Open GPT reasoning model for self-hosted agents and controllable deployments
1 figure withheld: the value failed a range check.
Specification
most-agreed values
Context
131K
Max output
66K
Released
2025-08-05
Knowledge cutoff
2025-09
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.159
Output
$0.636
Cache read
$0.075
Cache write
$0.18
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Priority input | fireworks_ai | $0.18 |
| Priority output | fireworks_ai | $0.72 |
Rate limits
Requests per minute
300
Quality
6 benchmarks · 3 sources
Composite
47th
percentile of 334 scored models
Rank
179 / 334
±0.07 sd
Evidence
6 × 3
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
coding22nd2/3 bench
reasoning50th3/4 bench
math92nd1/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9 ±4.5 | high | Epoch AI | 2025-12-11 |
| GPQA diamond | 75.8 ±2.7 | high | Epoch AI | 2025-12-11 |
| Chess Puzzles | 20.0 ±3.1 | high | Epoch AI | 2025-12-11 |
| Aider polyglot | 41.8 | high · aider diff | Aider | 2025-08-06 |
| Mystery Game Puzzles | 1.0 ±0.0 | default · 2 runs | Epoch AI | 2026-08-27 |
| SWE-Bench verified | 26.0 | default · mini-SWE-agent | SWE-bench | — |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 77 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| kenari | free | free | — | — | 131K | 33K | — |
| nvidia | free | free | — | — | 128K | 8K | — |
| qvac | free | free | — | — | 131K | 33K | — |
| kilo | $0.03 | $0.17 | $0.03 | — | 131K | 118K | — |
| orcarouter | $0.03 | $0.17 | — | — | 131K | 33K | — |
| wandb | $0.03 | $0.17 | $0.03 | — | 131K | 131K | — |
| wandb · wandb | $0.03 | $0.17 | — | — | 131K | 131K | — |
| llmgateway | $0.032 | $0.14 | $0.032 | — | 131K | 33K | — |
| llmgateway-providers · runware | $0.032 | $0.14 | $0.032 | — | 131K | 33K | — |
| deepinfra | $0.037 | $0.17 | — | — | 131K | 16K 131K | — |
| edenai · flexai | $0.037 | $0.17 | — | — | 131K | 33K | — |
| openrouter | $0.037 | $0.17 | — | — | 131K | 118K 33K | — |
| helicone | $0.04 | $0.16 | — | — | 131K | 131K | — |
| io-net | $0.04 | $0.40 | $0.02 | $0.08 | 131K | 4K | — |
| tensorx | $0.04 | $0.20 | $0.01 | $0.05 | 131K | 33K | — |
| crusoe | $0.05 | $0.20 | $0.05 | — | 131K | 33K | — |
| novita | $0.05 | $0.25 | — | — | 131K | 33K | — |
| novita-ai | $0.05 | $0.25 | — | — | 131K | 33K | — |
| siliconflow | $0.05 | $0.45 | — | — | 131K | 8K | — |
| dinference | $0.0675 | $0.27 | — | — | 131K | 33K | — |
| databricks | $0.072 $0.15 | $0.28 $0.60 | $0.15 | $0.15 | 131K | 33K 131K | — |
| abacus | $0.08 | $0.44 | — | — | 128K | 16K | — |
| ovhcloud · ovhcloud | $0.08 | $0.40 | — | — | 131K | 131K | — |
| cortecs | $0.089 | $0.446 | $0.01 | — | 131K | 131K | — |
| edenai · ovhcloud | $0.09 | $0.47 | — | — | 131K | 33K | — |
| merge-gateway | $0.09 | $0.36 | — | — | 131K | 33K | — |
| ovhcloud | $0.09 | $0.47 | — | — | 131K | 131K | — |
| baseten | $0.10 | $0.50 | — | — | 128K | 128K | — |
| llmgateway-providers · bytedance | $0.10 | $0.50 | $0.02 | — | 128K | 32K | — |
| submodel | $0.10 | $0.50 | — | — | 131K | 33K | — |
| vercel | $0.10 | $0.50 | — | — | 131K | 131K | — |
| openreason | $0.1055 | $0.422 | — | — | 131K | 33K | — |
| coralbricks | $0.12 | $0.60 | free | — | 131K | 33K | — |
| aiand | $0.15 | $0.60 | $0.08 | — | 131K | 33K | — |
| aki-io | $0.15 | $0.55 | — | — | 128K | 33K | — |
| amazon-bedrock | $0.15 | $0.60 | — | — | 128K | 16K | — |
| azure_ai | $0.15 | $0.60 | — | — | 131K | 131K | — |
| bedrock_mantle · bedrock-mantle | $0.15 $0.18 | $0.60 $0.72 | — | — | 131K | 33K | — |
| edenai | $0.15 $0.35 $0.037 | $0.60 $0.75 $0.17 | $0.075 $0.15 $0.015 $0.014 $0.35 | $0.15 | 131K 128K | 33K | — |
| fastrouter | $0.15 | $0.60 | — | — | 131K | 33K | — |
| fireworks_ai | $0.15 | $0.60 | $0.015 | — | 131K | 33K | — |
| fireworks-ai · accounts | $0.15 | $0.60 | $0.015 | — | 131K | 33K | — |
| frogbot | $0.15 | $0.60 | — | — | 131K | 33K | — |
| groq | $0.15 | $0.60 | $0.075 | — | 131K | 66K | — |
| impossibl | $0.15 $0.35 | $0.60 $0.75 | $0.075 $0.015 | — | 131K | 33K | — |
| llmgateway-providers | $0.15 $0.35 | $0.75 $0.60 | — | — | 131K | 33K 33K | — |
| nebius | $0.15 | $0.60 | $0.015 | $0.18 | 131K | 8K 131K | — |
| neon | $0.15 | $0.60 | — | — | 131K | 25K | — |
| pioneer | $0.15 | $0.60 | $0.015 | $0.15 | 131K | 131K | — |
| scaleway | $0.15 | $0.60 | — | — | 128K | 33K | — |
| scaleway · scaleway | $0.15 | $0.60 | — | — | 128K | 33K | — |
| tensormesh · tensormesh | $0.15 | $0.60 | free | — | 131K | 131K | — |
| tinfoil | $0.15 | $0.60 | — | — | 131K | 33K | — |
| together_ai | $0.15 | $0.60 | — | — | 131K | — | — |
| togetherai | $0.15 | $0.60 | — | — | 131K | 131K | — |
| watsonx | $0.159 | $0.636 | — | — | 131K | 33K 131K | — |
| llmgateway-providers · scx-ai | $0.17 | $0.55 | — | — | 131K | 33K | — |
| scx-ai | $0.17 | $0.55 | — | — | 131K | 131K | — |
| edenai · ionos | $0.1733 | $0.7508 | — | — | 131K | 33K | — |
| edenai · scaleway | $0.1733 | $0.6931 | — | — | 128K | 33K | — |
| hyper | $0.178 | $0.68 | $0.089 | — | 128K | 13K | — |
| replicate · replicate | $0.18 | $0.72 | — | — | — | — | — |
| sambanova · sambanova | $0.22 | $0.59 | — | — | 131K | 131K | — |
| greenpt | $0.228 | $0.798 | — | — | 131K | 33K | — |
| evroc | $0.23 | $0.92 | — | — | 66K | 66K | — |
| huggingface | $0.25 | $0.69 | — | — | 131K | 33K | — |
| cerebras | $0.35 | $0.75 | — | — | 131K | 41K 33K | — |
| cloudflare | $0.35 | $0.75 | — | — | 128K | 128K | — |
| cloudflare-workers-ai · cf | $0.35 | $0.75 | — | — | 128K | 16K | — |
| nano-gpt | $0.35 | $0.75 | — | — | 128K | 16K | — |
| privatemode-ai | $0.4969 | $1.9644 | $0.0462 | — | 128K | 33K | — |
| stackit | $0.53 | $0.76 | — | — | 131K | 8K | — |
| crusoe · crusoe | $0.80 | $0.80 | — | — | 131K | 131K | — |
| regolo-ai | $1.00 | $4.20 | — | — | 128K | 16K | — |
| nano-gpt · tee | $2.00 | $2.00 | $2.00 | — | 131K | 16K | — |
| cloudferro-sherlock | $2.92 | $2.92 | — | — | 131K | 131K | — |
| 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 | $0.15 |
| 2026-09-02 | edenai | Cache read | $0.015 |
| 2026-09-04 | edenai | Cache read | $0.075 |
| 2026-09-02 | impossibl | Cache read | $0.015 |
| 2026-09-04 | impossibl | Cache read | $0.075 |
| 2026-09-02 | hyper | Cache write | $0.095 |
| 2026-09-02 | hyper | Cache write | $0.094 |
| 2026-09-09 | hyper | Cache write | $0.089 |
| 2026-09-10 | hyper | Cache write | $0.09 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Input | $0.15 |
| 2026-09-09 | bedrock_mantle · bedrock-mantle | Input | $0.15 |
| 2026-09-02 | edenai | Input | $0.037 |
| 2026-09-04 | edenai | Input | $0.15 |
| 2026-09-02 | edenai · flexai | Input | $0.039 |
| 2026-09-09 | edenai · flexai | Input | $0.037 |
| 2026-09-02 | edenai · ionos | Input | $0.1739 |
| 2026-09-02 | edenai · ionos | Input | $0.1737 |
| 2026-09-04 | edenai · ionos | Input | $0.1742 |
| 2026-09-05 | edenai · ionos | Input | $0.1743 |
| 2026-09-09 | edenai · ionos | Input | $0.1742 |
| 2026-09-10 | edenai · ionos | Input | $0.1748 |
| 2026-09-11 | edenai · ionos | Input | $0.1742 |
| 2026-09-12 | edenai · ionos | Input | $0.1739 |
| 2026-09-15 | edenai · ionos | Input | $0.1733 |
| 2026-09-02 | edenai · scaleway | Input | $0.1739 |
| 2026-09-02 | edenai · scaleway | Input | $0.1737 |
| 2026-09-04 | edenai · scaleway | Input | $0.1742 |
| 2026-09-05 | edenai · scaleway | Input | $0.1743 |
| 2026-09-09 | edenai · scaleway | Input | $0.1742 |
| 2026-09-10 | edenai · scaleway | Input | $0.1748 |
| 2026-09-11 | edenai · scaleway | Input | $0.1742 |
| 2026-09-12 | edenai · scaleway | Input | $0.1739 |
| 2026-09-15 | edenai · scaleway | Input | $0.1733 |
| 2026-09-02 | hyper | Input | $0.19 |
| 2026-09-02 | hyper | Input | $0.188 |
| 2026-09-09 | hyper | Input | $0.178 |
| 2026-09-10 | hyper | Input | $0.18 |
| 2026-09-11 | hyper | Input | $0.178 |
| 2026-09-12 | hyper | Input | $0.168 |
| 2026-09-15 | hyper | Input | $0.178 |
| 2026-09-02 | nebius | Input | $0.15 |
| 2026-09-06 | nebius | Input | $0.15 |
| 2026-09-02 | neon | Input | $0.072 |
| 2026-09-02 | neon | Input | $0.15 |
| 2026-09-02 | openrouter | Input | $0.037 |
| 2026-09-06 | openrouter | Input | $0.037 |
| 2026-09-02 | watsonx | Input | $0.159 |
| 2026-09-06 | watsonx | Input | $0.159 |
| 2026-09-02 | bedrock_mantle · bedrock-mantle | Output | $0.60 |
| 2026-09-09 | bedrock_mantle · bedrock-mantle | Output | $0.60 |
| 2026-09-02 | edenai | Output | $0.17 |
| 2026-09-04 | edenai | Output | $0.60 |
| 2026-09-02 | edenai · flexai | Output | $0.10 |
| 2026-09-09 | edenai · flexai | Output | $0.17 |
| 2026-09-02 | edenai · ionos | Output | $0.7533 |
| 2026-09-02 | edenai · ionos | Output | $0.7526 |
| 2026-09-04 | edenai · ionos | Output | $0.755 |
| 2026-09-05 | edenai · ionos | Output | $0.7554 |
| 2026-09-09 | edenai · ionos | Output | $0.7549 |
| 2026-09-10 | edenai · ionos | Output | $0.7574 |
| 2026-09-11 | edenai · ionos | Output | $0.755 |
| 2026-09-12 | edenai · ionos | Output | $0.7535 |
| 2026-09-15 | edenai · ionos | Output | $0.7508 |
| 2026-09-02 | edenai · scaleway | Output | $0.6954 |
| 2026-09-02 | edenai · scaleway | Output | $0.6947 |
| 2026-09-04 | edenai · scaleway | Output | $0.6969 |
| 2026-09-05 | edenai · scaleway | Output | $0.6973 |
| 2026-09-09 | edenai · scaleway | Output | $0.6968 |
| 2026-09-10 | edenai · scaleway | Output | $0.6991 |
| 2026-09-11 | edenai · scaleway | Output | $0.697 |
| 2026-09-12 | edenai · scaleway | Output | $0.6955 |
| 2026-09-15 | edenai · scaleway | Output | $0.6931 |
| 2026-09-02 | hyper | Output | $0.63 |
| 2026-09-02 | hyper | Output | $0.70 |
| 2026-09-09 | hyper | Output | $0.68 |
| 2026-09-10 | hyper | Output | $0.61 |
| 2026-09-11 | hyper | Output | $0.68 |
| 2026-09-12 | hyper | Output | $0.66 |
| 2026-09-15 | hyper | Output | $0.68 |
| 2026-09-02 | llmgateway-providers | Output | $0.60 |
| 2026-09-04 | llmgateway-providers | Output | $0.75 |
| 2026-09-02 | nebius | Output | $0.60 |
| 2026-09-06 | nebius | Output | $0.60 |
| 2026-09-02 | neon | Output | $0.28 |
| 2026-09-02 | neon | Output | $0.60 |
| 2026-09-02 | openrouter | Output | $0.17 |
| 2026-09-06 | openrouter | Output | $0.17 |
| 2026-09-02 | watsonx | Output | $0.636 |
| 2026-09-06 | watsonx | Output | $0.636 |
| 2026-09-11 | hyper | Cache read | $0.089 |
| 2026-09-12 | hyper | Cache read | $0.084 |
| 2026-09-15 | hyper | Cache read | $0.089 |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first