Top models by tokens
The models processing the most tokens through Respan, tracked weekly.
LLM Leaderboard
What teams run on the Respan gateway, how models score on the Respan Index, what they cost, and whether their providers are up.
Top models by tokens
The models processing the most tokens through Respan, tracked weekly.
What teams run on the Respan gateway, how models score on the Respan Index, what they cost, and whether their providers are up.
The models processing the most tokens through Respan, tracked weekly.
The models accounting for the most gateway spend, tracked weekly.
The models handling the most gateway requests, tracked weekly.
The providers serving the most gateway traffic, against the prior period.
| Provider | Change | |
|---|---|---|
Anthropic | 479.1B | ↓45% |
OpenAI | 413B | ↓52% |
OpenRouter | 128.1B | ↓38% |
Azure OpenAI | 48.1B | ↑23% |
Respan | 42.6B | ↓48% |
DeepSeek | 34.9B | NEW |
Respan Cloud | 15.3B | ↓80% |
Google AI | 14.1B | ↓2% |
Parasail | 5.9B | ↓16% |
Baseten | 1.6B | NEW |
The models gaining and losing gateway traffic fastest, week over week.
DeepSeek V4.1 Flash
by deepseek
32.6B tokens
NEW
Claude Haiku 5.5
by anthropic
4.15B tokens
NEW
GPT-5.6 Sol
by openai
3.21B tokens
↓91%
GPT-6 Sol
by openai
2.8B tokens
↓91%
GPT-6 Luna
by openai
26.2B tokens
↓87%
GPT-6.1 Terra
by openai
2.88B tokens
↓86%
GPT-6.1 Sol
by openai
35.6B tokens
↓83%
Models ranked on one 0 to 100 score from public benchmarks and lab results.
| Model | Respan Index | $ in / out | Context | |
|---|---|---|---|---|
| 1. | Claude Opus 5.5by Anthropic | 74.1 | $4 / $20 | 1M |
| 2. | Claude Sonnet 5.5by Anthropic | 73.5 | $2 / $10 | 1M |
| 3. | GPT-6 Astraby OpenAI | 71.8 | $10 / $50 | 1.1M |
| 4. | Kimi K3.1 Proby Moonshot AI | 70.9 | $1.8 / $9 | 1.0M |
| 5. | Muse Wonder Fullby Meta | 70.8 | - | - |
List prices per 1M tokens. * Estimated, no published scores in that category.
Respan Index against blended price per 1M tokens (3 input to 1 output), cheapest on the right.
Best value models, best score first:
The top three for each task, from the Respan Index and list prices.
Llama 4 Scout
by Meta
10M tokens
Index 10.7
Grok 4.1 Fast Reasoning
by xAI
2M tokens
Index 22.6
Grok 4 Fast Reasoning
by xAI
2M tokens
Index 20.1
Compare families:Claude vs GeminiClaude vs GrokClaude vs GPTGemini vs GPTGemini vs GrokClaude vs DeepSeekClaude vs KimiDeepSeek vs Qwen
Live status from each provider's official status page, every five minutes.
Minor incidents show on the bars but don't lower uptime. Data from each provider's official status page.
62 public benchmarks, combined into one score for 165 models.
Version 1.1, 2,907 cited results from Respan's benchmark database.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.