fomo2 dispatches LLM calls to different providers based on the task at hand. Cheap, frequent calls (dedup, narratives) run on small Ollama Cloud models; the smartest calls reserve Gemini 2.5 Pro. This page shows the current routing, the OpenRouter leaderboard, and the closest Ollama Cloud match for each ranked model.
Edit provider/model below to override routing live. Saved overrides
persist across restarts via Redis (key fomo2:llm:routing_overrides).
Sources:
default
yaml
runtime
| Task kind | Provider | Model | Source | |
|---|---|---|---|---|
dedup |
default | |||
default |
default | |||
embedding |
default | |||
enrich |
default | |||
goal_default |
default | |||
goal_pro |
default | |||
narrative |
default | |||
prediction_scoring |
default | |||
validation |
default | |||
watcher |
default | |||
wizard |
default |
What each task tier actually used + spent over the last 24h. Total: €0.0000 across 17 LLM calls. Ollama Cloud is a flat $20/month subscription — its rows show $0 marginal cost. Gemini is pay-per-use, so its rows reflect real spend.
| Task | Top model | Calls (top) | Total calls | Cost (24h) |
|---|---|---|---|---|
goal_pro |
kimi-k2:1t-cloud |
3 | 3 | €0.0000 |
goal_default |
gpt-oss:120b-cloud |
12 | 12 | €0.0000 |
narrative |
gpt-oss:20b-cloud |
2 | 2 | €0.0000 |
| # | OpenRouter model | Ctx | Prompt ($/1M) | Compl ($/1M) | Ollama Cloud match | fomo2 task kinds |
|---|---|---|---|---|---|---|
| 1 |
Anthropic: Claude Sonnet 4
anthropic/claude-sonnet-4
|
1,000,000 | $3.000 | $15.000 | no Ollama equivalent | |
| 2 |
Anthropic: Claude Opus 4
anthropic/claude-opus-4
|
200,000 | $15.000 | $75.000 | no Ollama equivalent | |
| 3 |
Google: Gemini 2.5 Pro
google/gemini-2.5-pro
|
1,048,576 | $1.250 | $10.000 | no Ollama equivalent | |
| 4 |
Google: Gemini 2.5 Flash
google/gemini-2.5-flash
|
1,048,576 | $0.300 | $2.500 | no Ollama equivalent | |
| 5 |
OpenAI: GPT-4o
openai/gpt-4o
|
128,000 | $2.500 | $10.000 | no Ollama equivalent | |
| 6 |
OpenAI: GPT-4o-mini
openai/gpt-4o-mini
|
128,000 | $0.150 | $0.600 | no Ollama equivalent | |
| 7 |
OpenAI: gpt-oss-120b
openai/gpt-oss-120b
|
131,072 | $0.039 | $0.180 |
gpt-oss:120b-cloud
|
default goal_default validation wizard |
| 8 |
OpenAI: gpt-oss-20b
openai/gpt-oss-20b
|
131,072 | $0.030 | $0.140 |
gpt-oss:20b-cloud
|
dedup enrich narrative |
| 9 |
DeepSeek: DeepSeek V3
deepseek/deepseek-chat
|
163,840 | $0.320 | $0.890 |
deepseek-v3.1:671b-cloud
|
|
| 10 |
MoonshotAI: Kimi K2 0711
moonshotai/kimi-k2
|
131,072 | $0.570 | $2.300 |
kimi-k2:1t-cloud
|
goal_pro |
| 11 |
Meta: Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instruct
|
131,072 | $0.100 | $0.320 |
qwen3-coder:480b-cloud
|
prediction_scoring watcher |
| 12 |
Mistral Large
mistralai/mistral-large
|
128,000 | $2.000 | $6.000 | no Ollama equivalent | |
| 13 |
AI21: Jamba Large 1.7
ai21/jamba-large-1.7
|
256,000 | $2.000 | $8.000 | no Ollama equivalent | |
| 14 |
AionLabs: Aion-1.0
aion-labs/aion-1.0
|
131,072 | $4.000 | $8.000 | no Ollama equivalent | |
| 15 |
AionLabs: Aion-1.0-Mini
aion-labs/aion-1.0-mini
|
131,072 | $0.700 | $1.400 | no Ollama equivalent | |
| 16 |
AionLabs: Aion-2.0
aion-labs/aion-2.0
|
131,072 | $0.800 | $1.600 | no Ollama equivalent | |
| 17 |
AionLabs: Aion-RP 1.0 (8B)
aion-labs/aion-rp-llama-3.1-8b
|
32,768 | $0.800 | $1.600 | no Ollama equivalent | |
| 18 |
AlfredPros: CodeLLaMa 7B Instruct Solidity
alfredpros/codellama-7b-instruct-solidity
|
4,096 | $0.800 | $1.200 | no Ollama equivalent | |
| 19 |
Tongyi DeepResearch 30B A3B
alibaba/tongyi-deepresearch-30b-a3b
|
131,072 | $0.090 | $0.450 | no Ollama equivalent | |
| 20 |
AllenAI: Olmo 3 32B Think
allenai/olmo-3-32b-think
|
65,536 | $0.150 | $0.500 | no Ollama equivalent | |
| 21 |
Amazon: Nova 2 Lite
amazon/nova-2-lite-v1
|
1,000,000 | $0.300 | $2.500 | no Ollama equivalent | |
| 22 |
Amazon: Nova Lite 1.0
amazon/nova-lite-v1
|
300,000 | $0.060 | $0.240 | no Ollama equivalent | |
| 23 |
Amazon: Nova Micro 1.0
amazon/nova-micro-v1
|
128,000 | $0.035 | $0.140 | no Ollama equivalent | |
| 24 |
Amazon: Nova Premier 1.0
amazon/nova-premier-v1
|
1,000,000 | $2.500 | $12.500 | no Ollama equivalent | |
| 25 |
Amazon: Nova Pro 1.0
amazon/nova-pro-v1
|
300,000 | $0.800 | $3.200 | no Ollama equivalent | |
| 26 |
Magnum v4 72B
anthracite-org/magnum-v4-72b
|
32,768 | $3.000 | $5.000 | no Ollama equivalent | |
| 27 |
Anthropic: Claude 3 Haiku
anthropic/claude-3-haiku
|
200,000 | $0.250 | $1.250 | no Ollama equivalent | |
| 28 |
Anthropic: Claude 3.5 Haiku
anthropic/claude-3.5-haiku
|
200,000 | $0.800 | $4.000 | no Ollama equivalent | |
| 29 |
Anthropic: Claude Haiku 4.5
anthropic/claude-haiku-4.5
|
200,000 | $1.000 | $5.000 | no Ollama equivalent | |
| 30 |
Anthropic: Claude Opus 4.1
anthropic/claude-opus-4.1
|
200,000 | $15.000 | $75.000 | no Ollama equivalent | |
| 31 |
Anthropic: Claude Opus 4.5
anthropic/claude-opus-4.5
|
200,000 | $5.000 | $25.000 | no Ollama equivalent | |
| 32 |
Anthropic: Claude Opus 4.6
anthropic/claude-opus-4.6
|
1,000,000 | $5.000 | $25.000 | no Ollama equivalent | |
| 33 |
Anthropic: Claude Opus 4.6 (Fast)
anthropic/claude-opus-4.6-fast
|
1,000,000 | $30.000 | $150.000 | no Ollama equivalent | |
| 34 |
Anthropic: Claude Opus 4.7
anthropic/claude-opus-4.7
|
1,000,000 | $5.000 | $25.000 | no Ollama equivalent | |
| 35 |
Anthropic: Claude Opus 4.7 (Fast)
anthropic/claude-opus-4.7-fast
|
1,000,000 | $30.000 | $150.000 | no Ollama equivalent | |
| 36 |
Anthropic: Claude Sonnet 4.5
anthropic/claude-sonnet-4.5
|
1,000,000 | $3.000 | $15.000 | no Ollama equivalent | |
| 37 |
Anthropic: Claude Sonnet 4.6
anthropic/claude-sonnet-4.6
|
1,000,000 | $3.000 | $15.000 | no Ollama equivalent | |
| 38 |
Arcee AI: Coder Large
arcee-ai/coder-large
|
32,768 | $0.500 | $0.800 | no Ollama equivalent | |
| 39 |
Arcee AI: Maestro Reasoning
arcee-ai/maestro-reasoning
|
131,072 | $0.900 | $3.300 | no Ollama equivalent | |
| 40 |
Arcee AI: Spotlight
arcee-ai/spotlight
|
131,072 | $0.180 | $0.180 | no Ollama equivalent |
Source: openrouter.ai/rankings + /api/v1/models. Cached for 24h.