
|
113
113
|
"devDependencies": {
|
|
114
|
-
"@blockrun/router-core": "https://codeload.github.com/BlockRunAI/router-core/tar.gz/
|
|
114
|
+
"@blockrun/router-core": "https://codeload.github.com/BlockRunAI/router-core/tar.gz/5ee7c23c993013a8052588191569db5cf7fb793c",
|
|
115
115
|
"@eslint/js": "^10.0.1",
|
|
116
116
|
"eslint": "^10.2.0",
|
|
117
117
|
"openclaw": "^2026.7.2-beta.7",
|
package/scripts/benchmark.py
CHANGED
|
@@ -39,7 +39,7 @@ MODELS = [
|
|
|
39
39
|
# MiniMax
|
|
40
40
|
"minimax/minimax-m2.5",
|
|
41
41
|
# NVIDIA
|
|
42
|
-
"nvidia/
|
|
42
|
+
"nvidia/nemotron-3.5-lightning",
|
|
43
43
|
]
|
|
44
44
|
|
|
45
45
|
PROMPTS = [
|
|
@@ -146,7 +146,7 @@ PRICING = {
|
|
|
146
146
|
"xai/grok-4-1-fast-reasoning": (0.2, 0.5), "xai/grok-4-1-fast-non-reasoning": (0.2, 0.5),
|
|
147
147
|
"xai/grok-4-0709": (0.2, 1.5),
|
|
148
148
|
"minimax/minimax-m2.5": (0.3, 1.1),
|
|
149
|
-
"nvidia/
|
|
149
|
+
"nvidia/nemotron-3.5-lightning": (0, 0),
|
|
150
150
|
}
|
|
151
151
|
|
|
152
152
|
|
package/scripts/reinstall.sh
CHANGED
|
@@ -880,14 +880,16 @@ echo " /model sonnet → claude-sonnet-4.6"
|
|
|
880
880
|
echo " /model opus → claude-opus-5"
|
|
881
881
|
echo " /model codex → openai/gpt-5.3-codex"
|
|
882
882
|
echo " /model deepseek → deepseek/deepseek-chat"
|
|
883
|
-
echo " /model free →
|
|
883
|
+
echo " /model free → nemotron-3.5-lightning (default free)"
|
|
884
884
|
echo ""
|
|
885
885
|
echo "Free models (no wallet needed):"
|
|
886
|
-
echo " /model
|
|
887
|
-
echo " /model
|
|
888
|
-
echo " /model
|
|
886
|
+
echo " /model lightning → nemotron-3.5-lightning (1M ctx, reasoning)"
|
|
887
|
+
echo " /model nano-30b → nemotron-3-nano-30b (fastest, ~121 tok/s)"
|
|
888
|
+
echo " /model north-mini → north-mini-code (Cohere, coding, sub-second)"
|
|
889
|
+
echo " /model laguna → laguna-xs-2.1 (Poolside, coding, ~161 tok/s)"
|
|
889
890
|
echo " /model vision-free → nemotron-3-nano-omni (text/image/video/audio)"
|
|
890
|
-
echo " /model
|
|
891
|
+
echo " /model ultra-550b → nemotron-3-ultra-550b (550B MoE, 1M ctx)"
|
|
892
|
+
echo " /model llama-vision → llama-3.2-11b-vision (Meta Llama, images)"
|
|
891
893
|
echo ""
|
|
892
894
|
echo "OpenClaw slash commands:"
|
|
893
895
|
echo " /wallet → wallet balance, address, chain"
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: clawrouter
|
|
3
|
-
description: Hosted-gateway LLM router — save
|
|
3
|
+
description: Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data (global stocks, crypto, FX, commodities), Twitter/X intelligence, prediction-market data across Polymarket, Kalshi, Limitless, Opinion, Predict.Fun, dFlow + UMA oracle resolution + wallet identity & clustering, phone-number intelligence (carrier + SIM-swap fraud detection) plus AI-powered outbound voice calls (Twilio + Bland.ai), AND the Surf unified crypto data API (84 endpoints — CEX/DEX, on-chain SQL over 80+ ClickHouse tables, 100M+ labeled wallets, prediction markets, social/CT mindshare, news, VC fund intel) as built-in agent tools. Not a local-inference tool — prompts are sent to the blockrun.ai gateway.
|
|
4
4
|
triggers:
|
|
5
5
|
- "clawrouter"
|
|
6
6
|
- "claw router"
|
|
@@ -53,7 +53,7 @@ metadata:
|
|
|
53
53
|
|
|
54
54
|
# ClawRouter
|
|
55
55
|
|
|
56
|
-
Hosted-gateway LLM router that saves <!-- br:savings.autoVsBaselinePct -->
|
|
56
|
+
Hosted-gateway LLM router that saves <!-- br:savings.autoVsBaselinePct -->84<!-- /br:savings.autoVsBaselinePct -->% on inference costs by forwarding each request to the blockrun.ai gateway, which picks the cheapest model capable of handling it across <!-- br:models.chatVisible -->76<!-- /br:models.chatVisible --> models from 9 providers (<!-- br:models.free -->7<!-- /br:models.free --> free open-weight models). All billing flows through one USDC wallet; you do not hold provider API keys.
|
|
57
57
|
|
|
58
58
|
**This is not a local-inference tool.** ClawRouter is a thin local proxy. Your prompts are sent over HTTPS to the blockrun.ai gateway for model execution. If your workload requires inference that never leaves your machine, use a local runtime like Ollama — ClawRouter is not the right tool for that use case.
|
|
59
59
|
|
|
@@ -137,7 +137,7 @@ Curated primaries on the default `auto` profile:
|
|
|
137
137
|
- **COMPLEX** — code generation, multi-step analysis → gemini-3.1-pro ($2/$12)
|
|
138
138
|
- **REASONING** — proofs, formal logic, multi-step math → grok-4-1-fast-reasoning ($0.20/$0.50)
|
|
139
139
|
|
|
140
|
-
Turns that actually need their attached tools switch to agent-tuned tiers (gpt-4o-mini → kimi-k2.7 → claude-sonnet-4.6). `eco` opens on the free tier (
|
|
140
|
+
Turns that actually need their attached tools switch to agent-tuned tiers (gpt-4o-mini → kimi-k2.7 → claude-sonnet-4.6). `eco` opens on the free tier (nemotron-3.5-lightning); `premium` climbs to gpt-5.3-codex / claude-fable-5 / claude-sonnet-4.6. Full chains: [docs/routing-profiles.md](../../docs/routing-profiles.md).
|
|
141
141
|
|
|
142
142
|
Prices are per 1M input/output tokens. Per-tier
|
|
143
143
|
savings percentages are deliberately not quoted here: the published figure is
|
|
@@ -147,7 +147,7 @@ it against a baseline nobody wrote down. See
|
|
|
147
147
|
|
|
148
148
|
## Available Models
|
|
149
149
|
|
|
150
|
-
<!-- br:models.chatVisible -->
|
|
150
|
+
<!-- br:models.chatVisible -->76<!-- /br:models.chatVisible --> models including: gpt-5.6-terra [balanced, stable default], gpt-5.6-sol [flagship], gpt-5.6-luna [cost-efficient], gpt-5.6-sol/terra/luna-pro [pro reasoning tiers], gpt-5.5, gpt-5.5-pro [max compute], chat-latest [ChatGPT Instant], gpt-5.4, gpt-4o, o3, claude-fable-5, claude-opus-5 [Anthropic flagship, 1M ctx], claude-opus-4.8, claude-opus-4.7, claude-opus-4.5, claude-sonnet-5, claude-sonnet-4.6, gemini-3.1-pro, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-2.5-flash, deepseek-v4-pro, deepseek-chat, grok-4.5, grok-4.3, grok-build-0.1, glm-5.3 [Z.AI flagship, 1M ctx], glm-5.3-flash [natively multimodal, 1M ctx — $0.15/$0.50], glm-5.2, minimax-m3, kimi-k3 [1M ctx flagship], kimi-k2.7, qwen3.7-max [Qwen flagship, 1M ctx], qwen3.7-plus, qwen3.7-flash, hy3 [Tencent], mimo [Xiaomi MiMo-V2.5 Pro, 1M ctx], and 7 free open-weight models (nemotron-3.5-lightning [1M ctx, thinking mode — the free default], nemotron-3-nano-30b [fastest, ~121 tok/s], nemotron-3-ultra-550b [550B/55B MoE, 1M ctx — the largest free model], nemotron-3-nano-omni-30b-a3b-reasoning [256K ctx], llama-3.2-11b-vision [Meta Llama], north-mini-code [Cohere, coding, sub-second], laguna-xs-2.1 [Poolside, coding, ~161 tok/s]). The free tier is text-only — image turns route to a paid vision model, because the two free models the catalogs advertise as vision-capable fail a solid-colour probe on both chains and do so with an HTTP 200.
|
|
151
151
|
|
|
152
152
|
## Built-in Agent Tools
|
|
153
153
|
|
package/src/top-models.json
CHANGED
|
@@ -27,20 +27,27 @@
|
|
|
27
27
|
"xai/grok-4.5",
|
|
28
28
|
"xai/grok-4.3",
|
|
29
29
|
"xai/grok-build-0.1",
|
|
30
|
+
"zai/glm-5.3",
|
|
31
|
+
"zai/glm-5.3-flash",
|
|
30
32
|
"zai/glm-5.2",
|
|
31
33
|
"zai/glm-5.1",
|
|
32
34
|
"zai/glm-5-turbo",
|
|
33
35
|
"zai/glm-5",
|
|
36
|
+
"xiaomi/mimo-v2.5",
|
|
34
37
|
"minimax/minimax-m3",
|
|
35
38
|
"minimax/minimax-m2.7",
|
|
36
39
|
"moonshot/kimi-k3",
|
|
37
40
|
"qwen/qwen3.7-max",
|
|
41
|
+
"qwen/qwen3.8-flash",
|
|
42
|
+
"deepseek/deepseek-v4-flash-vision-exp",
|
|
38
43
|
"deepseek/deepseek-v4-pro",
|
|
39
44
|
"deepseek/deepseek-chat",
|
|
40
45
|
"deepseek/deepseek-reasoner",
|
|
46
|
+
"free/nemotron-3.5-lightning",
|
|
47
|
+
"free/nemotron-3-nano-30b",
|
|
48
|
+
"free/laguna-xs-2.1",
|
|
49
|
+
"free/north-mini-code",
|
|
41
50
|
"free/nemotron-3-nano-omni-30b-a3b-reasoning",
|
|
42
|
-
"free/
|
|
43
|
-
"free/
|
|
44
|
-
"free/nemotron-nano-9b-v2",
|
|
45
|
-
"free/nemotron-nano-12b-v2-vl"
|
|
51
|
+
"free/nemotron-3-ultra-550b",
|
|
52
|
+
"free/llama-3.2-11b-vision"
|
|
46
53
|
]
|