Today's nugget

The daily digest

Every morning: the cheapest AI models, the best value-for-money flagships, and provider technical incidents — at a glance.

Generated 11/07, 02:01 AMSource: OpenRouter (live)477 models tracked

Deal of the day

The cheapest paid model across all categories.

OpenAI: gpt-oss-120b

openai

$0.021

/ 1M tokens (moyen)

in $0.012

out $0.046

ctx 131K

Top 5 cheapest

All paid models, ranked by blended price per million tokens.

OpenAI: gpt-oss-120b

openai · ctx 131K

in $0.012·out $0.046

$0.021

/1M

inclusionAI: Ling 3.0 Tiny

inclusionai · ctx 262K

in $0.015·out $0.045

$0.022

/1M

Mistral: Mistral Nemo

mistralai · ctx 131K

in $0.029·out $0.030

$0.029

/1M

ScaleDown: Summarize

scaledown · ctx 1M

in $0.040·out Free

$0.030

/1M

ScaleDown: Extract

scaledown · ctx 1M

in $0.040·out Free

$0.030

/1M

Best value for money

The market's flagship models, cheapest to priciest.

Gemini 1.5 Flash

Google · ctx 1M

in $0.075·out $0.300

$0.131

/1M

DeepSeek R1

DeepSeek · ctx 64K

in $0.550·out $2.19

$0.960

/1M

Claude 3.5 Haiku

Anthropic · ctx 200K

in $0.800·out $4.00

$1.60

/1M

Gemini 1.5 Pro

Google · ctx 2M

in $1.25·out $5.00

$2.19

/1M

Mistral Large

Mistral · ctx 128K

in $2.00·out $6.00

$3.00

/1M

Grok 2

xAI · ctx 131K

in $2.00·out $10.00

$4.00

/1M

OpenAI: GPT-4o

openai · ctx 128K

in $2.50·out $10.00

$4.38

/1M

Command R+

Cohere · ctx 128K

in $2.50·out $10.00

$4.38

/1M

Claude 3.5 Sonnet

Anthropic · ctx 200K

in $3.00·out $15.00

$6.00

/1M

OpenAI · ctx 200K

in $15.00·out $60.00

$26.25

/1M

Cheapest per provider

Each provider's most economical model.

openai

OpenAI: gpt-oss-120b

$0.021

ctx 131K

inclusionai

inclusionAI: Ling 3.0 Tiny

$0.022

ctx 262K

mistralai

Mistral: Mistral Nemo

$0.029

ctx 131K

scaledown

ScaleDown: Summarize

$0.030

ctx 1M

sao10k

Sao10K: Llama 3 8B Lunaris

$0.042

ctx 8K

nex-agi

Nex AGI: Nex-N2.5-Mini

$0.044

ctx 262K

Provider technical incidents

Reported anomalies: latency, downtime, tightened quotas. Updated manually.

Latency spike on the gpt-4o APIwarning

OpenAI · 2026-11-06

Several users report high response times and intermittent timeouts on gpt-4o under load. The rest of the catalogue (gpt-4o-mini, o1) remains stable.

Tightened rate limits on Claude 3.5 Sonnetinfo

Anthropic · 2026-11-05

Anthropic lowered per-minute quotas on Claude 3.5 Sonnet for recent accounts. Claude 3.5 Haiku is unaffected. Check your dashboard for your current tier.

Intermittent 502 errors on deepseek-r1critical

DeepSeek · 2026-11-07

The deepseek-r1 endpoint returns 502s intermittently this morning. Aggregator (OpenRouter) automatic retries fall back to alternative routes.

Gemini 2.0 Flash now generally availableinfo

Google · 2026-11-04

Gemini 2.0 Flash reached GA. Competitive per-million-token pricing and low latency — a strong value-for-money candidate right now.

Lengthening queue on Mistral Largewarning

Mistral · 2026-11-06

Time-to-first-token is rising on Mistral Large during European peak hours. Mistral Small stays smooth.

Grok 2 stable, increased monitoringinfo

xAI · 2026-11-03

No notable incidents on Grok 2. Increased monitoring after last week's latency spikes, now resolved.

o1 missing from live feedwarning

OpenAI · 2026-11-07