Open GPT reasoning model for self-hosted agents and controllable deployments
Specification
most-agreed values
Context
131K
Max output
66K
Released
2025-08-05
Knowledge cutoff
2024-06
Retires
2026-09-15
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.075
Output
$0.30
Cache read
$0.0375
Cache write
$0.07
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | bedrock_mantle · bedrock-mantle | $0.035 |
| Batch output | bedrock_mantle · bedrock-mantle | $0.15 |
| Priority input | bedrock_mantle · bedrock-mantle | $0.1225 |
| Priority output | bedrock_mantle · bedrock-mantle | $0.525 |
Batch input is 50% below the interactive input price at the same listing.
Rate limits
Requests per minute
300
Quality
2 benchmarks · 1 source
Composite
42nd
percentile of 344 scored models
Rank
200 / 344
±0.09 sd
Evidence
2 × 1
too little evidence to place with confidence
Effort range
19.9
points between effort settings
reasoning34th1/4 bench
math48th1/7 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| medium | 59th | 2 |
| low | 35th | 2 |
| high | 35th | 2 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 65.3 ±5.9 | medium | Epoch AI | 2026-08-27 |
| ↳ | 50.8 ±6.7 | high | Epoch AI | 2026-08-27 |
| ↳ | 40.3 ±6.3 | low | Epoch AI | 2026-08-27 |
| Settings differ by 25.0 points on this benchmark. | ||||
| GPQA diamond | 60.8 ±2.5 | medium | Epoch AI | 2026-08-27 |
| ↳ | 53.2 ±2.5 | low | Epoch AI | 2026-08-27 |
| ↳ | 46.0 ±3.6 | high | Epoch AI | 2026-08-06 |
| Settings differ by 14.8 points on this benchmark. | ||||
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 56 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| lmstudio | free | free | — | — | 131K | 33K | — |
| nvidia | free | free | — | — | 131K | 33K | — |
| qvac | free | free | — | — | 131K | 33K | — |
| edenai · greenference | $0.009 | $0.045 | $0.0045 | — | 131K | 33K | — |
| darkbloom · darkbloom | $0.0145 | $0.07 | — | — | 131K | 33K | — |
| kilo | $0.018 | $0.09 | $0.009 | — | 131K | 33K | — |
| openrouter | $0.018 | $0.09 | $0.009 | — | 131K | 33K | — |
| edenai · flexai | $0.02 | $0.10 | $0.003 | — | 131K | 33K | — |
| nano-gpt | $0.02 | $0.10 | — | — | 131K | 16K | — |
| deepinfra | $0.03 | $0.14 | — | — | 131K | 16K 131K | — |
| vercel | $0.03 | $0.14 | — | — | 131K | 8K | — |
| wandb | $0.03 | $0.13 | $0.03 | — | 131K | 131K | — |
| wandb · wandb | $0.03 | $0.13 | — | — | 131K | 131K | — |
| kenari | $0.036 | $0.1543 | $0.0037 | — | 131K | 33K | — |
| inferenceapis · inferenceapis | $0.04 | $0.19 | — | — | 131K | 131K | — |
| llmgateway | $0.04 | $0.19 | $0.01 | — | 131K | 33K | — |
| llmgateway-providers · consensusprotocol | $0.04 | $0.19 | $0.01 | — | 128K | 33K | — |
| merge-gateway | $0.04 | $0.15 | $0.02 | — | 128K | 32K | — |
| novita | $0.04 | $0.15 | — | — | 131K | 33K | — |
| ovhcloud · ovhcloud | $0.04 | $0.15 | — | — | 131K | 131K | — |
| siliconflow | $0.04 | $0.18 | — | — | 131K | 8K | — |
| clarifai | $0.045 | $0.18 | — | — | 131K | 16K | — |
| cortecs | $0.045 | $0.167 | — | — | 131K | 131K | — |
| edenai · ovhcloud | $0.05 | $0.18 | — | — | 131K | 33K | — |
| helicone | $0.05 | $0.20 | — | — | 131K | 131K | — |
| ovhcloud | $0.05 | $0.18 | — | — | 131K | 131K | — |
| together_ai | $0.05 | $0.20 | — | — | 131K | 131K | 2026-09-15 |
| io-net | $0.055 | $0.194 | $0.0275 | — | 64K | 4K | — |
| amazon-bedrock | $0.07 | $0.30 | — | — | 131K | 131K | — |
| bedrock_mantle · bedrock-mantle | $0.07 $0.084 | $0.30 $0.36 | — | — | 131K | 16K | — |
| databricks | $0.07 | $0.30 | $0.07 | $0.07 | 131K | 25K 131K | — |
| edenai · arkanecloud | $0.07 | $0.25 | $0.05 | — | 131K | 33K | — |
| fastrouter | $0.07 | $0.25 | $0.007 | — | 131K | 33K | — |
| fireworks_ai | $0.07 | $0.30 | $0.035 | — | 131K | 33K | — |
| frogbot | $0.07 | $0.20 | — | — | 131K | 33K | — |
| neon | $0.07 | $0.30 | — | — | 131K | 25K | — |
| oci | $0.07 | $0.30 | — | — | 128K | 16K | — |
| oci · oci | $0.07 | $0.30 | — | — | 128K | 128K | — |
| prime | $0.07 | $0.30 | — | — | 131K | 33K | — |
| tensormesh · tensormesh | $0.07 | $0.28 | free | — | 131K | 131K | — |
| edenai | $0.075 $0.03 $0.07 $0.20 | $0.30 $0.14 | $0.0375 $0.007 | $0.07 | 131K 128K | 33K | — |
| groq | $0.075 | $0.30 | $0.0375 | — | 131K | 66K | — |
| impossibl | $0.075 $0.07 | $0.30 | $0.0375 $0.035 | — | 131K | 33K | — |
| tempr | $0.075 | $0.30 | $0.0375 | — | 131K | 66K | — |
| aimlapi | $0.0794 | $0.3174 | $0.0397 | — | 131K | 118K | — |
| replicate · replicate | $0.09 | $0.36 | — | — | — | — | — |
| huggingface | $0.10 | $0.50 | — | — | 131K | 33K | — |
| llmgateway-providers | $0.10 | $0.50 | — | — | 131K | 33K | — |
| regolo-ai | $0.1121 | $0.471 | — | — | 128K | 16K | — |
| lowrouter · auto | $0.113 | $0.4745 | — | — | 131K | 33K | — |
| opper | $0.1162 | $0.4881 | — | — | 128K | 8K | — |
| stackit | $0.18 | $0.29 | — | — | 131K | 8K | — |
| thinkingmachines | $0.18 | $0.45 | $0.036 | — | 33K | 33K | — |
| cloudflare | $0.20 | $0.30 | — | — | 128K | 128K | — |
| cloudflare-workers-ai · cf | $0.20 | $0.30 | — | — | 128K | 16K | — |
| qiniu-ai | — | — | — | — | 128K | 4K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | edenai | Cache read | $0.07 |
| 2026-09-02 | edenai | Cache read | $0.007 |
| 2026-09-04 | edenai | Cache read | $0.0375 |
| 2026-10-22 | edenai | Cache read | $0.007 |
| 2026-10-24 | edenai | Cache read | $0.0375 |
| 2026-10-26 | edenai | Cache read | $0.007 |
| 2026-10-31 | edenai | Cache read | $0.0375 |
| 2026-09-02 | impossibl | Cache read | $0.035 |
| 2026-09-04 | impossibl | Cache read | $0.0375 |
| 2026-10-19 | impossibl | Cache read | $0.035 |
| 2026-10-20 | impossibl | Cache read | $0.0375 |
| 2026-10-22 | impossibl | Cache read | $0.035 |
| 2026-10-24 | impossibl | Cache read | $0.0375 |
| 2026-10-26 | impossibl | Cache read | $0.035 |
| 2026-10-28 | impossibl | Cache read | $0.0375 |
| 2026-10-29 | impossibl | Cache read | $0.035 |
| 2026-10-30 | impossibl | Cache read | $0.0375 |
| 2026-10-31 | impossibl | Cache read | $0.035 |
| 2026-11-01 | impossibl | Cache read | $0.0375 |
| 2026-09-02 | io-net | Cache read | $0.015 |
| 2026-10-22 | io-net | Cache read | $0.0275 |
| 2026-09-02 | nano-gpt · tee | Cache read | $0.10 |
| 2026-09-11 | nano-gpt · tee | Cache read | $0.02 |
| 2026-09-02 | openrouter | Cache read | $0.03 |
| 2026-09-19 | openrouter | Cache read | $0.03 |
| 2026-09-23 | openrouter | Cache read | $0.03 |
| 2026-09-29 | openrouter | Cache read | $0.009 |
| 2026-09-30 | openrouter | Cache read | $0.009 |
| 2026-10-10 | openrouter | Cache read | $0.009 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Input | $0.075 |
| 2026-09-09 | bedrock_mantle · bedrock-mantle | Input | $0.075 |
| 2026-09-11 | bedrock_mantle · bedrock-mantle | Input | $0.07 |
| 2026-09-02 | databricks | Input | $0.05 |
| 2026-10-22 | databricks | Input | $0.07 |
| 2026-09-02 | edenai | Input | $0.03 |
| 2026-09-04 | edenai | Input | $0.075 |
| 2026-09-18 | edenai | Input | $0.075 |
| 2026-09-24 | edenai | Input | $0.03 |
| 2026-10-19 | edenai | Input | $0.20 |
| 2026-10-20 | edenai | Input | $0.075 |
| 2026-10-21 | edenai | Input | $0.03 |
| 2026-10-22 | edenai | Input | $0.03 |
| 2026-10-23 | edenai | Input | $0.20 |
| 2026-10-24 | edenai | Input | $0.075 |
| 2026-10-25 | edenai | Input | $0.075 |
| 2026-10-26 | edenai | Input | $0.07 |
| 2026-10-28 | edenai | Input | $0.07 |
| 2026-10-29 | edenai | Input | $0.07 |
| 2026-10-30 | edenai | Input | $0.20 |
| 2026-10-31 | edenai | Input | $0.03 |
| 2026-11-01 | edenai | Input | $0.075 |
| 2026-09-02 | edenai · flexai | Input | $0.02 |
| 2026-09-09 | edenai · flexai | Input | $0.03 |
| 2026-09-24 | edenai · flexai | Input | $0.018 |
| 2026-09-25 | edenai · flexai | Input | $0.02 |
| 2026-09-02 | fastrouter | Input | $0.05 |
| 2026-10-22 | fastrouter | Input | $0.07 |
| 2026-09-02 | impossibl | Input | $0.07 |
| 2026-09-04 | impossibl | Input | $0.075 |
| 2026-10-19 | impossibl | Input | $0.07 |
| 2026-10-20 | impossibl | Input | $0.075 |
| 2026-10-22 | impossibl | Input | $0.07 |
| 2026-10-24 | impossibl | Input | $0.075 |
| 2026-10-26 | impossibl | Input | $0.07 |
| 2026-10-28 | impossibl | Input | $0.075 |
| 2026-10-29 | impossibl | Input | $0.07 |
| 2026-10-30 | impossibl | Input | $0.075 |
| 2026-10-31 | impossibl | Input | $0.07 |
| 2026-11-01 | impossibl | Input | $0.075 |
| 2026-09-02 | io-net | Input | $0.03 |
| 2026-10-22 | io-net | Input | $0.055 |
| 2026-09-02 | kenari | Input | free |
| 2026-10-22 | kenari | Input | $0.036 |
| 2026-09-02 | kilo | Input | $0.02 |
| 2026-09-20 | kilo | Input | $0.018 |
| 2026-09-02 | llmgateway | Input | $0.05 |
| 2026-09-02 | llmgateway | Input | $0.04 |
| 2026-09-02 | llmgateway-providers | Input | $0.05 |
| 2026-09-04 | llmgateway-providers | Input | $0.10 |
| 2026-09-15 | llmgateway-providers | Input | $0.10 |
| 2026-09-02 | nano-gpt | Input | $0.20 |
| 2026-10-19 | nano-gpt | Input | $0.02 |
| 2026-09-02 | nano-gpt · tee | Input | $0.20 |
| 2026-09-11 | nano-gpt · tee | Input | $0.04 |
| 2026-09-02 | neon | Input | $0.05 |
| 2026-09-02 | neon | Input | $0.07 |
| 2026-09-02 | openrouter | Input | $0.03 |
| 2026-09-06 | openrouter | Input | $0.03 |
| 2026-09-23 | openrouter | Input | $0.018 |
| 2026-10-10 | openrouter | Input | $0.018 |
| 2026-09-02 | regolo-ai | Input | $0.40 |
| 2026-10-22 | regolo-ai | Input | $0.1121 |
| 2026-09-02 | together_ai | Input | $0.05 |
| 2026-09-24 | together_ai | Input | $0.05 |
| 2026-09-02 | vercel | Input | $0.05 |
| 2026-09-17 | vercel | Input | $0.03 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Output | $0.30 |
| 2026-09-09 | bedrock_mantle · bedrock-mantle | Output | $0.30 |
| 2026-09-02 | databricks | Output | $0.20 |
| 2026-10-22 | databricks | Output | $0.30 |
| 2026-09-02 | edenai | Output | $0.14 |
| 2026-09-04 | edenai | Output | $0.30 |
| 2026-09-18 | edenai | Output | $0.30 |
| 2026-09-24 | edenai | Output | $0.14 |
| 2026-10-19 | edenai | Output | $0.30 |
| 2026-10-21 | edenai | Output | $0.14 |
| 2026-10-23 | edenai | Output | $0.30 |
| 2026-10-31 | edenai | Output | $0.14 |
| 2026-11-01 | edenai | Output | $0.30 |
| 2026-09-02 | edenai · flexai | Output | $0.10 |
| 2026-09-09 | edenai · flexai | Output | $0.13 |
| 2026-09-24 | edenai · flexai | Output | $0.09 |
| 2026-09-25 | edenai · flexai | Output | $0.10 |
| 2026-09-02 | fastrouter | Output | $0.20 |
| 2026-10-22 | fastrouter | Output | $0.25 |
| 2026-09-02 | io-net | Output | $0.14 |
| 2026-10-22 | io-net | Output | $0.194 |
| 2026-09-02 | kenari | Output | free |
| 2026-10-22 | kenari | Output | $0.1543 |
| 2026-09-02 | kilo | Output | $0.10 |
| 2026-09-20 | kilo | Output | $0.09 |
| 2026-09-02 | llmgateway | Output | $0.20 |
| 2026-09-02 | llmgateway | Output | $0.19 |
| 2026-09-02 | llmgateway-providers | Output | $0.20 |
| 2026-09-04 | llmgateway-providers | Output | $0.50 |
| 2026-09-15 | llmgateway-providers | Output | $0.50 |
| 2026-09-02 | merge-gateway | Output | $0.20 |
| 2026-10-03 | merge-gateway | Output | $0.15 |
| 2026-09-02 | nano-gpt | Output | $0.30 |
| 2026-10-19 | nano-gpt | Output | $0.10 |
| 2026-09-02 | nano-gpt · tee | Output | $0.80 |
| 2026-09-11 | nano-gpt · tee | Output | $0.15 |
| 2026-09-02 | neon | Output | $0.20 |
| 2026-09-02 | neon | Output | $0.30 |
| 2026-09-02 | openrouter | Output | $0.13 |
| 2026-09-06 | openrouter | Output | $0.13 |
| 2026-09-23 | openrouter | Output | $0.09 |
| 2026-10-10 | openrouter | Output | $0.09 |
| 2026-09-02 | regolo-ai | Output | $1.80 |
| 2026-10-22 | regolo-ai | Output | $0.471 |
| 2026-09-02 | together_ai | Output | $0.20 |
| 2026-09-24 | together_ai | Output | $0.20 |
| 2026-09-02 | vercel | Output | $0.20 |
| 2026-09-17 | vercel | Output | $0.14 |
| 2026-09-24 | edenai · flexai | Cache read | $0.0027 |
| 2026-09-25 | edenai · flexai | Cache read | $0.003 |
| 2026-10-13 | aimlapi | Cache read | $0.0516 |
| 2026-10-23 | aimlapi | Cache read | $0.0397 |
| 2026-10-13 | aimlapi | Input | $0.1032 |
| 2026-10-23 | aimlapi | Input | $0.0794 |
| 2026-10-13 | aimlapi | Output | $0.4126 |
| 2026-10-23 | aimlapi | Output | $0.3174 |
More from OpenAI
most-hosted first